![[International Conference on Machine Learning Logo]](/v267/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, Canada
[edit]
Editors: Aarti Singh, Maryam Fazel, Daniel Hsu, Simon Lacoste-Julien, Felix Berkenkamp, Tegan Maharaj, Kiri Wagstaff, Jerry Zhu
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1-26
Lightweight Protocols for Distributed Private Quantile Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27-58
Breaking the $n^1.5$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59-72
Improved Approximations for Hard Graph Problems using Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73-101
Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:102-125
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:126-153
Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:154-173
Consensus Is All You Get: The Role of Attention in Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:174-184
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:185-203
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:204-230
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:231-245
EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:246-355
Star Attention: Efficient LLM Inference over Long Sequences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:356-371
Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:372-419
Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:420-443
An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:444-459
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:460-476
Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:477-498
Design Considerations in Offline Preference-based RL
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:499-512
Optimal Fair Learning Robust to Adversarial Distribution Shift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:513-530
FedECADO: A Dynamical System Model of Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:531-549
The Missing Alignment Link of In-context Learning on Sequences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:550-565
Proto Successor Measure: Representing the Behavior Space of an RL Agent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:566-586
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:587-615
NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:616-638
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:639-661
Understanding the difficulties of posterior predictive estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:662-702
Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:703-729
Online Laplacian-Based Representation Learning in Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:730-751
Otter: Generating Tests from Issues to Validate SWE Patches
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:752-771
General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:772-795
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:796-808
Vision Graph Prompting via Semantic Low-Rank Decomposition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:809-821
An Instrumental Value for Data Production and its Application to Data Pricing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:822-856
Simple Path Structural Encoding for Graph Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:857-873
Implicit degree bias in the link prediction task
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:874-908
Nesterov Method for Asynchronous Pipeline Parallel Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:909-924
When, Where and Why to Average Weights?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:925-941
The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:942-963
A Tale of Two Structures: Do LLMs Capture the Fractal Complexity of Language?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:964-1025
NETS: A Non-equilibrium Transport Sampler
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1026-1055
Prediction via Shapley Value Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1056-1101
Differentiable Quadratic Optimization For the Maximum Independent Set Problem
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1102-1127
SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1128-1158
Direct Motion Models for Assessing Generated Videos
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1159-1183
Towards Trustworthy Federated Learning with Untrusted Participants
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1184-1227
Subgroups Matter for Robust Bias Mitigation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1228-1249
Aligning Multimodal Representations through an Information Bottleneck
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1250-1270
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1271-1297
Explaining the role of Intrinsic Dimensionality in Adversarial Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1298-1313
The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1314-1342
Continuously Updating Digital Twins using Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1343-1366
Determinant Estimation under Memory Constraints and Neural Scaling Laws
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1367-1400
Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1401-1418
Generalization and Robustness of the Tilted Empirical Risk
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1419-1461
Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1462-1482
Graph-Based Algorithms for Diverse Similarity Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1483-1504
Pixel-level Certified Explanations via Randomized Smoothing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1505-1533
Private Lossless Multiple Release
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1534-1553
A Reasoning-Based Approach to Cryptic Crossword Clue Solving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1554-1573
Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1574-1603
Online Conformal Prediction via Online Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1604-1649
Revisiting Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1650-1689
Aligning LLMs by Predicting Preferences from User Writing Samples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1690-1721
Gridded Transformer Neural Processes for Spatio-Temporal Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1722-1761
LLMs can see and hear without any training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1762-1776
Tracking The Best Expert Privately
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1777-1795
Faster Rates for Private Adversarial Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1796-1832
Improving the Scaling Laws of Synthetic Data with Deliberate Practice
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1833-1863
Autoformulation of Mathematical Optimization Models Using LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1864-1886
Risk and cross validation in ridge regression with correlated samples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1887-1930
Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1931-1949
PAC Learning with Improvements
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1950-1981
The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:1982-2044
Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2045-2080
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2081-2113
Near-Optimal Decision Trees in a SPLIT Second
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2114-2175
Adaptive Estimation and Learning under Temporal Distribution Shift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2176-2202
Contract Design Under Approximate Best Responses
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2203-2220
Sampling Binary Data by Denoising through Score Functions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2221-2240
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2241-2292
A Parametric Contextual Online Learning Theory of Brokerage
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2293-2309
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2310-2334
Positional Attention: Expressivity and Learnability of Algorithmic Computation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2335-2390
Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2391-2408
Active Fine-Tuning of Multi-Task Policies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2409-2441
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2442-2457
Impossible Videos
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2458-2483
KoNODE: Koopman-Driven Neural Ordinary Differential Equations with Evolving Parameters for Time Series Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2484-2519
SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2520-2534
Multivariate Conformal Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2535-2559
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2560-2580
Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2581-2602
Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2603-2645
InfAlign: Inference-aware language model alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2646-2672
Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2673-2696
Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2697-2714
Causal Discovery from Conditionally Stationary Time Series
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2715-2741
MathConstruct: Challenging LLM Reasoning with Constructive Proofs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2742-2769
On Measuring Long-Range Interactions in Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2770-2789
Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2790-2800
Differentiable Structure Learning with Ancestral Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2801-2835
CRANE: Reasoning with constrained LLM generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2836-2857
BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2858-2893
Fully Dynamic Embedding into $\ell_p$ Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2894-2909
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2910-2929
Visual and Domain Knowledge for Professional-level Graph-of-Thought Medical Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2930-2952
QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2953-2967
Ehrenfeucht-Haussler Rank and Chain of Thought
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2968-2977
Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:2978-3002
Feature Shift Localization Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3003-3029
On Volume Minimization in Conformal Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3030-3053
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3054-3070
A Certified Unlearning Approach without Access to Source Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3071-3090
Robust Conformal Outlier Detection under Contaminated Reference Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3091-3141
What makes an Ensemble (Un) Interpretable?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3142-3201
Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3202-3225
Competing Bandits in Matching Markets via Super Stability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3226-3250
Zero Shot Generalization of Vision-Based RL Without Data Augmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3251-3273
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3274-3306
Grokking at the Edge of Linear Separability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3307-3334
xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3335-3357
RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3358-3392
Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3393-3472
Correlation Clustering Beyond the Pivot Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3473-3499
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3500-3532
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3533-3561
Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3562-3579
Theoretical guarantees on the best-of-n alignment policy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3580-3602
The Generalized Skew Spectrum of Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3603-3622
The Limits of Predicting Agents from Behaviour
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3623-3658
Distilling the Knowledge in Data Pruning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3659-3676
Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3677-3711
A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3712-3730
AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3731-3748
Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3749-3775
Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3776-3805
Puzzle: Distillation-Based NAS for Inference-Optimized LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3806-3830
Memory Layers at Scale
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3831-3842
Global curvature for second-order optimization of neural networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3843-3876
No-Regret is not enough! Bandits with General Constraints through Adaptive Regret Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3877-3898
Online Learning in the Random-Order Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3899-3919
Modular Duality in Deep Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3920-3930
Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3931-3951
Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3952-3975
Geometry-Informed Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3976-4004
Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4005-4019
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4020-4042
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4043-4068
Whitened CLIP as a Likelihood Surrogate of Images and Captions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4069-4095
Highly Compressed Tokenizer Can Generate Without Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4096-4114
Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4115-4129
Multiaccuracy and Multicalibration via Proxy Groups
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4130-4152
AtlasD: Automatic Local Symmetry Discovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4153-4171
Multi-Objective Causal Bayesian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4172-4195
Almost Optimal Fully Dynamic $k$-Center Clustering with Recourse
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4196-4209
Learning multivariate Gaussians with imperfect advice
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4210-4252
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4253-4267
Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4268-4288
IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4289-4302
Scaling Inference-Efficient Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4303-4323
Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4324-4344
Rethinking Aleatoric and Epistemic Uncertainty
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4345-4359
DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4360-4383
The dark side of the forces: assessing non-conservative force models for atomistic machine learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4384-4414
Learning Likelihood-Free Reference Priors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4415-4434
ENSUR: Equitable and Statistically Unbiased Recommendation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4435-4454
Universal Approximation of Mean-Field Models via Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4455-4470
False Coverage Proportion Control for Conformal Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4471-4481
Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4482-4506
GaussMark: A Practical Approach for Structural Watermarking of Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4507-4569
Probably Approximately Global Robustness Certification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4570-4587
Point Cloud Dataset Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4588-4601
Physics-Informed Generative Modeling of Wireless Channels
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4602-4626
Generative Social Choice: The Next Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4627-4659
Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4660-4699
A Variational Perspective on Generative Protein Fitness Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4700-4712
Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4713-4736
DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4737-4756
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4757-4790
Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4791-4822
Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4823-4838
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4839-4873
Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4874-4910
Flowing Datasets with Wasserstein over Wasserstein Gradient Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4911-4967
Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4968-4997
How Much Can We Forget about Data Contamination?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4998-5016
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5017-5044
On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5045-5100
Reinforcement Learning with Random Time Horizons
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5101-5123
On the Query Complexity of Verifier-Assisted Language Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5124-5155
Quantifying Treatment Effects: Estimating Risk Ratios via Observational Studies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5156-5217
Learning to Match Unpaired Data with Minimum Entropy Coupling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5218-5240
Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5241-5275
AutoEval Done Right: Using Synthetic Data for Model Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5276-5290
BARK: A Fully Bayesian Tree Kernel for Black-box Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5291-5318
Mechanisms of Projective Composition of Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5319-5354
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5355-5382
DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5383-5417
Relative Error Fair Clustering in the Weak-Strong Oracle Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5418-5453
Learning-Augmented Hierarchical Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5454-5507
Integer Programming for Generalized Causal Bootstrap Designs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5508-5530
E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5531-5557
Cross-regularization: Adaptive Model Complexity through Validation Gradients
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5558-5577
The Limits of Tractable Marginalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5578-5593
Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5594-5614
Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5615-5648
Ergodic Generative Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5649-5668
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5669-5724
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5725-5748
NEAR: Neural Electromagnetic Array Response
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5749-5774
ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5775-5792
Competitively Consistent Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5793-5810
O-MAPL: Offline Multi-agent Preference Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5811-5841
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5842-5855
Understanding and Improving Length Generalization in Recurrent Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5856-5874
Deep Reinforcement Learning from Hierarchical Preference Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5875-5893
Accurate and Efficient World Modeling with Masked Latent Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5894-5912
Distributed Differentially Private Data Analytics via Secure Sketching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5913-5942
Nearly Optimal Sample Complexity for Learning with Label Proportions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5943-5976
Distillation Scaling Laws
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:5977-6045
Where is the Truth? The Risk of Getting Confounded in a Continual World
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6046-6076
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6077-6101
On Efficient Estimation of Distributional Treatment Effects under Covariate-Adaptive Randomization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6102-6125
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6126-6148
Learning curves theory for hierarchically compositional data with power-law distributed features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6149-6164
GEFA: A General Feature Attribution Framework Using Proxy Gradient Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6165-6192
HyperNear: Unnoticeable Node Injection Attacks on Hypergraph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6193-6210
Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6211-6228
From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6229-6242
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6243-6256
Targeted Unlearning with Single Layer Unlearning Gradient
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6257-6290
Attention-Level Speculation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6291-6318
Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6319-6340
Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6341-6365
Understanding the Limits of Deep Tabular Methods with Temporal Shift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6366-6386
Self-Discriminative Modeling for Anomalous Graph Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6387-6408
Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6409-6425
Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6426-6504
From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6505-6521
Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6522-6542
EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6543-6553
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6554-6576
Adversarial Robust Generalization of Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6577-6614
AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6615-6633
CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6634-6653
Open-Det: An Efficient Learning Framework for Open-Ended Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6654-6674
MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6675-6698
Prediction-Aware Learning in Multi-Agent Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6699-6725
Learning Safe Control via On-the-Fly Bandit Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6726-6745
AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6746-6777
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6778-6793
Signed Laplacians for Constrained Graph Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6794-6810
Low-Rank Thinning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6811-6848
Discovering Symbolic Cognitive Models from Human and Animal Behavior
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6849-6890
A Theoretical Framework For Overfitting In Energy-based Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6891-6919
The impact of uncertainty on regularized learning in games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6920-6957
DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6958-6977
A Mathematical Framework for AI-Human Integration in Work
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:6978-7012
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7013-7034
Large Language Models to Diffusion Finetuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7035-7057
Variational Learning of Fractional Posteriors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7058-7088
Transfer Q-Learning with Composite MDP Structures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7089-7106
On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7107-7130
TabSDS: a Lightweight, Fully Non-Parametric, and Model Free Approach for Generating Synthetic Tabular Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7131-7195
SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7196-7213
Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic Variables
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7214-7249
A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7250-7275
RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7276-7305
Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7306-7331
A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7332-7350
LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7351-7360
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7361-7373
LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7374-7392
Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7393-7416
Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7417-7429
Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO*
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7430-7484
Text-to-LoRA: Instant Transformer Adaption
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7485-7514
Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7515-7554
A Closer Look at Multimodal Representation Collapse
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7555-7577
Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7578-7594
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7595-7616
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7617-7633
LEVIS: Large Exact Verifiable Input Spaces for Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7634-7647
De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7648-7663
Learning Safety Constraints for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7664-7685
Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7686-7718
Subobject-level Image Tokenization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7719-7738
On the Power of Learning-Augmented Search Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7739-7762
A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7763-7780
Exploring Invariance in Images through One-way Wave Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7781-7815
PASS: Private Attributes Protection with Stochastic Data Substitution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7816-7839
Breaking Barriers: Combinatorial Algorithms for Non-Monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7840-7879
Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7880-7911
How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7912-7933
DLP: Dynamic Layerwise Pruning in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7934-7956
Scalable Private Partition Selection via Adaptive Weighting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7957-7981
SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7982-8001
KinDEL: DNA-Encoded Library Dataset for Kinase Inhibitors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8002-8021
Exogenous Isomorphism for Counterfactual Identifiability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8022-8064
Efficient Core-set Selection for Deep Learning Through Squared Loss Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8065-8076
Low-Rank Adapting Models for Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8077-8092
RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8093-8107
GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8108-8122
Volume-Aware Distance for Robust Similarity Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8123-8144
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8145-8171
Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8172-8183
CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8184-8211
AffinityFlow: Guided Flows for Antibody Affinity Maturation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8212-8225
A Variational Framework for Improving Naturalness in Generative Spoken Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8226-8244
MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8245-8260
Cross-City Latent Space Alignment for Consistency Region Embedding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8261-8274
Visual Generation Without Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8275-8295
RelGNN: Composite Message Passing for Relational Deep Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8296-8312
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8313-8344
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8345-8363
Language Models as Implicit Tree Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8364-8385
Contrastive Localized Language-Image Pre-Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8386-8402
Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8403-8426
Dequantified Diffusion-Schrödinger Bridge for Density Ratio Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8427-8452
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8453-8479
Learning with Selectively Labeled Data from Multiple Decision-makers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8480-8519
A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8520-8529
C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8530-8551
Falcon: Fast Visuomotor Policies via Partial Denoising
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8552-8573
Deep Principal Support Vector Machines for Nonlinear Sufficient Dimension Reduction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8574-8593
Retraining-free Merging of Sparse MoE via Hierarchical Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8594-8620
Non-Asymptotic Length Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8621-8682
Learnware Specification via Dual Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8683-8699
ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8700-8725
TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8726-8759
Nested Expectations with Kernel Quadrature
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8760-8793
Multiple-policy Evaluation via Density Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8794-8820
Information Bottleneck-guided MLPs for Robust Spatial-temporal Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8821-8855
Optimal Survey Design for Private Mean Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8856-8870
An Effective and Secure Federated Multi-View Clustering Method with Information-Theoretic Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8871-8889
DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8890-8909
Rethinking the Bias of Foundation Model under Long-tailed Distribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8910-8930
Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8931-8954
Conformal Tail Risk Control for Large Language Model Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8955-8978
VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:8979-9007
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9008-9028
Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9029-9072
Rethinking Time Encoding via Learnable Transformation Functions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9073-9104
Unbiased Evaluation of Large Language Models from a Causal Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9105-9120
OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9121-9145
Causal Logistic Bandits with Counterfactual Fairness Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9146-9175
Graph Generative Pre-trained Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9176-9197
Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9198-9230
Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9231-9276
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9277-9294
AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9295-9315
De-mark: Watermark Removal in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9316-9333
Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9334-9353
Stable Fair Graph Representation Learning with Lipschitz Constraint
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9354-9376
Learning without Isolation: Pathway Protection for Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9377-9399
Oscillation-Reduced MXFP4 Training for Vision Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9400-9414
Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9415-9442
Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9443-9486
Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9487-9499
Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9500-9515
An All-Atom Generative Model for Designing Protein Complexes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9516-9545
Discriminative Policy Optimization for Token-Level Reward Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9546-9565
Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9566-9589
Learn Singularly Perturbed Solutions via Homotopy Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9590-9613
Global Convergence and Rich Feature Learning in $L$-Layer Infinite-Width Neural Networks under $μ$ Parametrization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9614-9641
Learning Configurations for Data-Driven Multi-Objective Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9642-9663
Hierarchical Graph Tokenization for Molecule-Language Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9664-9690
Core Context Aware Transformers for Long Context Language Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9691-9710
Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9711-9727
Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9728-9746
A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9747-9763
Convergence of Consistency Model with Multistep Sampling under General Data Assumptions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9764-9782
Gaussian Mixture Flow Matching Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9783-9802
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9803-9817
Asymmetric Decision-Making in Online Knowledge Distillation: Unifying Consensus and Divergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9818-9828
On the Convergence of Continuous Single-timescale Actor-critic
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9829-9859
OmniArch: Building Foundation Model for Scientific Computing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9860-9887
FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9888-9909
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9910-9932
ExtPose: Robust and Coherent Pose Estimation by Extending ViTs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9933-9946
Tool Unlearning for Tool-Augmented LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9947-9963
Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9964-9981
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:9982-10009
Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10010-10024
TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10025-10089
Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10090-10105
A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10106-10120
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10121-10143
Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10144-10158
Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10159-10181
EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10182-10198
SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10199-10215
Adaptive Sample Sharing for Multi Agent Linear Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10216-10248
BILBO: BILevel Bayesian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10249-10268
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10269-10333
Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10334-10353
Copilot Arena: A Platform for Code LLM Evaluation in the Wild
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10354-10382
Empowering World Models with Reflection for Embodied Video Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10383-10410
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10411-10427
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10428-10448
SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10449-10468
Mixed-curvature decision trees and random forests
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10469-10498
Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10499-10523
Policy-labeled Preference Learning: Is Preference Enough for RLHF?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10524-10553
One-Step Generalization Ratio Guided Optimization for Domain Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10554-10582
ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10583-10601
Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10602-10643
Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10644-10665
How Contaminated Is Your Benchmark? Measuring Dataset Leakage in Large Language Models with Kernel Divergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10666-10682
A Hitchhiker’s Guide to Scaling Law Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10683-10699
Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10700-10740
Linear convergence of Sinkhorn’s algorithm for generalized static Schrödinger bridge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10741-10767
Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10768-10800
Fine-Grained Captioning of Long Videos through Scene Graph Consolidation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10801-10817
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10818-10838
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10839-10858
Learning to Route LLMs with Confidence Tokens
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10859-10878
Unifying Specialized Visual Encoders for Video Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10879-10900
WMAdapter: Adding WaterMark Control to Latent Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10901-10919
Objective drives the consistency of representational similarity across datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10920-10948
Relational Conformal Prediction for Correlated Time Series
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10949-10965
Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10966-10993
Optimization for Neural Operators can Benefit from Width
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10994-11041
Sample Complexity of Branch-length Estimation by Maximum Likelihood
