![[International Conference on Machine Learning Logo]](/v235/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 235: International Conference on Machine Learning, 21-27 July 2024, Vienna, Austria
[edit]
Editors: Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, Felix Berkenkamp
Revisiting Character-level Adversarial Attacks for Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1-30
Adaptively Perturbed Mirror Descent for Learning in Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31-80
InferCept: Efficient Intercept Support for Augmented Large Language Model Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:81-95
Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:96-116
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:117-134
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:135-168
A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:169-202
FrameQuant: Flexible Low-Bit Quantization for Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:203-227
BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from Images
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:228-245
Discovering Bias in Latent Space: An Unsupervised Debiasing Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:246-261
Optimal Coresets for Low-Dimensional Geometric Median
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:262-270
REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:271-290
CHAI: Clustered Head Attention for Efficient LLM Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:291-312
Learning to Play Atari in a World of Tokens
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:313-328
Probabilistic Generating Circuits - Demystified
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:329-342
Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:343-361
The Non-linear $F$-Design and Applications to Interactive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:362-396
ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:397-415
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:416-451
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:452-470
Policy Evaluation for Variance in Average Reward Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:471-502
Distinguishing the Knowable from the Unknowable with Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:503-549
Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:550-576
OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:577-596
How to Escape Sharp Minima with Random Perturbations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:597-618
Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:619-640
Not all distributional shifts are equal: Fine-grained robust conformal inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:641-665
Triple Changes Estimator for Targeted Policies
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:666-695
Improving Computational Complexity in Statistical Models with Local Curvature Information
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:696-719
Learning Mixtures of Gaussian Processes through Random Projection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:720-739
Encodings for Prediction-based Neural Architecture Search
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:740-759
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:760-786
In-Context Language Learning: Architectures and Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:787-812
Nonlinear Filtering with Brenier Optimal Transport Maps
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:813-839
Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:840-878
Gaussian Processes on Cellular Complexes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:879-905
Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:906-920
Stochastic Interpolants with Data-Dependent Couplings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:921-937
Evaluating Model Bias Requires Characterizing its Mistakes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:938-954
Energy-Efficient Gaussian Processes Using Low-Precision Arithmetic
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:955-975
Evaluation of Test-Time Adaptation Under Computational Time Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:976-991
On the Weight Dynamics of Deep Normalized Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:992-1007
No Dimensional Sampling Coresets for Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1008-1049
Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1050-1066
Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1067-1077
Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1078-1114
The Privacy Power of Correlated Noise in Decentralized Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1115-1143
Predicting Dose-Response Curves with Deep Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1144-1154
Robust and Conjugate Gaussian Process Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1155-1185
Beyond the Norms: Detecting Prediction Errors in Regression Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1186-1221
Position: Stop Making Unscientific AGI Performance Claims
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1222-1242
Hyperbolic Optimizer as a Dynamical System
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1243-1260
Stationarity without mean reversion in improper Gaussian processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1261-1275
Robust Graph Matching when Nodes are Corrupt
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1276-1305
Fast Algorithms for Hypergraph PageRank with Applications to Semi-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1306-1330
Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1331-1358
Generalization Error of Graph Neural Networks in the Mean-field Regime
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1359-1391
Scalable Online Exploration via Coverability
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1392-1455
WAVES: Benchmarking the Robustness of Image Watermarks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1456-1492
Training-Free Long-Context Scaling of Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1493-1510
Navigating Scaling Laws: Compute Optimality in Adaptive Model Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1511-1530
Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1531-1556
Adaptive Observation Cost Control for Variational Quantum Eigensolvers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1557-1578
Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1579-1615
Online conformal prediction with decaying step sizes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1616-1630
A Rate-Distortion View of Uncertainty Quantification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1631-1654
Practical Performance Guarantees for Pipelined DNN Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1655-1671
Unsupervised Concept Discovery Mitigates Spurious Correlations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1672-1688
Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1689-1708
Causal Action Influence Aware Counterfactual Data Augmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1709-1729
Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1730-1762
Simple linear attention language models balance the recall-throughput tradeoff
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1763-1840
Inferring Change Points in High-Dimensional Linear Regression via Approximate Message Passing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1841-1864
An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1865-1901
Learning the Target Network in Function Space
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1902-1923
Translation Equivariant Transformer Neural Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1924-1944
Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1945-1970
Bifurcated Attention for Single-Context Large-Batch Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1971-1991
Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:1992-2008
How Free is Parameter-Free Stochastic Optimization?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2009-2034
Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2035-2068
Agnostic Sample Compression Schemes for Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2069-2085
Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2086-2107
Random features models: a way to study the success of naive imputation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2108-2134
Switching the Loss Reduces the Cost in Batch Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2135-2158
Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2159-2167