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11042-11063
Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11064-11091
Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11092-11141
Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11142-11172
The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11173-11184
Breaking the Quadratic Barrier: Robust Cardinality Sketches for Adaptive Queries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11185-11199
Algorithms and Hardness for Active Learning on Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11200-11214
Kinetic Langevin Diffusion for Crystalline Materials Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11215-11244
Counterfactual Graphical Models: Constraints and Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11245-11254
Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11255-11287
Winner-takes-all for Multivariate Probabilistic Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11288-11312
Data-driven Design of Randomized Control Trials with Guaranteed Treatment Effects
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11313-11327
FAB-PPI: Frequentist, Assisted by Bayes, Prediction-Powered Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11328-11356
Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11357-11378
BARNN: A Bayesian Autoregressive and Recurrent Neural Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11379-11404
No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11405-11434
Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11435-11464
Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11465-11492
Prediction-Powered E-Values
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11493-11514
OR-Bench: An Over-Refusal Benchmark for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11515-11542
Improving Soft Unification with Knowledge Graph Embedding Methods
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11543-11562
Calibrating Video Watch-time Predictions with Credible Prototype Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11563-11584
An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11585-11603
InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11604-11619
Human Cognition-Inspired Hierarchical Fuzzy Learning Machine
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11620-11648
Enhancing Target-unspecific Tasks through a Features Matrix
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11649-11661
Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11662-11691
Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11692-11709
Robust Autonomy Emerges from Self-Play
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11710-11737
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11738-11775
Causal Abstraction Learning based on the Semantic Embedding Principle
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11776-11812
On Temperature Scaling and Conformal Prediction of Deep Classifiers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11813-11845
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11846-11861
Generalization of noisy SGD in unbounded non-convex settings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11862-11883
Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11884-11903
CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11904-11953
Adapting to Evolving Adversaries with Regularized Continual Robust Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11954-12000
EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12001-12021
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model’s Parameter-Efficient Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12022-12046
Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12047-12062
From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12063-12083
Learning With Multi-Group Guarantees For Clusterable Subpopulations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12084-12105
Confidence Difference Reflects Various Supervised Signals in Confidence-Difference Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12106-12120
MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12121-12160
Latent Variable Causal Discovery under Selection Bias
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12161-12178
Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12179-12213
MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12214-12228
Policy Gradient with Tree Expansion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12229-12255
Sparse-pivot: Dynamic correlation clustering for node insertions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12256-12279
Efficient Noise Calculation in Deep Learning-based MRI Reconstructions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12280-12313
Online Robust Reinforcement Learning Through Monte-Carlo Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12314-12343
Power Mean Estimation in Stochastic Continuous Monte-Carlo Tree Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12344-12376
Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12377-12401
Shifting Time: Time-series Forecasting with Khatri-Rao Neural Operators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12402-12435
Efficiently Vectorized MCMC on Modern Accelerators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12436-12458
Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12459-12489
Online Sparsification of Bipartite-Like Clusters in Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12490-12508
Retraining with Predicted Hard Labels Provably Increases Model Accuracy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12509-12538
A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12539-12553
Learning Gaussian DAG Models without Condition Number Bounds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12554-12589
Accelerated Diffusion Models via Speculative Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12590-12631
Distributional Diffusion Models with Scoring Rules
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12632-12676
EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully Homomorphic Encryption
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12677-12688
Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12689-12717
Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12718-12738
Provable Maximum Entropy Manifold Exploration via Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12739-12761
Breaking the Barrier of Hard Samples: A Data-Centric Approach to Synthetic Data for Medical Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12762-12815
Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12816-12839
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12840-12900
Trust-Region Twisted Policy Improvement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12901-12923
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12924-12943
Improving Transformer World Models for Data-Efficient RL
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12944-12968
An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12969-12986
A Unified Approach to Routing and Cascading for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:12987-13010
Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13011-13043
Learning Distribution-wise Control in Representation Space for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13044-13068
Towards Understanding Parametric Generalized Category Discovery on Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13069-13109
FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13110-13128
Predicting mutational effects on protein binding from folding energy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13129-13151
Procurement Auctions via Approximately Optimal Submodular Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13152-13180
Discrepancy Minimization in Input-Sparsity Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13181-13236
EGPlace: An Efficient Macro Placement Method via Evolutionary Search with Greedy Repositioning Guided Mutation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13237-13255
A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13256-13276
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13277-13326
EvoMesh: Adaptive Physical Simulation with Hierarchical Graph Evolutions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13327-13346
QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13347-13368
Theoretical Limitations of Ensembles in the Age of Overparameterization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13369-13401
HashAttention: Semantic Sparsity for Faster Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13402-13418
Compressing tree ensembles through Level-wise Optimization and Pruning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13419-13443
A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13444-13485
Continuous Bayesian Model Selection for Multivariate Causal Discovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13486-13512
Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13513-13545
Optimizing Adaptive Attacks against Watermarks for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13546-13569
Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13570-13600
On Learning Parallel Pancakes with Mostly Uniform Weights
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13601-13621
Batch List-Decodable Linear Regression via Higher Moments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13622-13642
On Fine-Grained Distinct Element Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13643-13678
Online Linear Classification with Massart Noise
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13679-13692
Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13693-13712
On Zero-Initialized Attention: Optimal Prompt and Gating Factor Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13713-13745
Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13746-13773
MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13774-13813
Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13814-13824
Visual Abstraction: A Plug-and-Play Approach for Text-Visual Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13825-13844
NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13845-13869
BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13870-13884
LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13885-13899
Ad-Hoc Human-AI Coordination Challenge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13900-13937
Leveraging Randomness in Model and Data Partitioning for Privacy Amplification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13938-13962
Maximum Entropy Reinforcement Learning with Diffusion Policy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13963-13983
Enhancing Decision-Making of Large Language Models via Actor-Critic
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:13984-14020
In-Context Reinforcement Learning From Suboptimal Historical Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14021-14039
Exactly Tight Information-theoretic Generalization Bounds via Binary Jensen-Shannon Divergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14040-14060
Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14061-14078
Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14079-14113
STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14114-14136
Permutation-based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14137-14151
Maintaining Proportional Committees with Dynamic Candidate Sets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14152-14168
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14169-14202
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14203-14230
Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14231-14259
A Lens into Interpretable Transformer Mistakes via Semantic Dependency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14260-14284
ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14285-14300
Emergent Response Planning in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14301-14320
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14321-14343
ADDQ: Adaptive distributional double Q-learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14344-14390
Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14391-14416
On the Importance of Embedding Norms in Self-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14417-14438
Sleeping Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14439-14498
Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14499-14514
Long-Short Alignment for Effective Long-Context Modeling in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14515-14535
Enabling Optimal Decisions in Rehearsal Learning under CARE Condition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14536-14561
Telling Peer Direct Effects from Indirect Effects in Observational Network Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14562-14578
Textual Unlearning Gives a False Sense of Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14579-14597
Reinforcement Learning with Segment Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14598-14647
Optimizing Temperature for Language Models with Multi-Sample Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14648-14668
Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14669-14681
Unsupervised Learning for Class Distribution Mismatch
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14682-14718
Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14719-14734
Deep Fuzzy Multi-view Learning for Reliable Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14735-14758
CoPINN: Cognitive Physics-Informed Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14759-14777
Unnatural Languages Are Not Bugs but Features for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14778-14792
MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14793-14806
DIS-CO: Discovering Copyrighted Content in VLMs Training Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14807-14832
Weakly Supervised Anomaly Detection via Dual-Tailed Kernel
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14833-14866
IT$^3$: Idempotent Test-Time Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14867-14883
SPHINX: Structural Prediction using Hypergraph Inference Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14884-14901
LASER: Attention with Exponential Transformation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14902-14917
Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14918-14933
Partially Observable Reinforcement Learning with Memory Traces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14934-14949
Not All Wrong is Bad: Using Adversarial Examples for Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14950-14971
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14972-14988
Aligned Multi Objective Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14989-15017
On the Importance of Gaussianizing Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15018-15037
Mind the Gap: A Practical Attack on GGUF Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15038-15065
Controlled Generation with Equivariant Variational Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15066-15078
A Market for Accuracy: Classification Under Competition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15079-15104
Enhancing Parallelism in Decentralized Stochastic Convex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15105-15129
WyckoffDiff – A Generative Diffusion Model for Crystal Symmetry
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15130-15147
Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15148-15181
Learn to Vaccinate: Combining Structure Learning and Effective Vaccination for Epidemic and Outbreak Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15182-15214
any4: Learned 4-bit Numeric Representation for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15215-15231
Graph Adaptive Autoregressive Moving Average Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15232-15265
Towards a Formal Theory of Representational Compositionality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15266-15295
In-Context Learning and Occam’s Razor
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15296-15319
Observation Interference in Partially Observable Assistance Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15320-15345
Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15346-15369
Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15370-15383
Distributed Event-Based Learning via ADMM
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15384-15418
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15419-15462
Reinforcement Learning for Quantum Control under Physical Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15463-15489
Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15490-15515
Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15516-15541
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15542-15563
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15564-15595
Regression for the Mean: Auto-Evaluation and Inference with Few Labels through Post-hoc Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15596-15612
Understanding Complexity in VideoQA via Visual Program Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15613-15636
Learning Mean Field Control on Sparse Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15637-15660
MedRAX: Medical Reasoning Agent for Chest X-ray
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15661-15676
Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15677-15699
De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15700-15718
SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15719-15735
Graph Minimum Factorization Distance and Its Application to Large-Scale Graph Data Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15736-15761
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15762-15778
Learning Changes in Graphon Attachment Network Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15779-15803
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15804-15832
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15833-15861
Safety-Polarized and Prioritized Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15862-15886
Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15887-15900
Demeaned Sparse: Efficient Anomaly Detection by Residual Estimate
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15901-15924
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15925-15942
Towards a Unified Framework of Clustering-based Anomaly Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15943-15959
FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15960-15975
Understanding and Mitigating Memorization in Diffusion Models for Tabular Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:15976-16005
Homophily Enhanced Graph Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16006-16028
Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16029-16039
Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16040-16057
FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16058-16077
Reliable Algorithm Selection for Machine Learning-Guided Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16078-16101
Temporal Difference Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16102-16143
Zero-Shot Adaptation of Parameter-Efficient Fine-Tuning in Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16144-16160
Speeding up Policy Simulation in Supply Chain RL
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16161-16177
Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16178-16236
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16237-16272
A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16273-16285
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16286-16306
On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16307-16354
In-Context Fine-Tuning for Time-Series Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16355-16374
DUNIA: Pixel-Sized Embeddings via Cross-Modal Alignment for Earth Observation Applications
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16375-16406
FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16407-16422
On Path to Multimodal Generalist: General-Level and General-Bench
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16423-16542
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16543-16572
Local Pan-privacy for Federated Analytics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16573-16588
Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16589-16603
OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16604-16633
On Differential Privacy for Adaptively Solving Search Problems via Sketching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16634-16669
Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16670-16710
Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16711-16726
Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16727-16743
PILAF: Optimal Human Preference Sampling for Reward Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16744-16776
Perceptually Constrained Precipitation Nowcasting Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16777-16795
Multi-Modal Object Re-identification via Sparse Mixture-of-Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16796-16807
ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16808-16824
HEAP: Hyper Extended A-PDHG Operator for Constrained High-dim PDEs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16825-16836
TAROT: Targeted Data Selection via Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16837-16852
Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16853-16883
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16884-16903
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16904-16930
Graph World Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16931-16955
Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16956-16976
Regularized Langevin Dynamics for Combinatorial Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16977-16992
On the Guidance of Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:16993-17029
CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17030-17048
BiMark: Unbiased Multilayer Watermarking for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17049-17067
Dual Feature Reduction for the Sparse-group Lasso and its Adaptive Variant
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17068-17099
WildChat-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17100-17130
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17131-17152
GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17153-17188
Faster Approximation Algorithms for k-Center via Data Reduction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17189-17202
Improving the Effective Receptive Field of Message-Passing Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17203-17220
From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17221-17238
The Value of Prediction in Identifying the Worst-Off
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17239-17261
Generalized Random Forests Using Fixed-Point Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17262-17305
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17306-17377
FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17378-17391
Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17392-17410
LSCD: Lomb–Scargle Conditioned Diffusion for Time series Imputation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17411-17436
Action-Dependent Optimality-Preserving Reward Shaping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17437-17451
SHARP-Distill: A 68$\times$ Faster Recommender System with Hypergraph Neural Networks and Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17452-17488
Adaptive Flow Matching for Resolving Small-Scale Physics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17489-17521
COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17522-17541
S4S: Solving for a Fast Diffusion Model Solver
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17542-17574
Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17575-17656
Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17657-17671
Prompt-to-Leaderboard: Prompt-Adaptive LLM Evaluations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17672-17689
Learning Mixtures of Experts with EM: A Mirror Descent Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17690-17726
Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17727-17745
EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17746-17763
Fast Large Language Model Collaborative Decoding via Speculation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17764-17782
ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17783-17805
PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17806-17831
Knowledge Retention in Continual Model-Based Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17832-17851
CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17852-17874
Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17875-17893
PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17894-17908
On the Statistical Mechanisms of Distributional Compositional Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17909-17927
Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17928-17959
Gradient Boosting Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17960-17985
PAC-Bayes Analysis for Recalibration in Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17986-18023
Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18024-18046
Generalized additive models via direct optimization of regularized decision stump forests
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18047-18061
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18062-18095
Parameter-Efficient Fine-Tuning of State Space Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18096-18131
More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18132-18142
Sanity Checking Causal Representation Learning on a Simple Real-World System
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18143-18169
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18170-18188
It’s My Data Too: Private ML for Datasets with Multi-User Training Examples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18189-18205
A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18206-18227
Feasible Action Search for Bandit Linear Programs via Thompson Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18228-18256
Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18257-18276
AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18277-18289
Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18290-18316
Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18317-18336
Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18337-18362
Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18363-18385
Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18386-18409
Complete-Tree Space Favors Data-Efficient Link Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18410-18429
MARGE: Improving Math Reasoning with Guided Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18430-18452
Model Uncertainty Quantification by Conformal Prediction in Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18453-18469
EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18470-18494
Volume Optimality in Conformal Prediction with Structured Prediction Sets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18495-18527
Neural Solver Selection for Combinatorial Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18528-18549
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18550-18565
NExtLong: Toward Effective Long-Context Training without Long Documents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18566-18584
LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18585-18611
Metadata Conditioning Accelerates Language Model Pre-training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18612-18629
Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18630-18657
OneForecast: A Universal Framework for Global and Regional Weather Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18658-18697
Doubly Protected Estimation for Survival Outcomes Utilizing External Controls for Randomized Clinical Trials
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18698-18723
REG: Rectified Gradient Guidance for Conditional Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18724-18743
AdaWorld: Learning Adaptable World Models with Latent Actions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18744-18771
Extreme Value Policy Optimization for Safe Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18772-18793
Robust ML Auditing using Prior Knowledge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18794-18810
Persistent Topological Features in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18811-18830
How Transformers Learn Structured Data: Insights From Hierarchical Filtering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18831-18847
Improving the Statistical Efficiency of Cross-Conformal Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18848-18867
Unified Breakdown Analysis for Byzantine Robust Gossip
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18868-18896
Statistical Collusion by Collectives on Learning Platforms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18897-18919
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18920-18953
Stochastic Online Conformal Prediction with Semi-Bandit Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18954-18965
Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18966-18988
Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:18989-19010
Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19011-19033
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19034-19055
Towards flexible perception with visual memory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19056-19081
REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19082-19111
Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19112-19136
Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19137-19160
Hybrid Quantum-Classical Multi-Agent Pathfinding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19161-19171
Time Series Representations with Hard-Coded Invariances
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19172-19195
Universal Neural Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19196-19232
Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19233-19247
Fast Tensor Completion via Approximate Richardson Iteration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19248-19265
Sample-Optimal Agnostic Boosting with Unlabeled Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19266-19285
QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles for model-monitoring
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19286-19306
Memorization Sinks: Isolating Memorization during LLM Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19307-19326
Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19327-19357
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19358-19405
Online Learning in Risk Sensitive constrained MDP
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19406-19425
Fraud-Proof Revenue Division on Subscription Platforms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19426-19436
Improved and Oracle-Efficient Online $\ell_1$-Multicalibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19437-19457
Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19458-19479
EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19480-19504
Optimizing Noise Distributions for Differential Privacy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19505-19522
Score Matching with Missing Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19523-19561
Discovering Spoofing Attempts on Language Model Watermarks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19562-19584
When can in-context learning generalize out of task distribution?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19585-19599
R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19600-19620
Great Models Think Alike and this Undermines AI Oversight
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19621-19678
SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19679-19711
Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19712-19733
EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19734-19754
Detecting Strategic Deception with Linear Probes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19755-19786
Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19787-19808
The Role of Sparsity for Length Generalization in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19809-19840
Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19841-19877
AdaSplash: Adaptive Sparse Flash Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19878-19896
Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19897-19911
Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19912-19931
Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19932-19963
PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19964-19995
Outlier-Aware Post-Training Quantization for Discrete Graph Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:19996-20015
Human Body Restoration with One-Step Diffusion Model and A New Benchmark
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20016-20026
Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20027-20046
A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20047-20074
Fast Inference with Kronecker-Sparse Matrices
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20075-20102
Calibrated Physics-Informed Uncertainty Quantification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20103-20141
Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20142-20161
Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20162-20186
CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20187-20225
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20226-20246
Masked Generative Nested Transformers with Decode Time Scaling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20247-20265
Test-Time Training Provably Improves Transformers as In-context Learners
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20266-20295
Clustering Items through Bandit Feedback: Finding the Right Feature out of Many
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20296-20325
The Importance of Being Lazy: Scaling Limits of Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20326-20367
Point-Level Topological Representation Learning on Point Clouds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20368-20398
Is Complex Query Answering Really Complex?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20399-20428
CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20429-20447
VerbalTS: Generating Time Series from Texts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20448-20476
Auditing Prompt Caching in Language Model APIs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20477-20496
Delta Decompression for MoE-based LLMs Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20497-20514
Binary Hypothesis Testing for Softmax Models and Leverage Score Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20515-20536
Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20537-20552
SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20553-20571
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20572-20597
QMamba: On First Exploration of Vision Mamba for Image Quality Assessment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20598-20611
Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20612-20639
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20640-20661
Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20662-20693
HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20694-20722
Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20723-20747
Active feature acquisition via explainability-driven ranking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20748-20765
SlimLLM: Accurate Structured Pruning for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20766-20776
Boosting Protein Graph Representations through Static-Dynamic Fusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20777-20792
Towards Lifelong Model Editing via Simulating Ideal Editor
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20793-20824
Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20825-20842
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20843-20857
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20858-20879
On the Diversity of Adversarial Ensemble Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20880-20902
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20903-20920
Variational Rectified Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20921-20940
Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20941-20963
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20964-20992
SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:20993-21066
Improving Out-of-Distribution Detection via Dynamic Covariance Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21067-21082
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21083-21100
SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21101-21137
Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21138-21162
Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21163-21183
RBench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21184-21201
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21202-21219
ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21220-21231
TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21232-21251
Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21252-21276
GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21277-21296
LAST SToP for Modeling Asynchronous Time Series
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21297-21321
A Machine Learning Approach to Duality in Statistical Physics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21322-21341
AMPO: Active Multi Preference Optimization for Self-play Preference Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21342-21368
AlphaPO: Reward Shape Matters for LLM Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21369-21394
PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21395-21417
HiRemate: Hierarchical Approach for Efficient Re-materialization of Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21418-21443
Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21444-21470
Inverse Bridge Matching Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21471-21496
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21497-21515
Exponential Family Variational Flow Matching for Tabular Data Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21516-21529