What is the Long-Run Distribution of Stochastic Gradient Descent? A Large Deviations Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2168-2229
HyperFields: Towards Zero-Shot Generation of NeRFs from Text
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2230-2247
Online Matrix Completion: A Collaborative Approach with Hott Items
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2248-2276
Differentiable Weightless Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2277-2295
The Pitfalls of Next-Token Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2296-2318
Simulation of Graph Algorithms with Looped Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2319-2363
QBMK: Quantum-based Matching Kernels for Un-attributed Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2364-2374
Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2375-2391
On the Complexity of Finite-Sum Smooth Optimization under the Polyak–Łojasiewicz Condition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2392-2417
Constrained Ensemble Exploration for Unsupervised Skill Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2418-2442
Image Hijacks: Adversarial Images can Control Generative Models at Runtime
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2443-2455
An Explicit Frame Construction for Normalizing 3D Point Clouds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2456-2473
Disentanglement Learning via Topology
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2474-2504
Adversarial Attacks on Combinatorial Multi-Armed Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2505-2526
Memory Consolidation Enables Long-Context Video Understanding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2527-2542
Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2543-2565
How Learning by Reconstruction Produces Uninformative Features For Perception
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2566-2585
Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2586-2606
A Field Guide for Pacing Budget and ROS Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2607-2638
On the Identifiability of Switching Dynamical Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2639-2672
Analyzing $D^α$ seeding for $k$-means
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2673-2699
Parsimonious Learning-Augmented Approximations for Dense Instances of $\mathcalNP$-hard Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2700-2714
Fair Resource Allocation in Multi-Task Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2715-2731
Linguistic Calibration of Long-Form Generations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2732-2778
Relational DNN Verification With Cross Executional Bound Refinement
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2779-2807
A Dynamic Algorithm for Weighted Submodular Cover Problem
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2808-2830
Dynamic Metric Embedding into lp Space
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2831-2845
VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2846-2856
Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2857-2902
Self-attention Networks Localize When QK-eigenspectrum Concentrates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2903-2922
Graph Out-of-Distribution Detection Goes Neighborhood Shaping
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2923-2943
Stochastic positional embeddings improve masked image modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2944-2958
Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2959-2989
Scale-Free Image Keypoints Using Differentiable Persistent Homology
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:2990-3002
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3003-3023
Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3024-3045
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3046-3072
Neural Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3073-3095
Generalization in Kernel Regression Under Realistic Assumptions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3096-3132
Local vs. Global Interpretability: A Computational Complexity Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3133-3167
Differentially Private Domain Adaptation with Theoretical Guarantees
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3168-3196
A Statistical Framework for Data-dependent Retrieval-Augmented Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3197-3223
On Mechanistic Knowledge Localization in Text-to-Image Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3224-3265
Monotone Individual Fairness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3266-3283
Graph Neural Networks Use Graphs When They Shouldn’t
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3284-3304
Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3305-3326
Standardized Interpretable Fairness Measures for Continuous Risk Scores
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3327-3346
Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3347-3381
Neural Networks Learn Statistics of Increasing Complexity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3382-3409
Accelerating Federated Learning with Quick Distributed Mean Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3410-3442
The Role of Learning Algorithms in Collective Action
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3443-3461
D-Flow: Differentiating through Flows for Controlled Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3462-3483
Transitional Uncertainty with Layered Intermediate Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3484-3505
Non-clairvoyant Scheduling with Partial Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3506-3538
Sequential Disentanglement by Extracting Static Information From A Single Sequence Element
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3539-3564
CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3565-3583
By Tying Embeddings You Are Assuming the Distributional Hypothesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3584-3610
Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3611-3636
Refining Minimax Regret for Unsupervised Environment Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3637-3657
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3658-3673
Prompt Sketching for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3674-3706
Counterfactual Metarules for Local and Global Recourse
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3707-3724
Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3725-3750
Position: Scaling Simulation is Neither Necessary Nor Sufficient for In-the-Wild Robot Manipulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3751-3762
Dynamic Facility Location in High Dimensional Euclidean Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3763-3775
Total Variation Distance Meets Probabilistic Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3776-3794
Hierarchical State Space Models for Continuous Sequence-to-Sequence Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3795-3816
Why do Variational Autoencoders Really Promote Disentanglement?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3817-3849
Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3850-3888
Multi-Patch Prediction: Adapting Language Models for Time Series Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3889-3912
Naive Bayes Classifiers over Missing Data: Decision and Poisoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3913-3934
How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3935-3951
Scalable Safe Policy Improvement for Factored Multi-Agent MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3952-3973
Improving fine-grained understanding in image-text pre-training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3974-3995
Position: Explain to Question not to Justify
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:3996-4006
ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4007-4026
Incorporating Information into Shapley Values: Reweighting via a Maximum Entropy Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4027-4045
Graph2Tac: Online Representation Learning of Formal Math Concepts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4046-4076
Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4077-4102
Comparing Graph Transformers via Positional Encodings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4103-4139
Stability Evaluation through Distributional Perturbation Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4140-4159
Dynamic Survival Analysis with Controlled Latent States
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4160-4204
Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4205-4229
Shifted Interpolation for Differential Privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4230-4266
How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4267-4299
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4300-4328
Position: Machine Learning-powered Assessments of the EU Digital Services Act Aid Quantify Policy Impacts on Online Harms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4329-4344
A Dynamical Model of Neural Scaling Laws
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4345-4382
A New Computationally Efficient Algorithm to solve Feature Selection for Functional Data Classification in High-dimensional Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4383-4402
Random matrix theory improved Fréchet mean of symmetric positive definite matrices
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4403-4415
Improving Neural Additive Models with Bayesian Principles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4416-4443
S$Ω$I: Score-based O-INFORMATION Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4444-4471
On dimensionality of feature vectors in MPNNs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4472-4481
Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4482-4516
Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4517-4541
Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu’s formula
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4542-4560
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4561-4584
Scalable AI Safety via Doubly-Efficient Debate
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4585-4602
Genie: Generative Interactive Environments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4603-4623
HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4624-4641
Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4642-4695
Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4696-4729
Differentially Private Bias-Term Fine-tuning of Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4730-4751
Bayesian Optimization of Function Networks with Partial Evaluations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4752-4784
Robustness of Nonlinear Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4785-4821
Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4822-4853
Explaining Graph Neural Networks via Structure-aware Interaction Index
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4854-4883
Assessing Large Language Models on Climate Information
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4884-4935
Semantically-correlated memories in a dense associative model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4936-4970
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:4971-5012
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5013-5034
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5035-5081
Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5082-5113
Learning Associative Memories with Gradient Descent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5114-5134
Bridging Environments and Language with Rendering Functions and Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5135-5188
Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping Compositions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5189-5208
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5209-5235
Enhancing Cross-Modal Fine-Tuning with Gradually Intermediate Modality Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5236-5257
Batch and match: black-box variational inference with a score-based divergence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5258-5297
Flextron: Many-in-One Flexible Large Language Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5298-5311
Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5312-5347
LoCoCo: Dropping In Convolutions for Long Context Compression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5348-5359
On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5360-5382
Sample-specific Masks for Visual Reprogramming-based Prompting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5383-5408
Human Alignment of Large Language Models through Online Preference Optimisation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5409-5435
Partially Stochastic Infinitely Deep Bayesian Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5436-5452
Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5453-5512
Mimicking Better by Matching the Approximate Action Distribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5513-5532
Graph Positional and Structural Encoder
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5533-5566
Successor Features for Efficient Multi-Subject Controlled Text Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5567-5583
Limited Preference Aided Imitation Learning from Imperfect Demonstrations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5584-5607
Predictive Dynamic Fusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5608-5628
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5629-5659
Can a Few Decide for Many? The Metric Distortion of Sortition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5660-5679
Stealing part of a production language model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5680-5705
AI Alignment with Changing and Influenceable Reward Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5706-5756
Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5757-5791
Online Learning under Budget and ROI Constraints via Weak Adaptivity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5792-5816
How Smooth Is Attention?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5817-5840
Hierarchical Integral Probability Metrics: A distance on random probability measures with low sample complexity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5841-5861
On the Implicit Bias of Adam
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5862-5906
Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5907-5933
Centralized Selection with Preferences in the Presence of Biases
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5934-5981
Using Left and Right Brains Together: Towards Vision and Language Planning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:5982-6001
Feasibility Consistent Representation Learning for Safe Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6002-6019
Simple Ingredients for Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6020-6047
Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6048-6065
Auditing Private Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6066-6092
Position: On the Possibilities of AI-Generated Text Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6093-6115
MaxMin-RLHF: Alignment with Diverse Human Preferences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6116-6135
Dense Reward for Free in Reinforcement Learning from Human Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6136-6154
Scribble-Supervised Semantic Segmentation with Prototype-based Feature Augmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6155-6169
Feature Importance Disparities for Data Bias Investigations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6170-6201
Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6202-6252
LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6253-6262
MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6263-6285
From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6286-6324
On the Role of Edge Dependency in Graph Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6325-6345
Performance Bounds for Active Binary Testing with Information Maximization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6346-6371
Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6372-6396
PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6397-6412
How Interpretable Are Interpretable Graph Neural Networks?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6413-6456
Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6457-6485
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6486-6502
InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6503-6518
MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6519-6538
Policy-conditioned Environment Models are More Generalizable
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6539-6561
MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6562-6595
Premise Order Matters in Reasoning with Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6596-6620
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6621-6642
Robust Classification via a Single Diffusion Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6643-6665
Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6666-6698
Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable Components
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6699-6727
Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6728-6756
CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6757-6775
On Interpolating Experts and Multi-Armed Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6776-6802
Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6803-6832
Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6833-6846
Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6847-6880
Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6881-6949
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6950-6972
Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6973-6991
Offline Transition Modeling via Contrastive Energy Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:6992-7014
Efficient Pareto Manifold Learning with Low-Rank Structure
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7015-7032
Toward Adaptive Reasoning in Large Language Models with Thought Rollback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7033-7056
Identifiability Matters: Revealing the Hidden Recoverable Condition in Unbiased Learning to Rank
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7057-7080
High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7081-7102
DiJiang: Efficient Large Language Models through Compact Kernelization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7103-7117
GeoMFormer: A General Architecture for Geometric Molecular Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7118-7142
TENG: Time-Evolving Natural Gradient for Solving PDEs With Deep Neural Nets Toward Machine Precision
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7143-7162
EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7163-7189
TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7190-7206
AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7207-7219
MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7220-7235
CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7236-7259
GRATH: Gradual Self-Truthifying for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7260-7279
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7280-7297
Performative Prediction with Bandit Feedback: Learning through Reparameterization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7298-7324
Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7325-7345
Recovering Labels from Local Updates in Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7346-7372
SelfIE: Self-Interpretation of Large Language Model Embeddings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7373-7388
Locally Differentially Private Decentralized Stochastic Bilevel Optimization with Guaranteed Convergence Accuracy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7389-7439
Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7440-7461
A General Framework for Learning from Weak Supervision
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7462-7485
Diffusion Model-Augmented Behavioral Cloning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7486-7510
AutoOS: Make Your OS More Powerful by Exploiting Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7511-7525
Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7526-7552
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7553-7567
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7568-7585
Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7586-7620
DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7621-7639
$\rm E(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7640-7666
FedMBridge: Bridgeable Multimodal Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7667-7686
Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7687-7699
One for All: A Universal Generator for Concept Unlearnability via Multi-Modal Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7700-7711
Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7712-7730
Diffusive Gibbs Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7731-7747
Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7748-7791
$\textttMoE-RBench$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7792-7808
LLaGA: Large Language and Graph Assistant
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7809-7823
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7824-7846
Compact Optimality Verification for Optimization Proxies
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7847-7863
Enhancing Implicit Shape Generators Using Topological Regularizations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7864-7879
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7880-7904
On the Trajectory Regularity of ODE-based Diffusion Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7905-7934
ODIN: Disentangled Reward Mitigates Hacking in RLHF
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7935-7952
Stacking Deep Set Networks and Pooling by Quantiles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7953-7971
What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7972-8001
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8002-8037
Layerwise Change of Knowledge in Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8038-8059
Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8060-8076
Causal Inference out of Control: Estimating Performativity without Treatment Randomization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8077-8103
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8104-8122
GaussianPro: 3D Gaussian Splatting with Progressive Propagation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8123-8140
Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8141-8162
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8163-8183
Can AI Assistants Know What They Don’t Know?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8184-8202
RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8203-8228
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8229-8247
Kernel Semi-Implicit Variational Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8248-8269
Creative Text-to-Audio Generation via Synthesizer Programming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8270-8285
Leveraging (Biased) Information: Multi-armed Bandits with Offline Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8286-8309
Language Models as Science Tutors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8310-8335
Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8336-8358
Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8359-8388
MS-TIP: Imputation Aware Pedestrian Trajectory Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8389-8402
Enhancing Trajectory Prediction through Self-Supervised Waypoint Distortion Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8403-8416
How Flawed Is ECE? An Analysis via Logit Smoothing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8417-8435
Safe Exploration in Dose Finding Clinical Trials with Heterogeneous Participants
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8436-8467
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8468-8486
Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8487-8509
Parameterized Physics-informed Neural Networks for Parameterized PDEs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8510-8533
Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8534-8555
Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8556-8577
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8578-8592
Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8593-8608
Tilt and Average : Geometric Adjustment of the Last Layer for Recalibration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8609-8628
Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8629-8650
Listwise Reward Estimation for Offline Preference-based Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8651-8671
BWS: Best Window Selection Based on Sample Scores for Data Pruning across Broad Ranges
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8672-8701
Embodied CoT Distillation From LLM To Off-the-shelf Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8702-8721
PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8722-8739
PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8740-8761
Online bipartite matching with imperfect advice
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8762-8781
A connection between Tempering and Entropic Mirror Descent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8782-8800
Learning Linear Block Error Correction Codes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8801-8814