Limitations of measure-first protocols in quantum machine learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21530-21545
Predicting the Susceptibility of Examples to Catastrophic Forgetting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21546-21569
Learning Extrapolative Sequence Transformations from Markov Chains
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21570-21590
Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21591-21628
Hierarchical Refinement: Optimal Transport to Infinity and Beyond
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21629-21661
Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21662-21684
Of Mice and Machines: A Comparison of Learning Between Real World Mice and RL Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21685-21703
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21704-21732
On the Role of Label Noise in the Feature Learning Process
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21733-21773
Retrieval Augmented Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21774-21797
Ranked Entropy Minimization for Continual Test-Time Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21798-21813
Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21814-21843
Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21844-21870
Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21871-21897
Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21898-21915
MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21916-21931
Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21932-21947
Heads up! Large Language Models Can Perform Tasks Without Your Instruction via Selective Attention Head Masking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21948-21973
Unveiling AI’s Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21974-21994
Representation Preserving Multiclass Agnostic to Realizable Reduction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21995-22008
A Trichotomy for List Transductive Online Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22009-22022
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22023-22043
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22044-22090
SafeMap: Robust HD Map Construction from Incomplete Observations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22091-22102
Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22103-22115
Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22116-22148
Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22149-22176
Optimal Decision Tree Pruning Revisited: Algorithms and Complexity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22177-22203
Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22204-22237
Wasserstein Flow Matching: Generative Modeling Over Families of Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22238-22258
Distillation of Discrete Diffusion through Dimensional Correlations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22259-22297
Generative Data Mining with Longtail-Guided Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22298-22317
Double Machine Learning for Causal Inference under Shared-State Interference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22318-22350
Random Policy Evaluation Uncovers Policies of Generative Flow Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22351-22367
ZipAR: Parallel Autoregressive Image Generation through Spatial Locality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22368-22378
DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22379-22391
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22392-22406
Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22407-22421
SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22422-22433
Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22434-22455
ReferSplat: Referring Segmentation in 3D Gaussian Splatting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22456-22467
Subspace Optimization for Large Language Models with Convergence Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22468-22522
Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22523-22547
Going Deeper into Locally Differentially Private Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22548-22565
Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22566-22579
Olica: Efficient Structured Pruning of Large Language Models without Retraining
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22580-22594
Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22595-22646
GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22647-22668
FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22669-22685
In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22686-22742
Primal-Dual Neural Algorithmic Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22743-22766
Chaos Meets Attention: Transformers for Large-Scale Dynamical Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22767-22791
Primphormer: Efficient Graph Transformers with Primal Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22792-22815
Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22816-22835
A Closer Look at Backdoor Attacks on CLIP
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22836-22852
RUN: Reversible Unfolding Network for Concealed Object Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22853-22864
Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22865-22880
DeepCrossAttention: Supercharging Transformer Residual Connections
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22881-22903
Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22904-22923
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22924-22945
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22946-22963
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22964-22987
Gradient Inversion of Multimodal Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22988-23004
Secant Line Search for Frank-Wolfe Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23005-23029
On the Duality between Gradient Transformations and Adapters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23030-23046
Neurosymbolic World Models for Sequential Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23047-23062
Measuring In-Context Computation Complexity via Hidden State Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23063-23082
Importance Corrected Neural JKO Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23083-23119
Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23120-23135
Decision-aware Training of Spatiotemporal Forecasting Models to Select a Top-K Subset of Sites for Intervention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23136-23154
Flexible Tails for Normalizing Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23155-23178
Generalization Analysis for Supervised Contrastive Representation Learning under Non-IID Settings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23179-23218
Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23219-23234
Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23235-23260
Logits are All We Need to Adapt Closed Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23261-23289
Models of Heavy-Tailed Mechanistic Universality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23290-23329
The Elicitation Game: Evaluating Capability Elicitation Techniques
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23330-23356
Uniform Mean Estimation for Heavy-Tailed Distributions via Median-of-Means
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23357-23381
Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23382-23396
LEAPS: A discrete neural sampler via locally equivariant networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23397-23416
Open Materials Generation with Stochastic Interpolants
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23417-23450
EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23451-23512
G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23513-23561
PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23562-23602
When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23603-23639
MTSTRec: Multimodal Time-Aligned Shared Token Recommender
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23640-23661
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting for Novel View Synthesis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23662-23681
On the Robustness of Reward Models for Language Model Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23682-23699
CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23700-23721
Trajectory Inference with Smooth Schrödinger Bridges
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23722-23750
A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23751-23773
On the Provable Separation of Scales in Maximal Update Parameterization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23774-23786
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23787-23804
The Role of Randomness in Stability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23805-23827
QPRL : Learning Optimal Policies with Quasi-Potential Functions for Asymmetric Traversal
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23828-23845
Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23846-23872
Universal Length Generalization with Turing Programs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23873-23893
Instruction-Following Pruning for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23894-23909
Do Vision-Language Models Really Understand Visual Language?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23910-23959
A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23960-23975
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:23976-24003
ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24004-24024
Private Federated Learning using Preference-Optimized Synthetic Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24025-24044
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24045-24079
Scaling Trends in Language Model Robustness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24080-24138
RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24139-24155
Elucidating the Design Space of Multimodal Protein Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24156-24175
Contextual Online Decision Making with Infinite-Dimensional Functional Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24176-24202
The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24203-24231
Nonparametric Modern Hopfield Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24232-24269
Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24270-24289
Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24290-24313
Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24314-24327
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24328-24346
VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24347-24370
Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24371-24390
EPIC: Efficient Position-Independent Caching for Serving Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24391-24402
Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24403-24423
Explicit Preference Optimization: No Need for an Implicit Reward Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24424-24446
PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24447-24481
A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24482-24508
Explicit Discovery of Nonlinear Symmetries from Dynamic Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24509-24534
Learning Imbalanced Data with Beneficial Label Noise
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24535-24569
Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24570-24590
Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24591-24620
Stochastic Deep Restoration Priors for Imaging Inverse Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24621-24652
From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24653-24677
Editable Concept Bottleneck Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24678-24726
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24727-24743
Incorporating Arbitrary Matrix Group Equivariance into KANs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24744-24760
Empirical Privacy Variance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24761-24804
IMTS is Worth Time $\times$ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24805-24822
Test-Time Learning for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24823-24849
sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24850-24868
D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24869-24892
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24893-24911
Reward Translation via Reward Machine in Semi-Alignable MDPs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24912-24931
Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24932-24949
A Physics-Augmented Deep Learning Framework for Classifying Single Molecule Force Spectroscopy Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24950-24974
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24975-25020
How Expressive are Knowledge Graph Foundation Models?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25021-25058
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25059-25074
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25075-25126
Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25127-25140
3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25141-25158
Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25159-25184
$\mathcalVista\mathcalDPO$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25185-25203
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25204-25234
Differential Coding for Training-Free ANN-to-SNN Conversion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25235-25264
Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25265-25310
MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25311-25328
High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25329-25355
Towards Escaping from Class Dependency Modeling for Multi-Dimensional Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25356-25371
Automated Hypothesis Validation with Agentic Sequential Falsifications
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25372-25437
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25438-25473
Flow Matching for Denoised Social Recommendation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25474-25485
Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25486-25499
Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25500-25515
How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25516-25549
Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25550-25565
OTTER: A Vision-Language-Action Model with Text-Aware Visual Feature Extraction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25566-25580
Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25581-25592
Calibrated Language Models and How to Find Them with Label Smoothing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25593-25612
Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25613-25633
TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awareness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25634-25653
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25654-25671
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25672-25692
Understanding Input Selectivity in Mamba: Impact on Approximation Power, Memorization, and Associative Recall Capacity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25693-25727
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25728-25749
Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25750-25761
Federated Oriented Learning: A Practical One-Shot Personalized Federated Learning Framework
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25762-25790
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25791-25812
Improving Flow Matching by Aligning Flow Divergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25813-25834
HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25835-25858
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25859-25875
A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25876-25907
DriveGPT: Scaling Autoregressive Behavior Models for Driving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25908-25921
Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25922-25946
Uncertainty Quantification for LLM-Based Survey Simulations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25947-25971
Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25972-25986
Learn Beneficial Noise as Graph Augmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25987-26001
IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26002-26019
Sample Complexity of Correlation Detection in the Gaussian Wigner Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26020-26040
Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26041-26057
EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26058-26076
Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26077-26105
Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26106-26142
MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26143-26161
GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26162-26174
Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26175-26201
On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26202-26226
TimeBase: The Power of Minimalism in Efficient Long-term Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26227-26246
Steering Protein Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26247-26260
Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26261-26282
Imitation Learning from a Single Temporally Misaligned Video
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26283-26310
Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26311-26337
Understanding Generalization in Quantum Machine Learning with Margins
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26338-26360
Constrained Online Convex Optimization with Polyak Feasibility Steps
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26361-26375
Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26376-26411
Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26412-26432
QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26433-26445
Robust Sparsification via Sensitivity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26446-26463
Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26464-26489
Pareto-frontier Entropy Search with Variational Lower Bound Maximization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26490-26522
Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26523-26541
Safe-EF: Error Feedback for Non-smooth Constrained Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26542-26585
Improving Consistency Models with Generator-Augmented Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26586-26610
Linear Mode Connectivity between Multiple Models modulo Permutation Symmetries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26611-26626
Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26627-26641
Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26642-26672
Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26673-26699
Multi-Turn Code Generation Through Single-Step Rewards
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26700-26716
Unifying 2D and 3D Vision-Language Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26717-26739
From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26740-26756
Towards an Explainable Comparison and Alignment of Feature Embeddings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26757-26796
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26797-26829
A Mixture-Based Framework for Guiding Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26830-26876
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26877-26895
Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26896-26924
BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26925-26945
Improving the Variance of Differentially Private Randomized Experiments through Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26946-26980
QT-DoG: Quantization-Aware Training for Domain Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:26981-27004
The Brain’s Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27005-27020
Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27021-27049
Black-Box Adversarial Attacks on LLM-Based Code Completion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27050-27069
Enforcing Idempotency in Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27070-27090
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27091-27112
Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27113-27133
ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27134-27197
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27198-27220
Pfeife: Automatic Pipeline Parallelism for PyTorch
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27221-27236
RZ-NAS: Enhancing LLM-guided Neural Architecture Search via Reflective Zero-Cost Strategy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27237-27254
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27255-27270
Multi-Armed Bandits with Interference: Bridging Causal Inference and Adversarial Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27271-27291
Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27292-27306
LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27307-27330
Controlling Large Language Model with Latent Action
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27331-27372
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27373-27398
Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27399-27425
Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27426-27491
FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27492-27509
AnyEdit: Edit Any Knowledge Encoded in Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27510-27533
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27534-27552
Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27553-27568
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27569-27585
CursorCore: Assist Programming through Aligning Anything
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27586-27623
OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27624-27648
SADA: Stability-guided Adaptive Diffusion Acceleration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27649-27669
Topology-aware Neural Flux Prediction Guided by Physics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27670-27684
StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27685-27709
Generative Point Cloud Registration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27710-27723
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27724-27771
FedClean: A General Robust Label Noise Correction for Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27772-27792
MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27793-27830
Compositional Condition Question Answering in Tabular Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27831-27850
Can Large Language Models Understand Intermediate Representations in Compilers?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27851-27872
DTZO: Distributed Trilevel Zeroth Order Learning with Provable Non-Asymptotic Convergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27873-27916
SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27917-27928
Mixture of Lookup Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27929-27940
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27941-27956
Noisy SIGNSGD Is More Differentially Private Than You (Might) Think
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27957-27978
A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:27979-28030
Compute or Load KV Cache? Why Not Both?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28031-28043
PARQ: Piecewise-Affine Regularized Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28044-28062
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28063-28096
Diffusion Instruction Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28097-28137
Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28138-28156
Large Language Models are Demonstration Pre-Selectors for Themselves
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28157-28186
Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28187-28212
LLM Alignment as Retriever Optimization: An Information Retrieval Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28213-28232
MoH: Multi-Head Attention as Mixture-of-Head Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28233-28255
Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28256-28287
Safety Certificate against Latent Variables with Partially Unidentifiable Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28288-28303
Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28304-28326
Adversaries Can Misuse Combinations of Safe Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28327-28349
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28350-28376
Approximate Differential Privacy of the $\ell_2$ Mechanism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28377-28392
All-atom Diffusion Transformers: Unified generative modelling of molecules and materials
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28393-28417
Learning Parametric Distributions from Samples and Preferences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28418-28445
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28446-28462
Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28463-28480
Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28481-28502
Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28503-28526
Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28527-28551
Grokking Beyond the Euclidean Norm of Model Parameters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28552-28618
Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28619-28643
Selective Preference Aggregation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28644-28669
UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28670-28688
The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28689-28720
Towards Better-than-2 Approximation for Constrained Correlation Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28721-28734
Solving Zero-Sum Convex Markov Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28735-28794
An analytic theory of creativity in convolutional diffusion models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28795-28831
FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28832-28848
Algorithmic Recourse for Long-Term Improvement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28849-28877
SPEX: Scaling Feature Interaction Explanations for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28878-28903
Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28904-28920
A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28921-28942
LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28943-28958
Revisiting Neural Networks for Few-Shot Learning: A Zero-Cost NAS Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28959-28976
What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28977-28990
How Far Is Video Generation from World Model: A Physical Law Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28991-29017
Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29018-29049
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29050-29077
The Power of Random Features and the Limits of Distribution-Free Gradient Descent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29078-29097
Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29098-29127
Falsification of Unconfoundedness by Testing Independence of Causal Mechanisms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29128-29147
Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29148-29204
PokéChamp: an Expert-level Minimax Language Agent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29205-29222
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29223-29264
One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29265-29293
Categorical Distributional Reinforcement Learning with Kullback-Leibler Divergence: Convergence and Asymptotics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29294-29320
Curvature Enhanced Data Augmentation for Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29321-29344
Leveraging Offline Data in Linear Latent Contextual Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29345-29389
Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29390-29448
Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29449-29468
Collapse or Thrive: Perils and Promises of Synthetic Data in a Self-Generating World
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29469-29494
Wyckoff Transformer: Generation of Symmetric Crystals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29495-29526
Model-Based Exploration in Monitored Markov Decision Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29527-29556
VinePPO: Refining Credit Assignment in RL Training of LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29557-29590
Conservative Offline Goal-Conditioned Implicit V-Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29591-29607
Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29608-29625
Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29626-29650
Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29651-29669
Bayesian Inference for Correlated Human Experts and Classifiers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29670-29686
Scalable Meta-Learning via Mixed-Mode Differentiation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29687-29705
When and How Does CLIP Enable Domain and Compositional Generalization?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29706-29734
ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29735-29752
Autoencoder-Based Hybrid Replay for Class-Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29753-29767
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29768-29783
FlexiClip: Locality-Preserving Free-Form Character Animation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29784-29798
ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29799-29818
Scaling Sparse Feature Circuits For Studying In-Context Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29819-29851
Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29852-29868
Hierarchical Reinforcement Learning with Targeted Causal Interventions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29869-29912
Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29913-29968
Neural Genetic Search in Discrete Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29969-29987
Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:29988-30010
GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30011-30037
Correlated Errors in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30038-30066
NegMerge: Sign-Consensual Weight Merging for Machine Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30067-30085
SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30086-30098
K$^2$IE: Kernel Method-based Kernel Intensity Estimators for Inhomogeneous Poisson Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30099-30112
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30113-30131
BoA: Attention-aware Post-training Quantization without Backpropagation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30132-30152
When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30153-30175
Do Not Mimic My Voice : Speaker Identity Unlearning for Zero-Shot Text-to-Speech
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30176-30198
Active Learning with Selective Time-Step Acquisition for PDEs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30199-30223
LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won’t Fail)
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30224-30247
Federated Learning for Feature Generalization with Convex Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30248-30266
Measuring Representational Shifts in Continual Learning: A Linear Transformation Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30267-30289
Improved Off-policy Reinforcement Learning in Biological Sequence Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30290-30315
Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30316-30333
Symmetry-Aware GFlowNets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30334-30362
Fair Clustering via Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30363-30399
Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30400-30436
NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30437-30461
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30462-30479
Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30480-30547
HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30548-30566
Flow-field inference from neural data using deep recurrent networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30567-30590
Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30591-30608
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30609-30630
Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30631-30653
Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30654-30671
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30672-30687
Linear Bandits with Partially Observable Features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30688-30719
Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30720-30748
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30749-30768
Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30769-30790
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30791-30825
Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30826-30878
Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30879-30899
Improving Out-of-Distribution Detection with Markov Logic Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30900-30910
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30911-30942
Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30943-30965
Policy Design for Two-sided Platforms with Participation Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30966-30985
Fleet of Agents: Coordinated Problem Solving with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:30986-31019
BAnG: Bidirectional Anchored Generation for Conditional RNA Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31020-31043
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31044-31062
Preference Learning for AI Alignment: a Causal Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31063-31083
Gravity-Bench-v1: A Benchmark on Gravitational Physics Discovery for Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31084-31104
Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination’s Impact on Machine Translation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31105-31132
Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31133-31157
The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31158-31181
Rank-One Modified Value Iteration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31182-31201
Field Matching: an Electrostatic Paradigm to Generate and Transfer Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31202-31222
A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31223-31248
Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31249-31274
Certified Unlearning for Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31275-31298
NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31299-31321
Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31322-31341
Constrained Pareto Set Identification with Bandit Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31342-31378
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31379-31396
UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31397-31418
Latent Thought Models with Variational Bayes Inference-Time Computation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31419-31436
Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31437-31466
FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31467-31485
Identifiable Object Representations under Spatial Ambiguities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31486-31518
Phase transitions for the existence of unregularized M-estimators in single index models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31519-31540
Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31541-31559
Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31560-31589
Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31590-31618
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31619-31633
CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31634-31647
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31648-31666
Privacy Attacks on Image AutoRegressive Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31667-31695
Improved Learning via k-DTW: A Novel Dissimilarity Measure for Curves
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31696-31726
Categorical Schrödinger Bridge Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31727-31751
Customizing the Inductive Biases of Softmax Attention using Structured Matrices
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31752-31776
Reconstructing Cell Lineage Trees from Phenotypic Features with Metric Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31777-31820
How to Train Your Multi-Exit Model? Analyzing the Impact of Training Strategies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31821-31840
Patch-wise Structural Loss for Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31841-31859
Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31860-31875
Positive-unlabeled AUC Maximization under Covariate Shift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31876-31891
A Model of Place Field Reorganization During Reward Maximization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31892-31929
The Complexity of Learning Sparse Superposed Features with Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31930-31963
A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31964-31990
Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31991-32010
Steerable Transformers for Volumetric Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32011-32031
Dynamical phases of short-term memory mechanisms in RNNs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32032-32062
QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32063-32077
Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32078-32115
High-Fidelity Simultaneous Speech-To-Speech Translation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32116-32129
Dynamic Similarity Graph Construction with Kernel Density Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32130-32163
An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32164-32187
Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32188-32205
Joint Localization and Activation Editing for Low-Resource Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32206-32227
FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32228-32245
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32246-32277
AssistanceZero: Scalably Solving Assistance Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32278-32305
On the Private Estimation of Smooth Transport Maps
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32306-32338
Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32339-32374
A Theoretical Justification for Asymmetric Actor-Critic Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32375-32405
Simple Randomized Rounding for Max-Min Eigenvalue Augmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32406-32419
A Meta-learner for Heterogeneous Effects in Difference-in-Differences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32420-32451
Liger: Linearizing Large Language Models to Gated Recurrent Structures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32452-32466
Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32467-32491
Gradient-based Explanations for Deep Learning Survival Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32492-32522
Feedforward Few-shot Species Range Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32523-32561
Robust and Conjugate Spatio-Temporal Gaussian Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32562-32592
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32593-32616
Adaptive kernel predictors from feature-learning infinite limits of neural networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32617-32648
Understanding Fixed Predictions via Confined Regions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32649-32674
Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32675-32703
Learning Utilities from Demonstrations in Markov Decision Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32704-32770
Scalable Sobolev IPM for Probability Measures on a Graph
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32771-32802
Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32803-32829
Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32830-32852
On the Learnability of Distribution Classes with Adaptive Adversaries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32853-32877
Are Large Brainwave Foundation Models Capable Yet ? Insights from Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32878-32888
Bayesian Weight Enhancement with Steady-State Adaptation for Test-time Adaptation in Dynamic Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32889-32906
Near-Optimal Sample Complexity for MDPs via Anchoring
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32907-32929
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32930-32964
Unpaired Point Cloud Completion via Unbalanced Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32965-32986
Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:32987-33004
Test-Time Adaptation with Binary Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33005-33024
Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33025-33056
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33110-33128
Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33129-33142
FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33143-33156
ETTA: Elucidating the Design Space of Text-to-Audio Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33157-33180
Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33181-33204
GenMol: A Drug Discovery Generalist with Discrete Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33205-33226
Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33227-33242
Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33243-33275
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33276-33299
SAFE: Finding Sparse and Flat Minima to Improve Pruning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33300-33321
Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33322-33351
Hyperspherical Normalization for Scalable Deep Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33352-33403
On the Similarities of Embeddings in Contrastive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33404-33434
All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33435-33475
Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33476-33498
Chip Placement with Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33499-33514
Combinatorial Reinforcement Learning with Preference Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33515-33575
Improved Online Confidence Bounds for Multinomial Logistic Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33576-33615
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33616-33634
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33635-33654
Channel Normalization for Time Series Channel Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33655-33687
From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33688-33714
Self-supervised Adversarial Purification for Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33715-33735
Lightweight Online Adaption for Time Series Foundation Model Forecasts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33736-33764
Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33765-33783
RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33784-33814
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33815-33832
Efficient Distributed Optimization under Heavy-Tailed Noise
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33833-33882
DRAG: Data Reconstruction Attack using Guided Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33883-33901
M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33902-33917
iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33918-33940
Quantum Optimization via Gradient-Based Hamiltonian Descent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33941-33959
Attributes Shape the Embedding Space of Face Recognition Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33960-33983
A Simple Model of Inference Scaling Laws
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33984-33998
The Double-Ellipsoid Geometry of CLIP
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:33999-34019
The Underlying Universal Statistical Structure of Natural Datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34020-34043
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34044-34053
Large Language-Geometry Model: When LLM meets Equivariance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34054-34073
Taming Knowledge Conflicts in Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34074-34104
When Bad Data Leads to Good Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34105-34118
EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34119-34143
Near Optimal Non-asymptotic Sample Complexity of 1-Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34144-34184
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34185-34208
From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34209-34231
Eliciting Language Model Behaviors with Investigator Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34232-34251
Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34252-34270
Towards Black-Box Membership Inference Attack for Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34271-34287
WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34288-34311
Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34312-34332
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34333-34354
RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34355-34378
Core Knowledge Deficits in Multi-Modal Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34379-34409
An Efficient Private GPT Never Autoregressively Decodes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34410-34428
(How) Do Language Models Track State?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34429-34452
Instruct2See: Learning to Remove Any Obstructions Across Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34453-34470
CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34471-34489
Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34490-34508
R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34509-34527
Average Sensitivity of Hierarchical $k$-Median Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34528-34548
Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34549-34563
What Limits Bidirectional Model’s Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34564-34577
Optimal Task Order for Continual Learning of Multiple Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34578-34603
Adapting Precomputed Features for Efficient Graph Condensation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34604-34617
Control and Realism: Best of Both Worlds in Layout-to-Image without Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34618-34629
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34630-34673
Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34674-34687
GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34688-34701
Reward-free World Models for Online Imitation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34702-34724
Pairwise Maximum Likelihood For Multi-Class Logistic Regression Model With Multiple Rare Classes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34725-34741
BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34742-34773
Sounding that Object: Interactive Object-Aware Image to Audio Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34774-34794
Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34795-34835
Prediction-Powered Adaptive Shrinkage Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34836-34875
EditLord: Learning Code Transformation Rules for Code Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34876-34903
Learning from Sample Stability for Deep Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34904-34919
Reinforced Lifelong Editing for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34920-34942
On the Generalization Ability of Next-Token-Prediction Pretraining
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34943-34975
Solving Satisfiability Modulo Counting Exactly with Probabilistic Circuits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34976-34997
MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:34998-35020
Instance Correlation Graph-based Naive Bayes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35021-35033
Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35034-35046
Blink of an eye: a simple theory for feature localization in generative models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35047-35080
SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35081-35100
Safety Alignment Can Be Not Superficial With Explicit Safety Signals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35101-35135
LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35136-35167
One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35168-35185
DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35186-35208
MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35209-35230
On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35231-35258
Approximation to Smooth Functions by Low-Rank Swish Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35259-35291
R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35292-35316
One Arrow, Two Hawks: Sharpness-aware Minimization for Federated Learning via Global Model Trajectory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35317-35341
FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35342-35365
RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35366-35389
Local Identifying Causal Relations in the Presence of Latent Variables
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35390-35418
Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35419-35437
CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35438-35456
From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35457-35480
BECAME: Bayesian Continual Learning with Adaptive Model Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35481-35501
HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35502-35518
Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35519-35535
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35536-35561
STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35562-35580
Active Evaluation Acquisition for Efficient LLM Benchmarking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35581-35602
Optimal Auction Design in the Joint Advertising
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35603-35619
Learning Input Encodings for Kernel-Optimal Implicit Neural Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35620-35636
Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35637-35655
Modified K-means Algorithm with Local Optimality Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35656-35684
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35685-35709
Policy Guided Tree Search for Enhanced LLM Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35710-35730
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35731-35752
Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35753-35768
VIP: Vision Instructed Pre-training for Robotic Manipulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35769-35778
Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35779-35798
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35799-35819
Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35820-35857
Balanced Learning for Domain Adaptive Semantic Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35858-35883
Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35884-35908
Fairness on Principal Stratum: A New Perspective on Counterfactual Fairness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35909-35921
PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35922-35941
Improving LLM Video Understanding with 16 Frames Per Second
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35942-35956
What If We Recaption Billions of Web Images with LLaMA-3?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35957-35976
TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:35977-35999
Dataflow-Guided Neuro-Symbolic Language Models for Type Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36000-36020
Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36021-36041
PIPA: Preference Alignment as Prior-Informed Statistical Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36042-36056
Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36057-36095
Geometry Informed Tokenization of Molecules for Language Model Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36096-36128
Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36129-36139
Settling the Maximin Share Fairness for Scheduling among Groups of Machines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36140-36150
FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36151-36169
Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36170-36191
RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36192-36214
Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36215-36235
Reflection-Bench: Evaluating Epistemic Agency in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36236-36264
Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36265-36280
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36281-36297
Approximately Correct Label Distribution Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36298-36309
Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36310-36339
Imagine While Reasoning in Space: Multimodal Visualization-of-Thought
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36340-36364
Extracting Rare Dependence Patterns via Adaptive Sample Reweighting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36365-36399
BCE vs. CE in Deep Feature Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36400-36434
Revisiting Cooperative Off-Policy Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36435-36450
KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36451-36485
One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36486-36529
Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36530-36550
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36551-36575
Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36576-36596
Understanding Nonlinear Implicit Bias via Region Counts in Input Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36597-36613
LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36614-36623
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36624-36651
Learning from True-False Labels via Multi-modal Prompt Retrieving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36652-36666
Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36667-36689
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36690-36706
Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36707-36721
MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36722-36742
LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36743-36764
Automatic Reward Shaping from Confounded Offline Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36765-36793
EgoPrivacy: What Your First-Person Camera Says About You?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36794-36809
Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36810-36830
CommVQ: Commutative Vector Quantization for KV Cache Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36831-36845
LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36846-36867
InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36868-36885
Tilted Sharpness-Aware Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36886-36905
Tensor Decomposition Based Memory-Efficient Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36906-36920
Geometric Representation Condition Improves Equivariant Molecule Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36921-36953
L-Diffusion: Laplace Diffusion for Efficient Pathology Image Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36954-36973
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36974-36992
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:36993-37014
OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37015-37050
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37051-37070
Efficient Bisection Projection to Ensure Neural-Network Solution Feasibility for Optimization over General Set
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37071-37099
Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37100-37130
ROPO: Robust Preference Optimization for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37131-37161
Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37162-37180
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37181-37207
Contrastive Learning with Simplicial Convolutional Networks for Short-Text Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37208-37221
ML$^2$-GCL: Manifold Learning Inspired Lightweight Graph Contrastive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37222-37236
TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37237-37256
COKE: Core Kernel for More Efficient Approximation of Kernel Weights in Multiple Kernel Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37257-37280
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37281-37298
Enhancing Performance of Explainable AI Models with Constrained Concept Refinement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37299-37338
Synonymous Variational Inference for Perceptual Image Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37339-37369
Compositional Generalization via Forced Rendering of Disentangled Latents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37370-37395
Robust Automatic Modulation Classification with Fuzzy Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37396-37408
Trusted Multi-View Classification with Expert Knowledge Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37409-37426
Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37427-37441
BSO: Binary Spiking Online Optimization Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37442-37455
BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37456-37475
Curvature-aware Graph Attention for PDEs on Manifolds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37476-37494
Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37495-37510
Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37511-37527
FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37528-37554
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37555-37572
BOOD: Boundary-based Out-Of-Distribution Data Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37573-37586
Unifews: You Need Fewer Operations for Efficient Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37587-37609
Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37610-37622
Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37623-37641
Interaction-Aware Gaussian Weighting for Clustered Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37642-37666
UnHiPPO: Uncertainty-aware Initialization for State Space Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37667-37681
Scaling Laws for Upcycling Mixture-of-Experts Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37682-37704
PRIME: Deep Imbalanced Regression with Proxies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37705-37729
Scalable Gaussian Processes with Latent Kronecker Structure
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37730-37744
Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37745-37761
Ensemble Learned Bloom Filters: Two Oracles are Better than One
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37762-37779
Semantics-aware Test-time Adaptation for 3D Human Pose Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37780-37796
Temporal Query Network for Efficient Multivariate Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37797-37814
Tightening Causal Bounds via Covariate-Aware Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37815-37845
Latent Variable Estimation in Bayesian Black-Litterman Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37846-37873
PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37874-37888
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37889-37905
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37906-37918
Isolated Causal Effects of Natural Language
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37919-37941
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37942-37958
Diffusion Adversarial Post-Training for One-Step Video Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37959-37974
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37975-37995
Kona: An Efficient Privacy-Preservation Framework for KNN Classification by Communication Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37996-38012
On Explaining Equivariant Graph Networks via Improved Relevance Propagation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38013-38028
Looking Beyond the Top-1: Transformers Determine Top Tokens in Order
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38029-38048
ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38049-38065
A Mixed-Curvature based Pre-training Paradigm for Multi-Task Vehicle Routing Solver
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38066-38101
DragSolver: A Multi-Scale Transformer for Real-World Automotive Drag Coefficient Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38102-38118
Finite-Time Analysis of Discrete-Time Stochastic Interpolants
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38119-38143
SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38144-38168
Physics Aware Neural Networks for Unsupervised Binding Energy Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38169-38187
Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38188-38209
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38210-38250
Offline Learning for Combinatorial Multi-armed Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38251-38289
Iterative Vectors: In-Context Gradient Steering without Backpropagation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38290-38312
DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38313-38331
A Selective Learning Method for Temporal Graph Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38332-38350
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38351-38364
Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38365-38383
SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38384-38396
Continual Reinforcement Learning by Planning with Online World Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38397-38423
Learning Robust Neural Processes with Risk-Averse Stochastic Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38424-38447
Quantum Speedup for Hypergraph Sparsification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38448-38466
Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38467-38488
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38489-38517
Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38518-38539
Federated Node-Level Clustering Network with Cross-Subgraph Link Mending
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38540-38556
Elucidating the design space of language models for image generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38557-38581
An Improved Clique-Picking Algorithm for Counting Markov Equivalent DAGs via Super Cliques Transfer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38582-38597
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38598-38622
FlipAttack: Jailbreak LLMs via Flipping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38623-38663
MissScore: High-Order Score Estimation in the Presence of Missing Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38664-38691
CogMath: Assessing LLMs’ Authentic Mathematical Ability from a Human Cognitive Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38692-38707
What Makes In-context Learning Effective for Mathematical Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38708-38721
Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38722-38743
Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38744-38766
HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38767-38788
POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38789-38808
Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38809-38826
C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38827-38841
Diving into Self-Evolving Training for Multimodal Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38842-38856
am-ELO: A Stable Framework for Arena-based LLM Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38857-38868
Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38869-38893
Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38894-38939
Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38940-38962
Tractable Transformers for Flexible Conditional Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38963-38986
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:38987-39015
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39016-39031
Learning Soft Sparse Shapes for Efficient Time-Series Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39032-39059
OmniAudio: Generating Spatial Audio from 360-Degree Video
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39060-39084
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39085-39105
Understanding the Unfairness in Network Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39106-39125
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39126-39146
Efficient Robotic Policy Learning via Latent Space Backward Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39147-39161
Nonconvex Theory of $M$-estimators with Decomposable Regularizers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39162-39170
The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39171-39189
Reward Modeling with Ordinal Feedback: Wisdom of the Crowd
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39190-39218
LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39219-39243
Permutation-Free High-Order Interaction Tests
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39244-39260
Deliberation in Latent Space via Differentiable Cache Augmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39261-39274
Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39275-39294
Sundial: A Family of Highly Capable Time Series Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39295-39317
Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39318-39365
Generative Human Trajectory Recovery via Embedding-Space Conditional Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39366-39380
Accurate Identification of Communication Between Multiple Interacting Neural Populations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39381-39404
PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39405-39419
Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39420-39454
Scalable First-order Method for Certifying Optimal k-Sparse GLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39455-39481
Efficient ANN-SNN Conversion with Error Compensation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39482-39495
Fast Estimation of Partial Dependence Functions using Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39496-39534
CoMemo: LVLMs Need Image Context with Image Memory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39535-39551
Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39552-39567
ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39568-39586
Slimming the Fat-Tail: Morphing-Flow for Adaptive Time Series Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39587-39623
AutoStep: Locally adaptive involutive MCMC
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39624-39650
Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39651-39668
Censor Dependent Variational Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39669-39693
Counterfactual Voting Adjustment for Quality Assessment and Fairer Voting in Online Platforms with Helpfulness Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39694-39712
Maximizing Intermediate Checkpoint Value in LLM Pretraining with Bayesian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39713-39741
HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39742-39754
Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39755-39773
Spectral-Aware Reservoir Computing for Fast and Accurate Time Series Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39774-39788
FreeMesh: Boosting Mesh Generation with Coordinates Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39789-39802
Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain Transfer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39803-39814
TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39815-39840
An Expressive and Self-Adaptive Dynamical System for Efficient Function Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39841-39852
Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39853-39870
Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39871-39897
TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39898-39914
Progressively Label Enhancement for Large Language Model Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39915-39928
TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39929-39946
Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39947-39967
La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39968-39986
BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39987-39996
Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Example
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:39997-40021
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40022-40042
TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40043-40068
SynEVO: A neuro-inspired spatiotemporal evolutional framework for cross-domain adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40069-40084
Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40085-40099
Efficient Federated Incomplete Multi-View Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40100-40114
NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare Analytics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40115-40133
BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40134-40151
Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40152-40193
Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40194-40213
Token Coordinated Prompt Attention is Needed for Visual Prompting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40214-40226
Hessian Geometry of Latent Space in Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40227-40252
BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40253-40269
Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40270-40289
Contour Integration Underlies Human-Like Vision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40290-40311
Fast Min-$ε$ Segmented Regression using Constant-Time Segment Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40312-40327
STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40328-40343
SAE-V: Interpreting Multimodal Models for Enhanced Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40344-40360
AAAR-1.0: Assessing AI’s Potential to Assist Research
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40361-40383
A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40384-40399
Super Deep Contrastive Information Bottleneck for Multi-modal Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40400-40410
Navigating Conflicting Views: Harnessing Trust for Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40411-40435
Aligning Protein Conformation Ensemble Generation with Physical Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40436-40451
Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40452-40463
WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40464-40490
Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40491-40504
Towards Practical Defect-Focused Automated Code Review
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40505-40536
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40537-40559
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40560-40592
Habitizing Diffusion Planning for Efficient and Effective Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40593-40613
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40614-40664
TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40665-40708
Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40709-40725
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40726-40740
Stochastic Forward–Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40741-40768
OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40769-40802
Agent Reviewers: Domain-specific Multimodal Agents with Shared Memory for Paper Review
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40803-40830
Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40831-40847
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40848-40867
LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40868-40887
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40888-40902
FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40903-40929
ToMA: Token Merge with Attention for Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40930-40951
Sparse Autoencoders, Again?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40952-40976
Constrained Exploitability Descent: An Offline Reinforcement Learning Method for Finding Mixed-Strategy Nash Equilibrium
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40977-40994
Learning with Expected Signatures: Theory and Applications
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40995-41055
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41056-41073
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41074-41102
Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41103-41119
Probing Visual Language Priors in VLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41120-41156
Vision-Language Models Create Cross-Modal Task Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41157-41176
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41177-41199
Quantum Algorithms for Finite-horizon Markov Decision Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41200-41234
Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41235-41253
Fast and Low-Cost Genomic Foundation Models via Outlier Removal
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41254-41289
Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41290-41310
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41311-41330
Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41331-41345
Beyond One-Hot Labels: Semantic Mixing for Model Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41346-41367
Efficient and Scalable Density Functional Theory Hamiltonian Prediction through Adaptive Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41368-41390
One-dimensional Path Convolution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41391-41406
Locality Preserving Markovian Transition for Instance Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41407-41431
Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41432-41449
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41450-41467
Causal Attribution Analysis for Continuous Outcomes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41468-41493
Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41494-41519
David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41520-41539
Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41540-41565
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41566-41585
Conformity Score Averaging for Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41586-41603
LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41604-41619
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41620-41647
Runtime Analysis of Evolutionary NAS for Multiclass Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41648-41666
Autonomy-of-Experts Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41667-41681
Dendritic Localized Learning: Toward Biologically Plausible Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41682-41700
Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41701-41737
Consensus Based Stochastic Optimal Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41738-41771
RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41772-41790
Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41791-41806
Meta-Black-Box-Optimization through Offline Q-function Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41807-41826
Improving Multimodal Learning Balance and Sufficiency through Data Remixing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41827-41836