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8815-8847
SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8848-8903
How Private are DP-SGD Implementations?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8904-8918
Sampling-based Multi-dimensional Recalibration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8919-8940
Prompt-tuning Latent Diffusion Models for Inverse Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8941-8967
MusicRL: Aligning Music Generation to Human Preferences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8968-8984
Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:8985-8999
Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9000-9032
$\mathttVITS$ : Variational Inference Thompson Sampling for contextual bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9033-9075
CogBench: a large language model walks into a psychology lab
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9076-9108
Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9109-9137
Improving Token-Based World Models with Parallel Observation Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9138-9160
Perturb-and-Project: Differentially Private Similarities and Marginals
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9161-9179
Multi-View Stochastic Block Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9180-9207
A Near-Linear Time Approximation Algorithm for Beyond-Worst-Case Graph Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9208-9229
Dynamic Correlation Clustering in Sublinear Update Time
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9230-9274
A2Q+: Improving Accumulator-Aware Weight Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9275-9291
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9292-9345
Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9346-9360
Statistical Inference Under Constrained Selection Bias
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9361-9379
Scaling Laws for the Value of Individual Data Points in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9380-9406
Time Series Diffusion in the Frequency Domain
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9407-9438
Conformal Prediction Sets Improve Human Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9439-9457
Agent Instructs Large Language Models to be General Zero-Shot Reasoners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9458-9549
Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9550-9575
Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9576-9602
Major-Minor Mean Field Multi-Agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9603-9632
Learning Latent Space Hierarchical EBM Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9633-9645
Harmonizing Generalization and Personalization in Federated Prompt Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9646-9661
Asymptotics of feature learning in two-layer networks after one gradient-step
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9662-9695
Ameliorate Spurious Correlations in Dataset Condensation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9696-9721
ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9722-9744
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9745-9761
Differentially Private Decentralized Learning with Random Walks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9762-9783
Getting the most out of your tokenizer for pre-training and domain adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9784-9805
Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9806-9833
Position: Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9834-9845
Multi-View Clustering by Inter-cluster Connectivity Guided Reward
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9846-9855
High-Order Contrastive Learning with Fine-grained Comparative Levels for Sparse Ordinal Tensor Completion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9856-9871
Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9872-9903
Averaging $n$-step Returns Reduces Variance in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9904-9930
Pruned Pivot: Correlation Clustering Algorithm for Dynamic, Parallel, and Local Computation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9931-9952
Physics and Lie symmetry informed Gaussian processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9953-9975
Exploring the Enigma of Neural Dynamics Through A Scattering-Transform Mixer Landscape for Riemannian Manifold
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9976-9990
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:9991-10016
Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10017-10040
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10041-10071
Boosting Offline Optimizers with Surrogate Sensitivity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10072-10090
Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10091-10108
Larimar: Large Language Models with Episodic Memory Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10109-10126
Understanding the Training Speedup from Sampling with Approximate Losses
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10127-10147
A decoder-only foundation model for time-series forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10148-10167
Disparate Impact on Group Accuracy of Linearization for Private Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10168-10184
New Bounds on the Cohesion of Complete-link and Other Linkage Methods for Agglomerative Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10185-10205
Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10206-10234
Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10235-10266
Provably Better Explanations with Optimized Aggregation of Feature Attributions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10267-10286
Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10287-10316
Asymptotically Optimal and Computationally Efficient Average Treatment Effect Estimation in A/B testing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10317-10367
Predicting Lagrangian Multipliers for Mixed Integer Linear Programs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10368-10384
Prediction-powered Generalization of Causal Inferences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10385-10408
An Unsupervised Approach for Periodic Source Detection in Time Series
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10409-10439
Multi-group Learning for Hierarchical Groups
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10440-10487
A3S: A General Active Clustering Method with Pairwise Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10488-10505
Variational Schrödinger Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10506-10529
Collaborative Learning with Different Labeling Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10530-10552
Exploring the Low-Pass Filtering Behavior in Image Super-Resolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10553-10573
Network Tight Community Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10574-10596
Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10597-10623
Multicalibration for Confidence Scoring in LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10624-10641
Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10642-10660
Stability and Multigroup Fairness in Ranking with Uncertain Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10661-10686
Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10687-10709
Bivariate Causal Discovery using Bayesian Model Selection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10710-10735
Trust Regions for Explanations via Black-Box Probabilistic Certification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10736-10764
Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10765-10791
Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10792-10810
Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10811-10840
Fast Co-Training under Weak Dependence via Stream-Based Active Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10841-10864
Convex and Bilevel Optimization for Neural-Symbolic Inference and Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10865-10896
Structure Your Data: Towards Semantic Graph Counterfactuals
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10897-10926
Efficient Algorithms for Sum-Of-Minimum Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10927-10959
AMPA: Adaptive Mixed Precision Allocation for Low-Bit Integer Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10960-10977
Understanding Forgetting in Continual Learning with Linear Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10978-11001