Efficient Online Reinforcement Learning for Diffusion Policy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41837-41853
Pruning for GNNs: Lower Complexity with Comparable Expressiveness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41854-41889
Overcoming Non-monotonicity in Transducer-based Streaming Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41890-41906
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41907-41942
Adversarial Robustness via Deformable Convolution with Stochasticity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41943-41958
HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41959-41974
Catching Two Birds with One Stone: Reward Shaping with Dual Random Networks for Balancing Exploration and Exploitation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41975-41991
"Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:41992-42008
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42009-42029
PTTA: Purifying Malicious Samples for Test-Time Model Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42030-42061
TANGO: Clustering with Typicality-Aware Nonlocal Mode-Seeking and Graph-Cut Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42062-42080
Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42081-42095
TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42096-42111
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42112-42129
COExpander: Adaptive Solution Expansion for Combinatorial Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42130-42164
Robust Spatio-Temporal Centralized Interaction for OOD Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42165-42192
A Closer Look at Generalized BH Algorithm for Out-of-Distribution Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42193-42208
Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42209-42235
Efficient Multi-modal Long Context Learning for Training-free Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42236-42251
Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42252-42292
Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42293-42308
An Online Statistical Framework for Out-of-Distribution Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42309-42324
Compositional Causal Reasoning Evaluation in Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42325-42365
Inverse problems with experiment-guided AlphaFold
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42366-42393
AKORN: Adaptive Knots generated Online for RegressioN splines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42394-42420
Linearization Turns Neural Operators into Function-Valued Gaussian Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42421-42452
Learning to Stop: Deep Learning for Mean Field Optimal Stopping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42453-42486
DataDecide: How to Predict Best Pretraining Data with Small Experiments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42487-42502
Compositional Risk Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42503-42553
Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42554-42578
Sable: a Performant, Efficient and Scalable Sequence Model for MARL
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42579-42614
Auditing $f$-differential privacy in one run
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42615-42641
SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42642-42667
LETS Forecast: Learning Embedology for Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42668-42690
Regret-Free Reinforcement Learning for Temporal Logic Specifications
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42691-42711
Residual Matrix Transformers: Scaling the Size of the Residual Stream
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42712-42729
Hypothesis Testing for Generalized Thurstone Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42730-42764
Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42765-42794
Reasoning Limitations of Multimodal Large Language Models. A case study of Bongard Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42795-42833
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42834-42856
Potemkin Understanding in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42857-42881
Learning Latent Graph Structures and their Uncertainty
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42882-42901
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42902-42946
Efficient Diffusion Models for Symmetric Manifolds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42947-42983
CTBench: A Library and Benchmark for Certified Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42984-43010
Hypo3D: Exploring Hypothetical Reasoning in 3D
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43011-43034
Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43035-43066
Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43067-43088
ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43089-43119
Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43120-43139
Transformative or Conservative? Conservation laws for ResNets and Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43140-43176
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43177-43199
Provable Length Generalization in Sequence Prediction via Spectral Filtering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43200-43224
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43225-43247
Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43248-43275
AuPair: Golden Example Pairs for Code Repair
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43276-43301
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43302-43330
The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43331-43352
Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43353-43374
Scaling Laws for Differentially Private Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43375-43398
Anytime-Constrained Equilibria in Polynomial Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43399-43416
Polynomial-Time Approximability of Constrained Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43417-43439
Leveraging Predictive Equivalence in Decision Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43440-43475
LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43476-43502
Return Capping: Sample Efficient CVaR Policy Gradient Optimisation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43503-43518
Weak-to-Strong Generalization Even in Random Feature Networks, Provably
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43519-43556
The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43557-43580
Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43581-43602
A Generalization Theory for Zero-Shot Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43603-43660
Heterogeneous Treatment Effect in Time-to-Event Outcomes: Harnessing Censored Data with Recursively Imputed Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43661-43693
MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43694-43715
Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43716-43753
TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43754-43780
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43781-43806
CLOVER: Cross-Layer Orthogonal Vectors Pruning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43807-43825
LAuReL: Learned Augmented Residual Layer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43826-43836
Diffusion on Language Model Encodings for Protein Sequence Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43837-43878
Discovering a Zero (Zero-Vector Class of Machine Learning)
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43879-43908
Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43909-43933
Benchmarking Quantum Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43934-43964
A Bregman Proximal Viewpoint on Neural Operators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43965-43989
On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:43990-44016
I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44017-44036
Rethinking Score Distilling Sampling for 3D Editing and Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44037-44053
Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44054-44075
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44076-44105
Computing Voting Rules with Improvement Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44106-44133
Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44134-44174
Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44175-44198
Embedding Safety into RL: A New Take on Trust Region Methods
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44199-44224
Function-Space Learning Rates
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44225-44251
Improving Your Model Ranking on Chatbot Arena by Vote Rigging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44252-44271
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44272-44291
Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44292-44350
Deep Neural Cellular Potts Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44351-44371
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44372-44395
Measuring Diversity: Axioms and Challenges
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44396-44411
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44412-44450
SING: Spatial Context in Large Language Model for Next-Gen Wearables
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44451-44469
Equivariant Neural Tangent Kernels
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44470-44503
Does learning the right latent variables necessarily improve in-context learning?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44504-44530
GMAIL: Generative Modality Alignment for generated Image Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44531-44553
NoLiMa: Long-Context Evaluation Beyond Literal Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44554-44570
Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44571-44593
Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44594-44614
Adversarial Inputs for Linear Algebra Backends
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44615-44626
A Variational Information Theoretic Approach to Out-of-Distribution Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44627-44651
Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44652-44698
Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44699-44725
A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44726-44749
DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44750-44774
Online Episodic Convex Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44775-44824
The Price of Linear Time: Error Analysis of Structured Kernel Interpolation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44825-44853
Dimensionality Reduction on Complex Vector Spaces for Euclidean Distance with Dynamic Weights
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44854-44873
Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44874-44886
Revisiting Non-Acyclic GFlowNets in Discrete Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44887-44910
SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44911-44935
Geometric Hyena Networks for Large-scale Equivariant Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44936-44955
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44956-44970
GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44971-44996
Sparse Autoencoders for Hypothesis Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:44997-45023
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45024-45049
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45050-45068
MIB: A Mechanistic Interpretability Benchmark
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45069-45108
Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45109-45128
Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45129-45150
Mahalanobis++: Improving OOD Detection via Feature Normalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45151-45184
Best of Both Worlds: Regret Minimization versus Minimax Play
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45185-45211
LineFlow: A Framework to Learn Active Control of Production Lines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45212-45235
Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45236-45255
A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45256-45271
Fast Exact Unlearning for In-Context Learning Data for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45272-45288
You Get What You Give: Reciprocally Fair Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45289-45310
LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45311-45341
A Classification View on Meta Learning Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45342-45361
Preference Adaptive and Sequential Text-to-Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45362-45394
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45395-45436
LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45437-45460
DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45461-45483
Matryoshka Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45484-45506
FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45507-45528
Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45529-45560
Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45561-45587
Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45588-45623
Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45624-45662
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45663-45681
Cost-efficient Collaboration between On-device and Cloud Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45682-45719
$\mathrmμ$nit Scaling: Simple and Scalable FP8 LLM Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45720-45736
Unified Screening for Multiple Diseases
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45737-45769
Kernel Quantile Embeddings and Associated Probability Metrics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45770-45800
A Sub-Problem Quantum Alternating Operator Ansatz for Correlation Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45801-45816
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45817-45851
WILTing Trees: Interpreting the Distance Between MPNN Embeddings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45852-45876
Identifying Neural Dynamics Using Interventional State Space Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45877-45894
Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45895-45910
A General Representation-Based Approach to Multi-Source Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45911-45933
Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45934-45953
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45954-45987
Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45988-46007
Synthetic Text Generation for Training Large Language Models via Gradient Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46008-46025
Layer-wise Quantization for Quantized Optimistic Dual Averaging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46026-46072
Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46073-46115
Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46116-46161
Lightspeed Geometric Dataset Distance via Sliced Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46162-46177
Provably Improving Generalization of Few-shot models with Synthetic Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46178-46195
Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46196-46210
Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46211-46241
Policy-Regret Minimization in Markov Games with Function Approximation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46242-46264
Time-Aware World Model for Adaptive Prediction and Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46265-46287
RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46288-46304
Faster Global Minimum Cut with Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46305-46319
FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46320-46345
EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46346-46376
Decomposition of Graphic Design with Unified Multimodal Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46377-46388
Towards a Mechanistic Explanation of Diffusion Model Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46389-46411
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46412-46426
Latent Action Learning Requires Supervision in the Presence of Distractors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46427-46447
Graph4MM: Weaving Multimodal Learning with Structural Information
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46448-46472
MVA: Linear Attention with High-order Query-Keys Integration and Multi-level Vocabulary Decomposition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46473-46497
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46498-46524
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46525-46553
Nonlinear transformers can perform inference-time feature learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46554-46585
Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46586-46610
Self-Bootstrapping for Versatile Test-Time Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46611-46628
Test-Time Multimodal Backdoor Detection by Contrastive Prompting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46629-46648
Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46649-46692
Pre-training Auto-regressive Robotic Models with 4D Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46693-46711
LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46712-46734
Stronger Neyman Regret Guarantees for Adaptive Experimental Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46735-46761
High-Dimensional Prediction for Sequential Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46762-46783
Stochastic Encodings for Active Feature Acquisition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46784-46814
Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46815-46836
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46837-46876
Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46877-46896
Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46897-46942
Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:46943-46970
Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47003-47016
Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47017-47043
Compressed Image Generation with Denoising Diffusion Codebook Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47044-47089
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47090-47131
Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47132-47154
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47155-47175
Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47176-47195
TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47196-47211
Activation Space Interventions Can Be Transferred Between Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47212-47286
Banyan: Improved Representation Learning with Explicit Structure
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47287-47301
Discrete and Continuous Difference of Submodular Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47302-47338
LieRE: Lie Rotational Positional Encodings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47339-47355
KernelBench: Can LLMs Write Efficient GPU Kernels?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47356-47415
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47416-47442
SAND: One-Shot Feature Selection with Additive Noise Distortion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47443-47455
Measuring Variable Importance in Heterogeneous Treatment Effects with Confidence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47456-47477
Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47478-47508
Validating Mechanistic Interpretations: An Axiomatic Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47509-47544
From Logits to Hierarchies: Hierarchical Clustering made Simple
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47545-47564
Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47565-47589
DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47590-47614
How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47615-47631
Can Transformers Reason Logically? A Study in SAT Solving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47632-47671
Preference Optimization for Combinatorial Optimization Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47672-47696
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47697-47716
Training Software Engineering Agents and Verifiers with SWE-Gym
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47717-47737
Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47738-47754
Variational Control for Guidance in Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47755-47780
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47781-47819
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47820-47836
Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47837-47858
Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47859-47878
Geometric Generative Modeling with Noise-Conditioned Graph Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47879-47901
Understanding High-Dimensional Bayesian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47902-47923
TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47924-47952
Optimization Proxies using Limited Labeled Data and Training Time – A Semi-Supervised Bayesian Neural Network Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47953-47970
Steer LLM Latents for Hallucination Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47971-47990
Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47991-48026
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48027-48040
Tensor Product Neural Networks for Functional ANOVA Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48041-48085
When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48086-48103
Flow Q-Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48104-48127
SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48128-48152
Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48153-48169
Ensemble Distribution Distillation via Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48170-48191
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48192-48244
Long-Form Speech Generation with Spoken Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48245-48261
Flexible and Efficient Grammar-Constrained Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48262-48275
Quantifying Memory Utilization with Effective State-Size
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48276-48334
On the Local Complexity of Linear Regions in Deep ReLU Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48335-48370
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48371-48392
Automatically Interpreting Millions of Features in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48393-48421
Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48422-48438
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48439-48469
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48470-48487
Stable Offline Value Function Learning with Bisimulation-based Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48488-48517
Representative Language Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48518-48541
Scaling Laws for Pre-training Agents and World Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48542-48562
Compact Matrix Quantum Group Equivariant Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48563-48594
Permutation Equivariant Neural Networks for Symmetric Tensors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48595-48634
Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48635-48661
Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48662-48678
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48679-48698
GoIRL: Graph-Oriented Inverse Reinforcement Learning for Multimodal Trajectory Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48699-48713
Hyper-Transforming Latent Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48714-48733
Approximating Latent Manifolds in Neural Networks via Vanishing Ideals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48734-48761
Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48762-48788
Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48789-48807
Conformal Prediction with Cellwise Outliers: A Detect-then-Impute Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48808-48831
KGMark: A Diffusion Watermark for Knowledge Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48832-48851
A Near Linear Query Lower Bound for Submodular Maximization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48852-48871
CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48872-48885
Circumventing Backdoor Space via Weight Symmetry
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48886-48922
Noise Conditional Variational Score Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48923-48947
Revisiting the Predictability of Performative, Social Events
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48948-48961
Mechanistic PDE Networks for Discovery of Governing Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48962-48973
Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:48974-49000
Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49001-49068
Training Deep Learning Models with Norm-Constrained LMOs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49069-49104
Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49105-49127
Wasserstein Policy Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49128-49149
Gandalf the Red: Adaptive Security for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49150-49194
Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49195-49258
Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49259-49276
Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49277-49291
Conditioning Diffusions Using Malliavin Calculus
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49292-49315
Revisiting Unbiased Implicit Variational Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49316-49328
Privacy Amplification Through Synthetic Data: Insights from Linear Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49329-49354
Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49355-49381
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49382-49398
Constrained Belief Updates Explain Geometric Structures in Transformer Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49399-49419
Do Bayesian Neural Networks Actually Behave Like Bayesian Models?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49420-49458
Rectifying Conformity Scores for Better Conditional Coverage
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49459-49492
To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49493-49536
Avoiding Catastrophe in Online Learning by Asking for Help
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49537-49568
Vintix: Action Model via In-Context Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49569-49602
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49603-49627
The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49628-49658
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49659-49688
DEALing with Image Reconstruction: Deep Attentive Least Squares
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49689-49708
MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49709-49736
Self-Consistency Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49737-49751
DCBM: Data-Efficient Visual Concept Bottleneck Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49752-49782
Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49783-49802
Graph Inverse Style Transfer for Counterfactual Explainability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49803-49829
WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49830-49859
Learning dynamics in linear recurrent neural networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49860-49902
Clone-Robust AI Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49903-49926
Janus: Dual-Server Multi-Round Secure Aggregation with Verifiability for Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49927-49945
SHE: Streaming-media Hashing Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49946-49958
Sample Efficient Demonstration Selection for In-Context Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49959-49982
Learning State-Based Node Representations from a Class Hierarchy for Fine-Grained Open-Set Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:49983-50005
Rethinking the Temperature for Federated Heterogeneous Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50006-50023
Universal Approximation Theorem of Deep Q-Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50024-50046
GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50047-50065
TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50066-50085
On the Out-of-Distribution Generalization of Self-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50086-50112
GCAL: Adapting Graph Models to Evolving Domain Shifts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50113-50129
Structure-informed Risk Minimization for Robust Ensemble Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50130-50141
PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50142-50170
How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50171-50188
Large Continual Instruction Assistant
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50189-50213
Enhancing Spectral GNNs: From Topology and Perturbation Perspectives
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50214-50234
Fast Incomplete Multi-view Clustering by Flexible Anchor Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50235-50245
GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50246-50268
DeFoG: Discrete Flow Matching for Graph Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50269-50326
Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50327-50337
WorldSimBench: Towards Video Generation Models as World Simulators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50338-50362
Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50363-50383
Info-Coevolution: An Efficient Framework for Data Model Coevolution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50384-50396
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50397-50434
Learning to Quantize for Training Vector-Quantized Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50435-50447
Exploiting Curvature in Online Convex Optimization with Delayed Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50448-50479
Lightweight-Mark: Rethinking Deep Learning-Based Watermarking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50480-50501
Feature out! Let Raw Image as Your Condition for Blind Face Restoration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50502-50525
The Lock-in Hypothesis: Stagnation by Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50526-50571
MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50572-50593
Efficient Graph Continual Learning via Lightweight Graph Neural Tangent Kernels-based Dataset Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50594-50618
Piloting Structure-Based Drug Design via Modality-Specific Optimal Schedule
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50619-50644
Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50645-50671
Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50672-50696
Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50697-50720
ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50721-50743
RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50744-50761
CoDy: Counterfactual Explainers for Dynamic Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50762-50785
P(all-atom) Is Unlocking New Path For Protein Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50786-50816
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50817-50847
AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50848-50864
Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50865-50892
Optimizing Test-Time Compute via Meta Reinforcement Finetuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50893-50925
Visual Autoregressive Modeling for Image Super-Resolution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50926-50948
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50949-50971
Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:50972-51008
Human-Aligned Image Models Improve Visual Decoding from the Brain
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51009-51038
Importance Sampling for Nonlinear Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51039-51059
The Relationship Between No-Regret Learning and Online Conformal Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51060-51078
Generation from Noisy Examples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51079-51093
Communicating Activations Between Language Model Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51094-51116
Differentially Private Boxplots
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51117-51139
You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51140-51155
FeatSharp: Your Vision Model Features, Sharper
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51156-51182
Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51183-51200
Diffusion Counterfactual Generation with Semantic Abduction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51201-51228
Towards Cost-Effective Reward Guided Text Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51229-51246
STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51247-51272
Adversarial Inception Backdoor Attacks against Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51273-51296
Statistical Hypothesis Testing for Auditing Robustness in Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51297-51313
Towards Memorization Estimation: Fast, Formal and Free
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51314-51340
RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51341-51368
When to retrain a machine learning model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51369-51404
Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51405-51420
Multi-View Graph Clustering via Node-Guided Contrastive Encoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51421-51435
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51436-51449
A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51450-51470
Inverse Optimization via Learning Feasible Regions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51471-51488
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51489-51502
Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51503-51530
Can Transformers Learn Full Bayesian Inference in Context?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51531-51582
Representative Ranking for Deliberation in the Public Sphere
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51583-51613
Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51614-51639
Understanding the Logic of Direct Preference Alignment through Logic
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51640-51658
General agents need world models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51659-51687
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51688-51702
Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51703-51723
Progressive Tempering Sampler with Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51724-51746
Resolving Lexical Bias in Model Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51747-51769
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51770-51786
FairPFN: A Tabular Foundation Model for Causal Fairness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51787-51808
A Reduction Framework for Distributionally Robust Reinforcement Learning under Average Reward
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51809-51850
Discrete Neural Algorithmic Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51851-51865
Concept Reachability in Diffusion Models: Beyond Dataset Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51866-51889
Separating Knowledge and Perception with Procedural Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51890-51904
Towards characterizing the value of edge embeddings in Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51905-51923
Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51924-51956
Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51957-51995
MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51996-52024
CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52025-52040
Fragments to Facts: Partial-Information Fragment Inference from LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52041-52064
Differential Privacy Under Class Imbalance: Methods and Empirical Insights
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52065-52109
Loss Functions and Operators Generated by f-Divergences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52110-52138
Implicit Riemannian Optimism with Applications to Min-Max Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52139-52172
G-Adaptivity: optimised graph-based mesh relocation for finite element methods
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52173-52197
No Free Lunch from Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52198-52224
From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52225-52257
Strategic Planning: A Top-Down Approach to Option Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52258-52302
LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52303-52344
Zero-Shot Offline Imitation Learning via Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52345-52381
Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52382-52421
Value-Based Deep RL Scales Predictably
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52422-52443
A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52444-52474
An Architecture Search Framework for Inference-Time Techniques
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52475-52507
Disparate Conditional Prediction in Multiclass Classifiers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52508-52525
Adversarial Reasoning at Jailbreaking Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52526-52551
Dueling Convex Optimization with General Preferences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52552-52564
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52565-52583
The Diffusion Duality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52584-52619
LGDM: Latent Guidance in Diffusion Models for Perceptual Evaluations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52620-52643