Recurrent Distance Filtering for Graph Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11002-11015
Robust Stable Spiking Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11016-11029
Fewer Truncations Improve Language Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11030-11048
Delving into Differentially Private Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11049-11071
Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11072-11090
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11091-11104
Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11105-11148
Consistent Adversarially Robust Linear Classification: Non-Parametric Setting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11149-11164
A Tale of Tails: Model Collapse as a Change of Scaling Laws
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11165-11197
Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11198-11226
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11227-11252
Impact of Decentralized Learning on Player Utilities in Stackelberg Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11253-11310
Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11311-11345
Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11346-11374
Position: Building Guardrails for Large Language Models Requires Systematic Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11375-11394
Accelerating PDE Data Generation via Differential Operator Action in Solution Space
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11395-11411
TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11412-11436
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11437-11452
Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11453-11473
Spike Distance Function as a Learning Objective for Spike Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11474-11500
Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11501-11543
Don’t Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11544-11572
Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11573-11591
Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11592-11612
On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11613-11641
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11642-11662
Principled Gradient-Based MCMC for Conditional Sampling of Text
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11663-11685
SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11686-11703
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11704-11720
Position: Compositional Generative Modeling: A Single Model is Not All You Need
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11721-11732
Improving Factuality and Reasoning in Language Models through Multiagent Debate
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11733-11763
Learning Iterative Reasoning through Energy Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11764-11776
When and How Does In-Distribution Label Help Out-of-Distribution Detection?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11777-11811
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11812-11829
Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11830-11887
Bottleneck-Minimal Indexing for Generative Document Retrieval
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11888-11904
MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11905-11917
MF-CLR: Multi-Frequency Contrastive Learning Representation for Time Series
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11918-11939
DE-COP: Detecting Copyrighted Content in Language Models Training Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11940-11956
Unveiling the Potential of AI for Nanomaterial Morphology Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11957-11978
Consistent Submodular Maximization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11979-11991
Observable Propagation: Uncovering Feature Vectors in Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11992-12033
Sharpness-Aware Data Generation for Zero-shot Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12034-12045
Making Old Things New: A Unified Algorithm for Differentially Private Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12046-12086
Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12087-12137
Outlier-robust Kalman Filtering through Generalised Bayes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12138-12171
Enabling Uncertainty Estimation in Iterative Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12172-12189
Barrier Algorithms for Constrained Non-Convex Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12190-12214
Efficient Exploration for LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12215-12227
Equivariant Frames and the Impossibility of Continuous Canonicalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12228-12267
Position: Insights from Survey Methodology can Improve Training Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12268-12283
Extreme Compression of Large Language Models via Additive Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12284-12303
Ai-sampler: Adversarial Learning of Markov kernels with involutive maps
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12304-12317
Efficient Error Certification for Physics-Informed Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12318-12347
Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12348-12370
Scalable Pre-training of Large Autoregressive Image Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12371-12384
Adaptive Online Experimental Design for Causal Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12385-12408
TSLANet: Rethinking Transformers for Time Series Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12409-12428
Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12429-12447
Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12448-12468
Approximate Nearest Neighbor Search with Window Filters
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12469-12490
DsDm: Model-Aware Dataset Selection with Datamodels
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12491-12526
Compositional Curvature Bounds for Deep Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12527-12546
Disentangled 3D Scene Generation with Layout Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12547-12559
PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12560-12587
High-Dimensional Geometric Streaming for Nearly Low Rank Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12588-12605
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12606-12633
Model Alignment as Prospect Theoretic Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12634-12651
Fast Timing-Conditioned Latent Audio Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12652-12665
Scaling Exponents Across Parameterizations and Optimizers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12666-12700
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12701-12722
Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12723-12753
DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12754-12783
Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12784-12805
On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12806-12831
On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong Convexity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12832-12857
Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12858-12881
Revisit the Essence of Distilling Knowledge through Calibration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12882-12894
DOGE: Domain Reweighting with Generalization Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12895-12915
Path-Guided Particle-based Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12916-12934
Bayesian Knowledge Distillation: A Bayesian Perspective of Distillation with Uncertainty Quantification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12935-12956
Exploring Correlations of Self-Supervised Tasks for Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12957-12972
INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12973-12992
BayOTIDE: Bayesian Online Multivariate Time Series Imputation with Functional Decomposition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:12993-13009
StackSight: Unveiling WebAssembly through Large Language Models and Neurosymbolic Chain-of-Thought Decompilation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13010-13028
Accelerating Heterogeneous Federated Learning with Closed-form Classifiers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13029-13048
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13049-13071
Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13072-13085
From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13086-13108
Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13109-13125
Bayesian Exploration Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13126-13152
Auto-Linear Phenomenon in Subsurface Imaging
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13153-13174
Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13175-13198
Fast White-Box Adversarial Streaming Without a Random Oracle
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13199-13224
DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13225-13240
Keypoint-based Progressive Chain-of-Thought Distillation for LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13241-13255
UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13256-13277
Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets Heisenberg
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13278-13325
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13326-13364
Memory Efficient Neural Processes via Constant Memory Attention Block
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13365-13386
Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13387-13422
AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13423-13444
GenCO: Generating Diverse Designs with Combinatorial Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13445-13459
Active Ranking and Matchmaking, with Perfect Matchings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13460-13480
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13481-13544
Trained Random Forests Completely Reveal your Dataset
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13545-13569
Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13570-13591
Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13592-13607
On Statistical Learning Theory for Distributional Inputs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13608-13632
Cooperative Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13633-13659
Critical feature learning in deep neural networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13660-13690
Neuroexplicit Diffusion Models for Inpainting of Optical Flow Fields
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13691-13705
Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13706-13733
Stochastic Q-learning for Large Discrete Action Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13734-13759
Federated Combinatorial Multi-Agent Multi-Armed Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13760-13782
Initial Guessing Bias: How Untrained Networks Favor Some Classes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13783-13839
Explaining Probabilistic Models with Distributional Values
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13840-13863
Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13864-13884
Weisfeiler-Leman at the margin: When more expressivity matters
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13885-13926
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13927-13942
Fair Off-Policy Learning from Observational Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13943-13972
Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:13973-14005
Trustworthy Actionable Perturbations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14006-14034
Interpretability Illusions in the Generalization of Simplified Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14035-14059
Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14060-14079
A Touch, Vision, and Language Dataset for Multimodal Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14080-14101
Hyperbolic Geometric Latent Diffusion Model for Graph Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14102-14124
Data Engineering for Scaling Language Models to 128K Context
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14125-14134
Language-guided Skill Learning with Temporal Variational Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14135-14156
PinNet: Pinpoint Instructive Information for Retrieval Augmented Code-to-Text Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14157-14174
Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14175-14206
Breaking through the learning plateaus of in-context learning in Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14207-14227
Towards Theoretical Understandings of Self-Consuming Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14228-14255
FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14256-14274
Uncertainty for Active Learning on Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14275-14307
KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14308-14342
Beyond the ROC Curve: Classification Trees Using Cost-Optimal Curves, with Application to Imbalanced Datasets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14343-14364
Positive Concave Deep Equilibrium Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14365-14381
Let Go of Your Labels with Unsupervised Transfer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14382-14407
Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14408-14432
Leverage Class-Specific Accuracy to Guide Data Generation for Improving Image Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14433-14452
Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14453-14470
Reflective Policy Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14471-14490
Confidence Aware Inverse Constrained Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14491-14512
Testing the Feasibility of Linear Programs with Bandit Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14513-14539
A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14540-14610
Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14611-14637
An Intrinsic Vector Heat Network
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14638-14650
Stochastic Weakly Convex Optimization beyond Lipschitz Continuity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14651-14680
A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14681-14701
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14702-14722
Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14723-14746
DMTG: One-Shot Differentiable Multi-Task Grouping
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14747-14762
Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14763-14789
Speech Self-Supervised Learning Using Diffusion Model Synthetic Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14790-14810
Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14811-14825
Non-convex Stochastic Composite Optimization with Polyak Momentum
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14826-14843
Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14844-14858
Decoupling Learning and Decision-Making: Breaking the $\mathcalO(\sqrtT)$ Barrier in Online Resource Allocation with First-Order Methods
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14859-14883
Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14884-14901
Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14902-14919
Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14920-14953
Prompt-based Visual Alignment for Zero-shot Policy Transfer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14954-14968
Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14969-14987
Projection-Free Online Convex Optimization with Time-Varying Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14988-15005
DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15006-15036
LLark: A Multimodal Instruction-Following Language Model for Music
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15037-15082
Memorization Through the Lens of Curvature of Loss Function Around Samples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15083-15101
Simplicity Bias via Global Convergence of Sharpness Minimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15102-15129
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15130-15152
Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15153-15179
Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15180-15208
Position: Categorical Deep Learning is an Algebraic Theory of All Architectures
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15209-15241
Masked Face Recognition with Generative-to-Discriminative Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15242-15254
Safe and Robust Subgame Exploitation in Imperfect Information Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15255-15270
No Double Descent in Principal Component Regression: A High-Dimensional Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15271-15293
Don’t trust your eyes: on the (un)reliability of feature visualizations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15294-15330
Learning with 3D rotations, a hitchhiker’s guide to SO(3)