Benign Overfitting in Token Selection of Attention Mechanism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52644-52727
Tuning LLM Judge Design Decisions for 1/1000 of the Cost
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52728-52744
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52745-52777
Joint Learning of Energy-based Models and their Partition Function
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52778-52797
Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52798-52832
Collapse-Proof Non-Contrastive Self-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52833-52860
MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52861-52876
$∞$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52877-52893
The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52894-52921
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52922-52957
The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52958-52994
Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:52995-53018
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53019-53041
NestQuant: nested lattice quantization for matrix products and LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53042-53062
Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53063-53079
Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53080-53094
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53095-53114
Symmetry-Robust 3D Orientation Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53115-53131
How Do Large Language Monkeys Get Their Power (Laws)?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53132-53176
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53177-53266
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53267-53294
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53295-53315
FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53316-53342
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53343-53387
Generative Intervention Models for Causal Perturbation Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53388-53412
Hyperband-based Bayesian Optimization for Black-box Prompt Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53413-53438
Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53439-53466
Temperature-Annealed Boltzmann Generators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53467-53500
Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53501-53556
Adjustment for Confounding using Pre-Trained Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53557-53580
Mastering Board Games by External and Internal Planning with Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53581-53644
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53645-53662
The Disparate Benefits of Deep Ensembles
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53663-53702
Learning Representations of Instruments for Partial Identification of Treatment Effects
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53703-53727
Cover learning for large-scale topology representation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53728-53756
Differentially Private Federated $k$-Means Clustering with Server-Side Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53757-53790
Bootstrapping Self-Improvement of Language Model Programs for Zero-Shot Schema Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53791-53826
LLMs Can Reason Faster Only If We Let Them
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53827-53842
SEMU: Singular Value Decomposition for Efficient Machine Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53843-53866
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53867-53905
Leveraging Per-Instance Privacy for Machine Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53906-53922
Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53923-53939
Zebra: In-Context Generative Pretraining for Solving Parametric PDEs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53940-53988
Doubly Robust Conformalized Survival Analysis with Right-Censored Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:53989-54029
Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54030-54057
Scaling Test-Time Compute Without Verification or RL is Suboptimal
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54058-54094
GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54095-54111
Confounder-Free Continual Learning via Recursive Feature Normalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54112-54142
Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54143-54166
SEAD: Unsupervised Ensemble of Streaming Anomaly Detectors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54167-54185
ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54186-54202
LongRoPE2: Near-Lossless LLM Context Window Scaling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54203-54218
Do Multiple Instance Learning Models Transfer?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54219-54238
Continuous Visual Autoregressive Generation via Score Maximization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54239-54253
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54254-54274
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54275-54299
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54300-54325
X-Hacking: The Threat of Misguided AutoML
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54326-54363
PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54364-54380
Compositional Flows for 3D Molecule and Synthesis Pathway Co-design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54381-54409
Active Reward Modeling: Adaptive Preference Labeling for Large Language Model Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54410-54430
Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54431-54456
Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54457-54475
Algorithms with Calibrated Machine Learning Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54476-54498
Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54499-54514
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54515-54558
BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54559-54581
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54582-54599
Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54600-54610
SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54611-54631
ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54632-54643
Drug-TTA: Test-Time Adaptation for Drug Virtual Screening via Multi-task Meta-Auxiliary Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54644-54662
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54663-54700
Zero-Shot Generalization of GNNs over Distinct Attribute Domains
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54701-54731
On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54732-54771
Learning Survival Distributions with the Asymmetric Laplace Distribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54772-54809
Counting atoms faster: policy-based nuclear magnetic resonance pulse sequencing for atomic abundance measurement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54810-54824
Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54825-54863
Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54864-54891
LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54892-54903
Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54904-54918
Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54919-54933
Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54934-54959
Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54960-54980
LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54981-54993
Targeted control of fast prototyping through domain-specific interface
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:54994-55015
Direct Prediction Set Minimization via Bilevel Conformal Classifier Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55016-55045
EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55046-55064
DSBRouter: End-to-end Global Routing via Diffusion Schrödinger Bridge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55065-55081
Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55082-55095
Minimum Width for Universal Approximation using Squashable Activation Functions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55096-55121
Online Pre-Training for Offline-to-Online Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55122-55144
Sassha: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55145-55171
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55172-55194
Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55195-55204
Offline Model-based Optimization for Real-World Molecular Discovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55205-55254
Tokenized Bandit for LLM Decoding and Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55255-55282
Statistical Test for Feature Selection Pipelines by Selective Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55283-55302
Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55303-55324
LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55325-55359
Diversified Flow Matching with Translation Identifiability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55360-55378
Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55379-55402
Refining Adaptive Zeroth-Order Optimization at Ease
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55403-55426
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55427-55450
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55451-55473
Probabilistic Factorial Experimental Design for Combinatorial Interventions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55474-55492
CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55493-55510
Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55511-55532
Variational Phylogenetic Inference with Products over Bipartitions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55533-55555
EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55556-55590
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55591-55613
Self-Organizing Visual Prototypes for Non-Parametric Representation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55614-55630
Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55631-55656
VCT: Training Consistency Models with Variational Noise Coupling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55657-55683
Byzantine-Resilient Federated Alternating Gradient Descent and Minimization for Partly-Decoupled Low Rank Matrix Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55684-55701
Avoiding spurious sharpness minimization broadens applicability of SAM
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55702-55719
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55720-55739
Efficiently Serving Large Multimodal Models Using EPD Disaggregation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55740-55756
"Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55757-55787
Test-Time Canonicalization by Foundation Models for Robust Perception
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55788-55809
A General Framework for Inference-time Scaling and Steering of Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55810-55827
Geometric Algebra Planes: Convex Implicit Neural Volumes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55828-55853
Layer by Layer: Uncovering Hidden Representations in Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55854-55875
Improving the Diffusability of Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55876-55905
Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55906-55949
In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55950-55971
Functional Alignment Can Mislead: Examining Model Stitching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55972-55998
Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:55999-56017
Private Model Personalization Revisited
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56018-56067
Conformal Prediction as Bayesian Quadrature
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56068-56084
Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56085-56100
Learning with Exact Invariances in Polynomial Time
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56101-56121
Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56122-56147
Learning Classifiers That Induce Markets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56148-56172
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56173-56203
LipsNet++: Unifying Filter and Controller into a Policy Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56204-56241
History-Guided Video Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56242-56280
Distributed Retraction-Free and Communication-Efficient Optimization on the Stiefel Manifold
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56281-56318
PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56319-56336
Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56337-56362
Smooth Interpolation for Improved Discrete Graph Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56363-56388
Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56389-56413
Deep Unsupervised Hashing via External Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56414-56428
Learning Invariant Causal Mechanism from Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56429-56464
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56465-56479
Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56480-56498
PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56499-56530
Learning Distances from Data with Normalizing Flows and Score Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56531-56548
DocVXQA: Context-Aware Visual Explanations for Document Question Answering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56549-56569
Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56570-56614
Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56615-56649
CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56650-56691
An Asymptotically Optimal Approximation Algorithm for Multiobjective Submodular Maximization at Scale
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56692-56718
Overtrained Language Models Are Harder to Fine-Tune
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56719-56789
Online Learning with Unknown Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56790-56819
The Polynomial Stein Discrepancy for Assessing Moment Convergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56820-56842
PaperBench: Evaluating AI’s Ability to Replicate AI Research
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56843-56873
Integration-free Kernels for Equivariant Gaussian Process Modelling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56874-56898
Prediction models that learn to avoid missing values
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56899-56919
Learning Adversarial MDPs with Stochastic Hard Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56920-56951
Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56952-56989
LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56990-57007
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57008-57029
Multimodal Medical Code Tokenizer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57030-57045
A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57046-57083
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57084-57111
SBGD: Improving Graph Diffusion Generative Model via Stochastic Block Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57112-57130
Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57131-57143
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57144-57163
On the Benefits of Active Data Collection in Operator Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57164-57190
Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57191-57211
A Generalization Result for Convergence in Learning-to-Optimize
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57212-57230
COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57231-57248
A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57249-57269
Unified Analysis of Continuous Weak Features Learning with Applications to Learning from Missing Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57270-57310
Tracking Most Significant Shifts in Infinite-Armed Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57311-57335
Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57336-57354
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57355-57373
Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57374-57390
Directed Graph Grammars for Sequence-based Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57391-57418
Wait-Less Offline Tuning and Re-solving for Online Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57419-57449
Invariant Deep Uplift Modeling for Incentive Assignment in Online Marketing via Probability of Necessity and Sufficiency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57450-57468
Is Noise Conditioning Necessary for Denoising Generative Models?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57469-57502
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57503-57522
CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57523-57543
Scaling Laws for Floating–Point Quantization Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57544-57570
Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57571-57586
FlatQuant: Flatness Matters for LLM Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57587-57613
Spherical-Nested Diffusion Model for Panoramic Image Outpainting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57614-57630
Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57631-57650
Average Certified Radius is a Poor Metric for Randomized Smoothing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57651-57666
DS-VLM: Diffusion Supervision Vision Language Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57667-57679
FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57680-57693
AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57694-57711
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57712-57727
The Emperor’s New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57728-57753
Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57754-57772
Earley-Driven Dynamic Pruning for Efficient Structured Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57773-57789
Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57790-57807
video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57808-57827
A Sample Efficient Conditional Independence Test in the Presence of Discretization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57828-57853
Idiosyncrasies in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57854-57885
Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57886-57937
CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57938-57960
Sample-specific Noise Injection for Diffusion-based Adversarial Purification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57961-57983
Parrot: Multilingual Visual Instruction Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57984-58007
Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58008-58028
Adaptive Partitioning Schemes for Optimistic Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58029-58064
Identifying Metric Structures of Deep Latent Variable Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58065-58087
No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58088-58105
Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58106-58141
Features are fate: a theory of transfer learning in high-dimensional regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58142-58168
Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58169-58188
Selective Response Strategies for GenAI
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58189-58226
Training a Generally Curious Agent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58227-58281
Physics-Informed Weakly Supervised Learning For Interatomic Potentials
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58282-58310
Instance-Optimal Pure Exploration for Linear Bandits on Continuous Arms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58311-58338
Distributionally Robust Active Learning for Gaussian Process Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58339-58358
Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58359-58405
Towards Learning to Complete Anything in Lidar
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58406-58430
Neutral residues: revisiting adapters for model extension
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58431-58447
FedBEns: One-Shot Federated Learning based on Bayesian Ensemble
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58448-58466
Scalable Equilibrium Sampling with Sequential Boltzmann Generators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58467-58498
Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58499-58544
Actor-Critics Can Achieve Optimal Sample Efficiency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58545-58590
$S^2$FGL: Spatial Spectral Federated Graph Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58591-58602
BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58603-58620
WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58621-58636
Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58637-58657
Cradle: Empowering Foundation Agents towards General Computer Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58658-58725
Vision-Language Model Selection and Reuse for Downstream Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58726-58738
Reflection-Window Decoding: Text Generation with Selective Refinement
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58739-58764
Learning Single Index Models with Diffusion Priors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58765-58788
Learning Monotonic Probabilities with a Generative Cost Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58789-58804
Investigating the Overlooked Hessian Structure: From CNNs to LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58805-58831
Concentration Distribution Learning from Label Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58832-58841
Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58842-58882
Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58883-58904
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58905-58930
Efficient Heterogeneity-Aware Federated Active Data Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58931-58943
LOGO — Long cOntext aliGnment via efficient preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58944-58968
Controllable Data Generation with Hierarchical Neural Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58969-58988
Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58989-59004
Multi-Session Budget Optimization for Forward Auction-based Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59005-59016
PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59017-59065
Optimizing Language Models for Inference Time Objectives using Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59066-59085
S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59086-59102
(How) Can Transformers Predict Pseudo-Random Numbers?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59103-59131
Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59132-59153
Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks’ Internal Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59154-59181
Deep Bayesian Filter for Bayes-Faithful Data Assimilation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59182-59209
Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59210-59236
A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59237-59258
Geometric Contact Flows: Contactomorphisms for Dynamics and Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59259-59284
Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59285-59303
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59304-59325
WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59326-59354
Comparing Few to Rank Many: Active Human Preference Learning Using Randomized Frank-Wolfe Method
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59355-59376
What can large language models do for sustainable food?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59377-59433
Hidden No More: Attacking and Defending Private Third-Party LLM Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59434-59469
NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59470-59491
MixMin: Finding Data Mixtures via Convex Minimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59492-59508
Optimal transport-based conformal prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59509-59527
Selective Prompt Anchoring for Code Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59528-59551
On Teacher Hacking in Language Model Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59552-59569
Learnable Spatial-Temporal Positional Encoding for Link Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59570-59597
Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59598-59620
New Bounds for Sparse Variational Gaussian Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59621-59638
Latent Mamba Operator for Partial Differential Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59639-59667
QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59668-59686
LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59687-59722
Understanding the Emergence of Multimodal Representation Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59723-59760
Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59761-59783
Understanding Chain-of-Thought in LLMs through Information Theory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59784-59811
Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59812-59828
Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59829-59845
Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59846-59866
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59867-59882
Accelerating Spectral Clustering under Fairness Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59883-59903
ADIOS: Antibody Development via Opponent Shaping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59904-59923
Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59924-59944
Identifying Causal Direction via Variational Bayesian Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59945-59968
Tree-Sliced Wasserstein Distance: A Geometric Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:59969-60000
Tree-Sliced Wasserstein Distance with Nonlinear Projection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60001-60033
Variance-Reduced Forward-Reflected-Backward Splitting Methods for Nonmonotone Generalized Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60034-60071
Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60072-60098
AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60099-60146
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60147-60182
RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60183-60217
Improving Generalization with Flat Hilbert Bayesian Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60218-60237
Reliable and Efficient Amortized Model-based Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60238-60265
MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60266-60279
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60280-60300
Set Valued Predictions For Robust Domain Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60301-60335
On the Impact of Performative Risk Minimization for Binary Random Variables
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60336-60361
Ranked from Within: Ranking Large Multimodal Models Without Labels
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60362-60384
Subgoal-Guided Policy Heuristic Search with Learned Subgoals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60385-60403
SafeArena: Evaluating the Safety of Autonomous Web Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60404-60441
The Batch Complexity of Bandit Pure Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60442-60468
Dynamic Sparse Training of Diagonally Sparse Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60469-60492
Toward a Unified Theory of Gradient Descent under Generalized Smoothness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60493-60514
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60515-60529
Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60530-60560
Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60561-60589
Online Curvature-Aware Replay: Leveraging $\mathbf2^nd$ Order Information for Online Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60590-60609
Does Data Scaling Lead to Visual Compositional Generalization?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60610-60634
Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60635-60656
A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60657-60710
Clustering via Self-Supervised Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60711-60726
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60727-60747
Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60748-60763
Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60764-60791
Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60792-60815
When to Forget? Complexity Trade-offs in Machine Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60816-60832
From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60833-60856
Dimension-Independent Rates for Structured Neural Density Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60857-60879
AutoCATE: End-to-End, Automated Treatment Effect Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60880-60904
Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60905-60923
Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60924-60963
Teaching Transformers Causal Reasoning through Axiomatic Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60964-60983
Covered Forest: Fine-grained generalization analysis of graph neural networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:60984-61034
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61035-61070
Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61071-61107
Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61108-61125
Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61126-61149
PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61150-61189
Softmax is not Enough (for Sharp Size Generalisation)
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61190-61211
Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61212-61239
Automated Benchmark Generation for Repository-Level Coding Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61240-61265
Improving Diversity in Language Models: When Temperature Fails, Change the Loss
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61266-61300
GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61301-61322
Positional Encoding meets Persistent Homology on Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61323-61343
BaxBench: Can LLMs Generate Correct and Secure Backends?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61344-61390
From Language Models over Tokens to Language Models over Characters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61391-61412
Language Models over Canonical Byte-Pair Encodings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61413-61443
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61444-61479
Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61480-61497
AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61498-61512
Flexibility-conditioned protein structure design with flow matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61513-61533
PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61534-61563
Computing Optimal Transport Maps and Wasserstein Barycenters Using Conditional Normalizing Flows
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61564-61581
Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61582-61600
Prune ’n Predict: Optimizing LLM Decision-making with Conformal Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61601-61634
What Makes a Good Feedforward Computational Graph?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61635-61651
B-score: Detecting biases in large language models using response history
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61652-61688
Equivariant Polynomial Functional Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61689-61744
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61745-61768
Feature Importance Metrics in the Presence of Missing Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61769-61789
Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61790-61809
Generalized Interpolating Discrete Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61810-61843
Topological Signatures of Adversaries in Multimodal Alignments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61844-61867
MiraGe: Editable 2D Images using Gaussian Splatting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61868-61884
Behavioral Exploration: Learning to Explore via In-Context Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61885-61912
Rethink GraphODE Generalization within Coupled Dynamical System
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61913-61928
EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61929-61941
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61942-61955
Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:61956-62019
Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62020-62083
Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62084-62101
Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62102-62120
Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62121-62134
Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62135-62154
Action Dubber: Timing Audible Actions via Inflectional Flow
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62155-62171
Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62172-62221
How to set AdamW’s weight decay as you scale model and dataset size
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62222-62250
Backdoor Attacks in Token Selection of Attention Mechanism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62251-62296
Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62297-62344
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62345-62356
Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62357-62372
Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62373-62400
Riemannian Diffusion Adaptation for Distributed Optimization on Manifolds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62401-62422
TruthFlow: Truthful LLM Generation via Representation Flow Correction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62423-62444
Federated Causal Structure Learning with Non-identical Variable Sets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62445-62466
A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62467-62504
Learning Event Completeness for Weakly Supervised Video Anomaly Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62505-62517
Efficient Source-free Unlearning via Energy-Guided Data Synthesis and Discrimination-Aware Multitask Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62518-62528
MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62529-62554
How to Evaluate and Mitigate IP Infringement in Visual Generative AI?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62555-62574
Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62575-62595
FrameBridge: Improving Image-to-Video Generation with Bridge Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62596-62626
TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62627-62651
WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62652-62671
CodeSync: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62672-62700
On Understanding Attention-Based In-Context Learning for Categorical Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62701-62728
Sampling from Binary Quadratic Distributions via Stochastic Localization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62729-62760
Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62761-62783
Compositional Scene Understanding through Inverse Generative Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62784-62803
Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62804-62824
GTR: A General, Multi-View, and Dynamic Framework for Trajectory Representation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62825-62844
DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62845-62856
FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62857-62889
From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62890-62915
GRAM: A Generative Foundation Reward Model for Reward Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62916-62936
Optimizing Large Language Model Training Using FP4 Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62937-62957
MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62958-62979
LLM-Augmented Chemical Synthesis and Design Decision Programs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62980-63001
PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63002-63015
MATS: An Audio Language Model under Text-only Supervision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63016-63035
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63036-63087
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63088-63112
ELoRA: Low-Rank Adaptation for Equivariant GNNs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63113-63135
Projection Pursuit Density Ratio Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63136-63168
Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63169-63185
Unified K-Means Clustering with Label-Guided Manifold Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63186-63199
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63200-63210
Transfer Learning for Nonparametric Contextual Dynamic Pricing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63211-63244
Event-Customized Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63245-63265
IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63266-63289
Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63290-63307
M+: Extending MemoryLLM with Scalable Long-Term Memory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63308-63323
ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63324-63344
Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63345-63354
Large Displacement Motion Transfer with Unsupervised Anytime Interpolation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63355-63364
Learning Fused State Representations for Control from Multi-View Observations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63365-63386
polybasic Speculative Decoding Through a Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63387-63398
One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63399-63416
Improving Rationality in the Reasoning Process of Language Models through Self-playing Game
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63417-63438
Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63439-63466
Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63467-63489
Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63490-63515
DANCE: Dual Unbiased Expansion with Group-acquired Alignment for Out-of-distribution Graph Fairness Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63516-63529
Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63530-63548
Differentiable Solver Search for Fast Diffusion Sampling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63549-63568
EpiCoder: Encompassing Diversity and Complexity in Code Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63569-63606
Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63607-63620
Enhancing Foundation Models with Federated Domain Knowledge Infusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63621-63635
A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63636-63661
NICE Data Selection for Instruction Tuning in LLMs with Non-differentiable Evaluation Metric
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63662-63689
CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63690-63706
Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63707-63733
Bayesian Active Learning for Bivariate Causal Discovery
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63734-63754
Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63755-63776
DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63777-63791
Generalization in Federated Learning: A Conditional Mutual Information Framework
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63792-63823
SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63824-63839
Attention-Only Transformers via Unrolled Subspace Denoising
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63840-63859
Variational Counterfactual Intervention Planning to Achieve Target Outcomes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63860-63881
Textural or Textual: How Vision-Language Models Read Text in Images
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63882-63896
Agent Workflow Memory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63897-63911
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63912-63928
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63929-63951
Teaching Physical Awareness to LLMs through Sounds
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63952-63971
MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63972-64004
Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI Synthesis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64005-64022
Diffusion Sampling Correction via Approximately 10 Parameters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64023-64043
Taming Rectified Flow for Inversion and Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64044-64058
Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64059-64083
Safety Reasoning with Guidelines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64084-64108
LightGTS: A Lightweight General Time Series Forecasting Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64109-64126
Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64127-64151
Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64152-64201
The Sparse-Plus-Low-Rank Quasi-Newton Method for Entropic-Regularized Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64202-64221
INRFlow: Flow Matching for INRs in Ambient Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64222-64243
Distributionally Robust Policy Learning under Concept Drifts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64244-64281
Learning-Order Autoregressive Models with Application to Molecular Graph Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64282-64301
High-Dimensional Tensor Regression With Oracle Properties
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64302-64342
Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64343-64366
GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64367-64376
Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64377-64402
Online Clustering of Dueling Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64403-64431
Origin Identification for Text-Guided Image-to-Image Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64432-64447
Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64448-64462
Enhancing Graph Contrastive Learning for Protein Graphs from Perspective of Invariance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64463-64490
Predictive Performance of Deep Quantum Data Re-uploading Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64491-64524
Learning Dynamics in Continual Pre-Training for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64525-64548
Discovering Latent Causal Graphs from Spatiotemporal Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64549-64585
DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64586-64603
Griffin: Towards a Graph-Centric Relational Database Foundation Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64604-64627
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64628-64654
BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64655-64669
CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64670-64689
GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64690-64710
Knowledge-Guided Wasserstein Distributionally Robust Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64711-64733
Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64734-64749
Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64750-64772
Accelerating Large Language Model Reasoning via Speculative Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64773-64805
Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64806-64821
CoSER: Coordinating LLM-Based Persona Simulation of Established Roles
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64822-64858
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64859-64879
Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64880-64894
Bridging Layout and RTL: Knowledge Distillation based Timing Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64895-64913
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64914-64936
Demonstration Selection for In-Context Learning via Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64937-64954
QuanONet: Quantum Neural Operator with Application to Differential Equation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64955-64975
Improving Model Alignment Through Collective Intelligence of Open-Source Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64976-64997
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64998-65019
Off-Policy Evaluation under Nonignorable Missing Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65020-65058
From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65059-65074
Enhancing Visual Localization with Cross-Domain Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65075-65090
A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65091-65121
Provable Zero-Shot Generalization in Offline Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65122-65143
A Non-isotropic Time Series Diffusion Model with Moving Average Transitions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65144-65166
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $α$-$β$-Divergence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65167-65212
Revisiting Differentially Private Algorithms for Decentralized Online Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65213-65235
CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65236-65252
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65253-65277
Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65278-65290
FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65291-65309
3D Question Answering via only 2D Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65310-65325
Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65326-65345
Fusing Reward and Dueling Feedback in Stochastic Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65346-65367
Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65368-65399
AutoAL: Automated Active Learning with Differentiable Query Strategy Search
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65400-65411
FDGen: A Fairness-Aware Graph Generation Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65412-65428
M$^3$HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65429-65448
Improving Value Estimation Critically Enhances Vanilla Policy Gradient
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65449-65463
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65464-65479
Optimal Algorithm for Max-Min Fair Bandit
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65480-65495
Beyond Message Passing: Neural Graph Pattern Machine
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65496-65517
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65518-65555
Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65556-65574
Demystifying Singular Defects in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65575-65594
Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65595-65617
A Theory for Conditional Generative Modeling on Multiple Data Sources
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65618-65654
Stabilizing Sample Similarity in Representation via Mitigating Random Consistency
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65655-65686
Rényi Neural Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65687-65707
A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65708-65737
Towards the Causal Complete Cause of Multi-Modal Representation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65738-65775
Equivalence is All: A Unified View for Self-supervised Graph Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65776-65789
N2GON: Neural Networks for Graph-of-Net with Position Awareness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65790-65801
Scaling Large Motion Models with Million-Level Human Motions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65802-65827
Learning Cascade Ranking as One Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65828-65844
COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65845-65866
Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65867-65896
Adaptive Elicitation of Latent Information Using Natural Language
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65897-65917
TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65918-65935
Prompt-based Depth Pruning of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65936-65948
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65949-65980
AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65981-65996
Identifying and Understanding Cross-Class Features in Adversarial Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:65997-66014
Representation Surgery in Model Merging with Probabilistic Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66015-66032
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66033-66061
Closed-form Solutions: A New Perspective on Solving Differential Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66062-66083
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66084-66102
Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66103-66117
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66118-66136
Stream-level Flow Matching with Gaussian Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66137-66154
Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66155-66177
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66178-66193
Zero-Inflated Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66194-66258
Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66259-66279
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66280-66299
Self-Consuming Generative Models with Adversarially Curated Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66300-66321
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66322-66357
Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66358-66377
Perception in Reflection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66378-66396
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66397-66418
Adversarial Combinatorial Semi-bandits with Graph Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66419-66436
Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66437-66466
Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66467-66480
Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66481-66519
Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66520-66538
Distributed Conformal Prediction via Message Passing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66539-66557
DiffusionVLA: Scaling Robot Foundation Models via Unified Diffusion and Autoregression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66558-66574
An Efficient Pruner for Large Language Model with Theoretical Guarantee
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66575-66596
Clustering Properties of Self-Supervised Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66597-66616
TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66617-66632
PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66633-66677
Organize the Web: Constructing Domains Enhances Pre-Training Data Curation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66678-66705
Spatial Reasoning with Denoising Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66706-66725
Certification for Differentially Private Prediction in Gradient-Based Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66726-66745
Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66746-66771
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66772-66832
Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66833-66860
Exploring Representations and Interventions in Time Series Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66861-66886
Context is Key: A Benchmark for Forecasting with Essential Textual Information
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66887-66944
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66945-66970
An End-to-End Model for Logits-Based Large Language Models Watermarking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66971-66991
Pointwise Information Measures as Confidence Estimators in Deep Neural Networks: A Comparative Study
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66992-67034
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67035-67080
Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67081-67110
Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67111-67127
Cross-Modal Alignment via Variational Copula Modelling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67128-67146
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67147-67171
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67172-67183
Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67184-67201
Bivariate Causal Discovery with Proxy Variables: Integral Solving and Beyond
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67202-67259
CollabLLM: From Passive Responders to Active Collaborators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67260-67283
How Do Transformers Learn Variable Binding in Symbolic Programs?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67284-67299
In-Context Learning as Conditioned Associative Memory Retrieval
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67300-67325
GPEN: Global Position Encoding Network for Enhanced Subgraph Representation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67326-67341
SpikF: Spiking Fourier Network for Efficient Long-term Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67342-67368
Label Distribution Propagation-based Label Completion for Crowdsourcing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67369-67381
Thinking LLMs: General Instruction Following with Thought Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67382-67407
Divide and Conquer: Learning Label Distribution with Subtasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67408-67426
Preserving AUC Fairness in Learning with Noisy Protected Groups
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67427-67448
Few-Shot Learner Generalizes Across AI-Generated Image Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67449-67460
Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67461-67475
Aligning Spoken Dialogue Models from User Interactions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67476-67498
Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67499-67536
Identifying biological perturbation targets through causal differential networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67537-67561
$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67562-67583
Learning Optimal Multimodal Information Bottleneck Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67584-67622
When Do LLMs Help With Node Classification? A Comprehensive Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67623-67649
TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67650-67669
In-Context Deep Learning via Transformer Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67670-67718
FLAM: Frame-Wise Language-Audio Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67719-67740
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67741-67755
On the Emergence of Position Bias in Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67756-67781
Distributed Parallel Gradient Stacking(DPGS): Solving Whole Slide Image Stacking Challenge in Multi-Instance Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67782-67792
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67793-67809
Directly Forecasting Belief for Reinforcement Learning with Delays
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67810-67832
Efficient Personalized Adaptation for Physiological Signal Foundation Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67833-67851
BackSlash: Rate Constrained Optimized Training of Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67852-67863
Towards Robustness and Explainability of Automatic Algorithm Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67864-67887
Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67888-67916
Rethinking Chain-of-Thought from the Perspective of Self-Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67917-67937
Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67938-67958
Supercharging Graph Transformers with Advective Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67959-67985
An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs’ Sentimental Perception Capability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:67986-67999
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68000-68014
Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68015-68035
Simplifying DINO via Coding Rate Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68036-68059
Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68060-68077
Weight matrices compression based on PDB model in deep neural networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68078-68093
Adaptive Localization of Knowledge Negation for Continual LLM Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68094-68117
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68118-68142
PINNsAgent: Automated PDE Surrogation with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68143-68165
Distinguishing Cause from Effect with Causal Velocity Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68166-68189
OW-VAP: Visual Attribute Parsing for Open World Object Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68190-68207
Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68208-68224
Causal Abstraction Inference under Lossy Representations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68225-68235
Learning the Electronic Hamiltonian of Large Atomic Structures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68236-68257
Minerva: A Programmable Memory Test Benchmark for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68258-68276
DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68277-68291
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68292-68315
GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68316-68342
When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68343-68363
Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68364-68390
Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68391-68439
MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68440-68458
LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68459-68471
ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68472-68490
Are High-Quality AI-Generated Images More Difficult for Models to Detect?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68491-68512
Trustworthy Machine Learning through Data-Specific Indistinguishability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68513-68534
A First-order Generative Bilevel Optimization Framework for Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68535-68558
Teaching Language Models to Critique via Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68559-68577
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68578-68598
The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68599-68625
KIND: Knowledge Integration and Diversion for Training Decomposable Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68626-68645
A Multi-Region Brain Model to Elucidate the Role of Hippocampus in Spatially Embedded Decision-Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68646-68670
Prior Knowledge Guided Neural Architecture Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68671-68686
Learning Vision and Language Concepts for Controllable Image Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68687-68709
Latent Diffusion Planning for Imitation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68710-68724
Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68725-68745
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68746-68776
FG-CLIP: Fine-Grained Visual and Textual Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68777-68793
Robust Reward Alignment via Hypothesis Space Batch Cutting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68794-68812
Simple Policy Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68813-68824
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68825-68846
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68847-68869
$\textttI$^2$MoE$: Interpretable Multimodal Interaction-aware Mixture-of-Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68870-68888
Knowledge Swapping via Learning and Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68889-68899
MIRROR: Make Your Object-Level Multi-View Generation More Consistent with Training-Free Rectification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68900-68927
One-Pass Feature Evolvable Learning with Theoretical Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68928-68952
MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68953-68969
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68970-68997
ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68998-69016
Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69017-69058
Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69059-69077
DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69078-69095
RLTHF: Targeted Human Feedback for LLM Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69096-69115
Rethinking Benign Overfitting in Two-Layer Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69116-69146
Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69147-69159
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69160-69188
Global Optimization with a Power-Transformed Objective and Gaussian Smoothing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69189-69216
Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69217-69239
Concept-Based Unsupervised Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69240-69261
Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69262-69278
Robust Multi-bit Text Watermark with LLM-based Paraphrasers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69279-69292
Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69293-69317
AdvAgent: Controllable Blackbox Red-teaming on Web Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69318-69330
RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69331-69362
RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69363-69376
Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69377-69431
Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69432-69450
Scalable Model Merging with Progressive Layer-wise Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69451-69477
Contradiction Retrieval via Contrastive Learning with Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69478-69506
Sub-Sequential Physics-Informed Learning with State Space Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69507-69525
Toward Efficient Kernel-Based Solvers for Nonlinear PDEs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69526-69544
Linear Contextual Bandits With Interference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69545-69582
Investigating Non-Transitivity in LLM-as-a-Judge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69583-69612
On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69613-69646
ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69647-69674
Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69675-69688
ProSec: Fortifying Code LLMs with Proactive Security Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69689-69704
Heterogeneous Label Shift: Theory and Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69705-69724
KV Shifting Attention Enhances Language Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69725-69748
Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69749-69771
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69772-69805
Learngene Tells You How to Customize: Task-Aware Parameter Initialization at Flexible Scales
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69806-69818
XAttention: Block Sparse Attention with Antidiagonal Scoring
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69819-69831
MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69832-69848
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69849-69877
CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69878-69907
CoastalBench: A Decade-Long High-Resolution Dataset to Emulate Complex Coastal Processes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69908-69920
Phase and Amplitude-aware Prompting for Enhancing Adversarial Robustness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69921-69935
DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69936-69949
Unlocking the Power of SAM 2 for Few-Shot Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69950-69966
Meta-Reinforcement Learning with Adaptation from Human Feedback via Preference-Order-Preserving Task Embedding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69967-69991
Reducing Tool Hallucination via Reliability Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:69992-70006
Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70007-70019
Test-time Adapted Reinforcement Learning with Action Entropy Regularization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70020-70031
Componential Prompt-Knowledge Alignment for Domain Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70032-70046
RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70047-70064
Multi-objective Linear Reinforcement Learning with Lexicographic Rewards
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70065-70085
Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70086-70104
PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70105-70119
Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70120-70159
Haste Makes Waste: A Simple Approach for Scaling Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70160-70182
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70183-70204
Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70205-70248
Reducing Confounding Bias without Data Splitting for Causal Inference via Optimal Transport
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70249-70267
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70268-70288
Training High Performance Spiking Neural Network by Temporal Model Calibration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70289-70308
CALM: Consensus-Aware Localized Merging for Multi-Task Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70309-70329
Heterogeneous Sufficient Dimension Reduction and Subspace Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70330-70409
Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70410-70441
Survival Analysis via Density Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70442-70471
A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70472-70497
The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70498-70514
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70515-70549
HyperIV: Real-time Implied Volatility Smoothing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70550-70564
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70576-70631
Disentangled Graph Spectral Domain Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70632-70648
Tensor-Var: Efficient Four-Dimensional Variational Data Assimilation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70649-70679
Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70680-70703
Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70704-70744
Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70745-70755
Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70756-70775
Learning Adaptive Lighting via Channel-Aware Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70776-70792
Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70793-70812
Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70813-70832
Let LLM Tell What to Prune and How Much to Prune
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70833-70849
ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70850-70872
Do We Really Need Message Passing in Brain Network Modeling?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70873-70887
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70888-70913
MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70914-70926
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70927-70942
BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70943-70952
SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70953-70972
CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:70973-70999
Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71000-71033
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71034-71050
On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71051-71072
HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71073-71091
PENCIL: Long Thoughts with Short Memory
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71092-71156
One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71157-71176
Demystifying Long Chain-of-Thought Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71177-71209
Neural Guided Diffusion Bridges
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71210-71230
Mixture of Experts Made Intrinsically Interpretable
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71231-71248
Dimension-Free Adaptive Subgradient Methods with Frequent Directions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71249-71274
Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71275-71301
Efficient Quantification of Multimodal Interaction at Sample Level
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71302-71317
Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71318-71357
Non-asymptotic Error Bounds in $\mathcalW_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71358-71382
Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71383-71404
DVI:A Derivative-based Vision Network for INR
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71405-71424
One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71425-71440
Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71441-71458
Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71459-71486
HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71487-71507
When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71508-71520
Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71521-71542
unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71543-71568
Neural Event-Triggered Control with Optimal Scheduling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71569-71592
Enhancing Graph Invariant Learning from a Negative Inference Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71593-71611
Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71612-71647
SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71648-71667
Arrow: Accelerator for Time Series Causal Discovery with Time Weaving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71668-71686
Diversity By Design: Leveraging Distribution Matching for Offline Model-Based Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71687-71738
Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71739-71764
OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71765-71779
Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71780-71797
Understanding Model Ensemble in Transferable Adversarial Attack
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71798-71833
An Analysis for Reasoning Bias of Language Models with Small Initialization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71834-71864
Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71865-71883
Near Optimal Best Arm Identification for Clustered Bandits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71884-71909
Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71910-71937
Emotional Face-to-Speech
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71938-71958
An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71959-71978
AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71979-71997
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71998-72040
Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72041-72062
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72063-72090
Towards Robust Influence Functions with Flat Validation Minima
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72091-72111
Non-stationary Diffusion For Probabilistic Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72112-72130
Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72131-72180
Action-Constrained Imitation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72181-72195
A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72196-72209
Relational Invariant Learning for Robust Solvation Free Energy Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72210-72227
MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72228-72243
All-atom inverse protein folding through discrete flow matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72244-72257
iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72258-72276
From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72277-72316
Random Registers for Cross-Domain Few-Shot Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72317-72333
Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72334-72348
Constrain Alignment with Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72349-72363
TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72364-72392
From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72393-72413
A Recipe for Causal Graph Regression: Confounding Effects Revisited
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72414-72427
Which Attention Heads Matter for In-Context Learning?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72428-72461
Trajectory World Models for Heterogeneous Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72462-72484
CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72485-72504
Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72505-72534
Interpreting the Repeated Token Phenomenon in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72535-72555
World Model Implanting for Test-time Adaptation of Embodied Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72556-72573
Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72574-72617
Monte Carlo Tree Diffusion for System 2 Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72618-72640
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72641-72655
Quadratic Upper Bound for Boosting Robustness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72656-72676
Maximum Total Correlation Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72677-72699
Test-time Correlation Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72700-72729
Effective and Efficient Masked Image Generation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72730-72746
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72747-72785
Fully Heteroscedastic Count Regression with Deep Double Poisson Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72786-72818
Radio: Rate–Distortion Optimization for Large Language Model Compression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72819-72836
UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein Distance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72837-72852
Bifurcate then Alienate: Incomplete Multi-view Clustering via Coupled Distribution Learning with Linear Overhead
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72853-72894
From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72895-72924
Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72925-72943
Improving Compositional Generation with Diffusion Models Using Lift Scores
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72944-72971
Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72972-72994
LLM Data Selection and Utilization via Dynamic Bi-level Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72995-73008
Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73009-73050
ResearchTown: Simulator of Human Research Community
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73051-73096
UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73097-73114
Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73115-73145
Density Ratio Estimation with Conditional Probability Paths
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73146-73174
On the Adversarial Robustness of Multi-Kernel Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73175-73196
MindCustomer: Multi-Context Image Generation Blended with Brain Signal
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73197-73220
Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73221-73240
Ultra-Resolution Adaptation with Ease
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73241-73261
Optimal and Practical Batched Linear Bandit Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73262-73285
MTL-UE: Learning to Learn Nothing for Multi-Task Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73286-73303
Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73304-73325
Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73326-73349
R.I.P.: Better Models by Survival of the Fittest Prompts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73350-73374
Continuous Semi-Implicit Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73375-73400
TS-SNN: Temporal Shift Module for Spiking Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73401-73415
OrcaLoca: An LLM Agent Framework for Software Issue Localization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73416-73436
Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73437-73454
Residual TPP: A Unified Lightweight Approach for Event Stream Data Analysis
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73455-73477
Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73478-73510
Free Process Rewards without Process Labels
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73511-73525
Deep Streaming View Clustering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73526-73540
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73541-73552
MARS: Unleashing the Power of Variance Reduction for Training Large Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73553-73587
CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73588-73603
How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73604-73644
Protein Structure Tokenization: Benchmarking and New Recipe
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73645-73670
Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73671-73682
Stray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density Clusters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73683-73700
Reinforce LLM Reasoning through Multi-Agent Reflection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73701-73731
Efficient Long Context Fine-tuning with Chunk Flow
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73732-73742
MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73743-73766
Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73767-73809
Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73810-73827
ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73828-73850
Optimal Information Retention for Time-Series Explanations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73851-73876
Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73877-73896
Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73897-73917
Interpreting CLIP with Hierarchical Sparse Autoencoders
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73918-73956
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73957-73973
Adaptive Data Collection for Robust Learning Across Multiple Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73974-73994
Regress, Don’t Guess: A Regression-like Loss on Number Tokens for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73995-74017
Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74018-74036
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74037-74050
TabFlex: Scaling Tabular Learning to Millions with Linear Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74051-74079
Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74080-74097
Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74098-74132
Parametric Scaling Law of Tuning Bias in Conformal Prediction
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74133-74156
Graph Diffusion for Robust Multi-Agent Coordination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74157-74174
LensLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74175-74196
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74197-74239
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74240-74270
Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74271-74287
EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74288-74305
Peripheral Memory for LLMs: Integration of Sequential Memory Banks with Adaptive Querying
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74306-74317
Contextures: Representations from Contexts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74318-74347
Normalizing Flows are Capable Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74348-74369
SPRI: Aligning Large Language Models with Context-Situated Principles
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74370-74405
UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74406-74421
Expected Variational Inequalities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74422-74446
LEMoN: Label Error Detection using Multimodal Neighbors
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74447-74489
Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74490-74514
Nonparametric Teaching for Graph Property Learners
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74515-74539
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74540-74564
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74565-74582
CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74583-74601
Ad Hoc Teamwork via Offline Goal-Based Decision Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74602-74616
When Maximum Entropy Misleads Policy Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74617-74638
When do neural networks learn world models?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74639-74670
Structure-Guided Large Language Models for Text-to-SQL Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74671-74691
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74692-74713
Fast Video Generation with Sliding Tile Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74714-74731
Primitive Vision: Improving Diagram Understanding in MLLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74732-74755
Unconstrained Robust Online Convex Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74756-74786
Learning from others’ mistakes: Finetuning machine translation models with span-level error annotations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74787-74803
Scaling Probabilistic Circuits via Monarch Matrices
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74804-74818
Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74819-74839
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74840-74857
TabNAT: A Continuous-Discrete Joint Generative Framework for Tabular Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74858-74881
Hardware and Software Platform Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74882-74895
MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74896-74910
UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74911-74922
Differentially Private Analysis for Binary Response Models: Optimality, Estimation, and Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74923-74937
L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74938-74949
Training Diffusion-based Generative Models with Limited Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74950-74965
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74966-74996
Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:74997-75029
Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75030-75066
Testing Conditional Mean Independence Using Generative Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75067-75096
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75097-75119
High Dynamic Range Novel View Synthesis with Single Exposure
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75120-75131
Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75132-75177
TLLC: Transfer Learning-based Label Completion for Crowdsourcing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75178-75191
Minimalist Concept Erasure in Generative Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75192-75215
Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75216-75233
Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75234-75252
LLMScan: Causal Scan for LLM Misbehavior Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75253-75282
MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75283-75296
Joker: Joint Optimization Framework for Lightweight Kernel Machines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75297-75313
On Exact Bit-level Reversible Transformers Without Changing Architecture
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75314-75328
Online Differentially Private Conformal Prediction for Uncertainty Quantification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75329-75368
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75369-75391
Rhomboid Tiling for Geometric Graph Deep Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75392-75412
Multiobjective distribution matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75413-75426
Adaptive Self-improvement LLM Agentic System for ML Library Development
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75427-75452
From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75453-75467
Learning Curves of Stochastic Gradient Descent in Kernel Regression
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75468-75502
EasyInv: Toward Fast and Better DDIM Inversion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75503-75512
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75513-75574
PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75575-75590
Reward-Augmented Data Enhances Direct Preference Alignment of LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75591-75614
Causality Inspired Federated Learning for OOD Generalization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75615-75637
M2PDE: Compositional Generative Multiphysics and Multi-component PDE Simulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75638-75666
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75667-75694
Learning to Steer Learners in Games
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75695-75733
SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75734-75756
DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75757-75778
Ladder-Residual: Parallelism-Aware Architecture for Accelerating Large Model Inference with Communication Overlapping
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75779-75792
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75793-75833
Multi-agent Architecture Search via Agentic Supernet
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75834-75852
Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75853-75877
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75878-75900
Generalization Performance of Ensemble Clustering: From Theory to Algorithm
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75901-75927
Preference learning made easy: Everything should be understood through win rate
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75928-75950
One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75951-75970
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75971-75998
DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75999-76022
Policy Filtration for RLHF to Mitigate Noise in Reward Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76023-76046
Training Dynamics of In-Context Learning in Linear Attention
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76047-76087
Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76088-76110
CellFlux: Simulating Cellular Morphology Changes via Flow Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76111-76138
Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76139-76158
ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76159-76174
Neural Encoding and Decoding at Scale
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76175-76192
Diverging Preferences: When do Annotators Disagree and do Models Know?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76193-76212
Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76213-76224
Active Treatment Effect Estimation via Limited Samples
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76225-76245
Contextual Linear Bandits with Delay as Payoff
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76246-76272
Function-to-Style Guidance of LLMs for Code Translation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76273-76288
Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76289-76307
e-GAI: e-value-based Generalized $α$-Investing for Online False Discovery Rate Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76308-76331
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76332-76360
Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76361-76384
MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76385-76396
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76397-76413
Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76414-76435
Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76436-76450
Learning to Reuse Policies in State Evolvable Environments
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76451-76476
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76477-76496
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76497-76517
Synthesizing Software Engineering Data in a Test-Driven Manner
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76518-76540
Efficient Network Automatic Relevance Determination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76541-76562
KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76563-76582
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76583-76599
Curse of High Dimensionality Issue in Transformer for Long Context Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76600-76624
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76625-76654
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76655-76677
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76678-76692
Don’t Restart, Just Reuse: Reoptimizing MILPs with Dynamic Parameters
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76693-76715
Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76716-76753
STAIR: Improving Safety Alignment with Introspective Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76754-76777
Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76778-76794
Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76795-76810
PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76811-76830
Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76831-76879
Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76880-76908
Tight and Fast Bounds for Multi-Label Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76909-76938
Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76939-76965
End-to-End Learning Framework for Solving Non-Markovian Optimal Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76966-76997
ConText: Driving In-context Learning for Text Removal and Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76998-77016
Generalization Analysis for Controllable Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77017-77043
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77044-77068
Strategic A/B testing via Maximum Probability-driven Two-armed Bandit
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77069-77089
Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77090-77106
Gap-Dependent Bounds for Federated $Q$-Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77107-77151
Inverse Flow and Consistency Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77152-77176
Conformal Anomaly Detection in Event Sequences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77177-77193
The Four Color Theorem for Cell Instance Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77194-77215
Efficient Skill Discovery via Regret-Aware Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77216-77232
Robust Multimodal Large Language Models Against Modality Conflict
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77233-77253
ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77254-77271
Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77272-77309
ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77310-77320
Improving LLM Safety Alignment with Dual-Objective Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77321-77341
DeepLayout: Learning Neural Representations of Circuit Placement Layout
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77342-77352
Efficient Motion Prompt Learning for Robust Visual Tracking
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77353-77370
Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77371-77389
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77390-77404
Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77405-77440
Understanding Mode Connectivity via Parameter Space Symmetry
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77441-77460
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77461-77486
Contextual Bandits for Unbounded Context Distributions
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77487-77520
Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77521-77538
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77539-77557
TTFSFormer: A TTFS-based Lossless Conversion of Spiking Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77558-77571
Learning Progress Driven Multi-Agent Curriculum
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77572-77588
SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77589-77607
Unlocking Post-hoc Dataset Inference with Synthetic Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77608-77629
GraphGPT: Generative Pre-trained Graph Eulerian Transformer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77630-77656
Improving Memory Efficiency for Training KANs via Meta Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77657-77676
Rejecting Hallucinated State Targets during Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77677-77702
Hierarchical Equivariant Policy via Frame Transfer
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77703-77722
Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77723-77739
Epsilon-VAE: Denoising as Visual Decoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77740-77759
Taming Diffusion for Dataset Distillation with High Representativeness
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77760-77780
Can We Predict Performance of Large Models across Vision-Language Tasks?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77781-77806
Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77807-77821
Weak-to-Strong Jailbreaking on Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77822-77843
SkipGPT: Each Token is One of a Kind
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77844-77863
Logarithmic Regret for Online KL-Regularized Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77864-77884
Understanding Synthetic Context Extension via Retrieval Heads
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77885-77910
GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77911-77925
Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77926-77947
Rethink the Role of Deep Learning towards Large-scale Quantum Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77948-77975
Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:77976-78002
Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78003-78022
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78023-78040
Model Immunization from a Condition Number Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78041-78066
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78067-78094
Can DBNNs Robust to Environmental Noise for Resource-constrained Scenarios?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78095-78114
Towards Attributions of Input Variables in a Coalition
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78115-78138
Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78139-78155
Test-Time Graph Neural Dataset Search With Generative Projection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78156-78169
Deep Electromagnetic Structure Design Under Limited Evaluation Budgets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78170-78189
Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78190-78207
Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78208-78220
MCU: An Evaluation Framework for Open-Ended Game Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78221-78259
Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78260-78275
Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78276-78296
Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78297-78314
Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78315-78337
Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78338-78373
Nonparametric Identification of Latent Concepts
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78374-78404
ExLM: Rethinking the Impact of $\texttt[MASK]$ Tokens in Masked Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78405-78433
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78434-78453
NeuronTune: Towards Self-Guided Spurious Bias Mitigation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78454-78477
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78478-78497
DPO Meets PPO: Reinforced Token Optimization for RLHF
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78498-78521
Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78522-78536
Semi-Supervised Blind Quality Assessment with Confidence-quantifiable Pseudo-label Learning for Authentic Images
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78537-78554
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78555-78574
Reinforcement Learning Control of a Physical Robot Device for Assisted Human Walking without a Simulator
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78575-78601
Implicit Subgraph Neural Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78602-78615
TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78616-78632
Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78633-78650
Inductive Moment Matching
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78651-78686
ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78687-78713
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78714-78758
Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78759-78785
TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78786-78811
Contrastive Visual Data Augmentation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78812-78826
Designing Cyclic Peptides via Harmonic SDE with Atom-Bond Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78827-78858
FloE: On-the-Fly MoE Inference on Memory-constrained GPU
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78859-78882
BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer Sharing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78883-78902
An Error Analysis of Flow Matching for Deep Generative Modeling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78903-78932
GSM-$∞$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78933-78983
Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:78984-79003
Robust Multi-Agent Reinforcement Learning with Stochastic Adversary
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79004-79027
Efficient and Separate Authentication Image Steganography Network
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79028-79044
Learning Efficient Robotic Garment Manipulation with Standardization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79045-79060
Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79061-79088
Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79089-79114
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79115-79135
KAN-AD: Time Series Anomaly Detection with Kolmogorov–Arnold Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79136-79149
Accelerating Unbiased LLM Evaluation via Synthetic Feedback
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79150-79167
Energy-Based Flow Matching for Generating 3D Molecular Structure
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79168-79191
Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79192-79225
A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79226-79253
Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79254-79280
Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79281-79327
Weakly-Supervised Contrastive Learning for Imprecise Class Labels
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79328-79365
A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79366-79388
Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79389-79413
DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79414-79435
Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79436-79471
Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79472-79489
Proposer-Agent-Evaluator (PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79490-79528
CERTAIN: Context Uncertainty-aware One-Shot Adaptation for Context-based Offline Meta Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79529-79547
H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79548-79569
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79570-79594
Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79595-79643
Stay Hungry, Keep Learning: Sustainable Plasticity for Deep Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79644-79672
Independence Tests for Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79673-79698
In-Context Adaptation to Concept Drift for Learned Database Operations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79699-79726
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79727-79745
How to Synthesize Text Data without Model Collapse?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79746-79771
Doubly Robust Fusion of Many Treatments for Policy Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79772-79789
When Can Proxies Improve the Sample Complexity of Preference Learning?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79790-79814
SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79815-79835
CPCF: A Cross-Prompt Contrastive Framework for Referring Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79836-79849
CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79850-79867
Introducing 3D Representation for Dense Volume-to-Volume Translation via Score Fusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79868-79902
The Case for Learned Provenance-based System Behavior Baseline
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79903-79917
Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79918-79937
Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79938-79962
EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79963-79984
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79985-80012
On the Power of Context-Enhanced Learning in LLMs
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80013-80089
How Effective Can Dropout Be in Multiple Instance Learning ?
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80090-80106
Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80107-80133
Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80134-80154
Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80155-80186
SE(3)-Equivariant Diffusion Policy in Spherical Fourier Space
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80187-80206
MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80207-80222
Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80223-80258
Gradient Aligned Regression via Pairwise Losses
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80259-80281
Enhancing Statistical Validity and Power in Hybrid Controlled Trials: A Randomization Inference Approach with Conformal Selective Borrowing
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80282-80309
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80310-80329
Efficient LiDAR Reflectance Compression via Scanning Serialization
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80330-80346
An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80347-80372
Measuring Diversity in Synthetic Datasets
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80373-80397
Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80398-80426
Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80427-80447
SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80448-80462
AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80463-80479
CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80480-80498
TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80499-80515
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80516-80532
Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80533-80550
Stealix: Model Stealing via Prompt Evolution
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80551-80568
Agent-as-a-Judge: Evaluate Agents with Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80569-80611
Commute Graph Neural Networks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80612-80628
PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80629-80661
Decoupled SGDA for Games with Intermittent Strategy Communication
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80662-80707
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80708-80739
Novelty Detection in Reinforcement Learning with World Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80740-80758
EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80759-80775
Analytical Lyapunov Function Discovery: An RL-based Generative Approach
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80776-80804
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcalO(T)$ Complexity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80805-80821
HPS: Hard Preference Sampling for Human Preference Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80822-80845
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80846-80872
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80873-80899
Random Feature Representation Boosting
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80900-80932
Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80933-80960
MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80961-80990
Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:80991-81004
Position: LLM Social Simulations Are a Promising Research Method
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81005-81034
Position: Generative AI Regulation Can Learn from Social Media Regulation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81035-81049
Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81050-81066
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81067-81089
Position: Stop treating ‘AGI’ as the north-star goal of AI research
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81090-81117
Position: Strong Consumer Protection is an Inalienable Defense for AI Safety in the United States
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81118-81129
Position: Rethinking Explainable Machine Learning as Applied Statistics
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81130-81142
Position: Don’t Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81143-81184
Position: Certified Robustness Does Not (Yet) Imply Model Security
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81185-81198
Position: A Theory of Deep Learning Must Include Compositional Sparsity
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81199-81210
Position: The Categorization of Race in ML is a Flawed Premise
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81211-81232
Position: Constants are Critical in Regret Bounds for Reinforcement Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81233-81275
Position: Current Model Licensing Practices are Dragging Us into a Quagmire of Legal Noncompliance
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81276-81291
Position: We Need An Algorithmic Understanding of Generative AI
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81292-81314
Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81315-81374
Position: Enough of Scaling LLMs! Lets Focus on Downscaling
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81375-81392
Position: It Is Time We Test Neural Computation In Vitro
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81393-81409
Position: Future Research and Challenges Remain Towards AI for Software Engineering
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81410-81470
Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81471-81493
Position: General Intelligence Requires Reward-based Pretraining
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81494-81513
Position: We Need Responsible, Application-Driven (RAD) AI Research
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81514-81525
Position: AI Should Not Be An Imitation Game: Centaur Evaluations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81526-81541
Position: AI Safety should prioritize the Future of Work
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81542-81555
Position: We Can’t Understand AI Using our Existing Vocabulary
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81556-81572
Position: Not All Explanations for Deep Learning Phenomena Are Equally Valuable
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81573-81587
Position: AI Safety Must Embrace an Antifragile Perspective
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81588-81605
Position: The Most Expensive Part of an LLM *should* be its Training Data
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81606-81616
Position: Build Agent Advocates, Not Platform Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81617-81633
Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81634-81651
Position: You Can’t Manufacture a NeRF
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81652-81664
Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81665-81677
Position: Humanity Faces Existential Risk from Gradual Disempowerment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81678-81688
Position: Supervised Classifiers Answer the Wrong Questions for OOD Detection
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81689-81713
Position: Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81714-81727
Position: In-House Evaluation Is Not Enough. Towards Robust Third-Party Evaluation and Flaw Disclosure for General-Purpose AI
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81728-81758
Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81759-81773
Position: Machine Learning Models Have a Supply Chain Problem
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81774-81785
Position: Lifetime tuning is incompatible with continual reinforcement learning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81786-81796
Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81797-81809
Position: Probabilistic Modelling is Sufficient for Causal Inference
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81810-81840
Position: Rethinking LLM Bias Probing Using Lessons from the Social Sciences
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81841-81860
Position: The Future of Bayesian Prediction Is Prior-Fitted
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81861-81875
Position: The Right to AI
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81876-81896
Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81897-81929
Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81930-81961
Position: Iterative Online-Offline Joint Optimization is Needed to Manage Complex LLM Copyright Risks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81962-81976
Position: Explainable AI Cannot Advance Without Better User Studies
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81977-81994
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81995-82015
Position: All Current Generative Fidelity and Diversity Metrics are Flawed
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82016-82050
Position: Principles of Animal Cognition to Improve LLM Evaluations
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82051-82061
Position: AI’s growing due process problem
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82062-82071
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82072-82090
Position: Theory of Mind Benchmarks are Broken for Large Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82091-82130
Position: Graph Matching Systems Deserve Better Benchmarks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82131-82150
Position: When Incentives Backfire, Data Stops Being Human
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82151-82165
Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82166-82178
Position: Societal Impacts Research Requires Benchmarks for Creative Composition Tasks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82179-82199
Position: Contextual Integrity is Inadequately Applied to Language Models
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82200-82210
Position: AI Agents Need Authenticated Delegation
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82211-82231
Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82232-82251
Position: AI Scaling: From Up to Down and Out
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82252-82264
Position: Human Baselines in Model Evaluations Need Rigor and Transparency (With Recommendations & Reporting Checklist)
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82265-82325
Position: Deep Learning is Not So Mysterious or Different
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82326-82346
Position: Retrieval-augmented systems can be dangerous medical communicators
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82347-82359
Position: LLMs Need a Bayesian Meta-Reasoning Framework for More Robust and Generalizable Reasoning
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82360-82383
Position: Formal Mathematical Reasoning—A New Frontier in AI
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82384-82398
Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82399-82408
Position: Challenges and Future Directions of Data-Centric AI Alignment
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82409-82425
Position: Editing Large Language Models Poses Serious Safety Risks
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82426-82440
Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82441-82459
Position: Language model developers should report train-test overlap
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82460-82482
Position: AI Evaluation Should Learn from How We Test Humans
; Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:82483-82508
subscribe via RSS