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15331-15350
Graph-Triggered Rising Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15351-15380
Improving Adversarial Energy-Based Model via Diffusion Process
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15381-15401
Reinforcement Learning within Tree Search for Fast Macro Placement
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15402-15417
Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15418-15437
Emergent Equivariance in Deep Ensembles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15438-15465
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15466-15490
Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15491-15511
State-Constrained Zero-Sum Differential Games with One-Sided Information
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15512-15539
Understanding Finetuning for Factual Knowledge Extraction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15540-15558
A Closer Look at the Limitations of Instruction Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15559-15589
Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15590-15609
Optimal Eye Surgeon: Finding image priors through sparse generators at initialization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15610-15645
Self-Correcting Self-Consuming Loops for Generative Model Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15646-15677
Kernel-Based Evaluation of Conditional Biological Sequence Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15678-15705
Better & Faster Large Language Models via Multi-token Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15706-15734
All-in-one simulation-based inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15735-15766
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15767-15787
Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15788-15808
CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15809-15822
Does Label Smoothing Help Deep Partial Label Learning?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15823-15838
AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15839-15853
A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15854-15892
Evolution-Inspired Loss Functions for Protein Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15893-15906
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15907-15928
E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15929-15950
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:15951-16070
Out-of-Domain Generalization in Dynamical Systems Reconstruction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16071-16114
MOMENT: A Family of Open Time-series Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16115-16152
Weighted distance nearest neighbor condensing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16153-16166
Test-Time Degradation Adaptation for Open-Set Image Restoration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16167-16177
Learning Universal Predictors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16178-16205
Long Range Propagation on Continuous-Time Dynamic Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16206-16225
The Expressive Power of Path-Based Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16226-16249
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16250-16274
Fine-grained Classes and How to Find Them
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16275-16294
AI Control: Improving Safety Despite Intentional Subversion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16295-16336
Stochastic Localization via Iterative Posterior Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16337-16376
A Bayesian Approach to Online Planning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16377-16403
Scaling Down Deep Learning with MNIST-1D
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16404-16415
Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16416-16459
A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16460-16501
Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16502-16529
On the Calibration of Human Pose Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16530-16547
EDISON: Enhanced Dictionary-Induced Tensorized Incomplete Multi-View Clustering with Gaussian Error Rank Minimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16548-16567
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16568-16621
Data-free Distillation of Diffusion Models with Bootstrapping
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16622-16646
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16647-16672
Predictive Performance Comparison of Decision Policies Under Confounding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16673-16705
On the Diminishing Returns of Width for Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16706-16730
Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16731-16750
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16751-16772
Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16773-16801
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16802-16812
DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16813-16848
Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16849-16868
ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16869-16890
On the Embedding Collapse when Scaling up Recommendation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16891-16909
FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16910-16944
Compressing Large Language Models by Joint Sparsification and Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16945-16957
Automated Loss function Search for Class-imbalanced Node Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16958-16973
COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:16974-17002
Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17003-17019
Diffusion Posterior Sampling is Computationally Intractable
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17020-17059
xT: Nested Tokenization for Larger Context in Large Images
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17060-17071
GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17072-17099
Light and Optimal Schrödinger Bridge Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17100-17122
Robust Yet Efficient Conformal Prediction Sets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17123-17147
Optimally Improving Cooperative Learning in a Social Setting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17148-17188
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent Parametric Partial Differential Equations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17189-17223
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17224-17245
Pursuing Overall Welfare in Federated Learning through Sequential Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17246-17278
Incorporating probabilistic domain knowledge into deep multiple instance learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17279-17297
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17298-17312
A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17313-17332
Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17333-17353
UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17354-17373
Model Assessment and Selection under Temporal Distribution Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17374-17392
Riemannian coordinate descent algorithms on matrix manifolds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17393-17415
Prototypical Transformer As Unified Motion Learners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17416-17436
SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17437-17453
Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17454-17479
Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17480-17504
Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17505-17518
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17519-17537
Interpreting Equivariant Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17538-17553
Flora: Low-Rank Adapters Are Secretly Gradient Compressors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17554-17571
Data-efficient Large Vision Models through Sequential Autoregression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17572-17596
MGit: A Model Versioning and Management System
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17597-17615
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17616-17635
Convergence Guarantees for the DeepWalk Embedding on Block Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17636-17656
Estimating the Permanent by Nesting Importance Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17657-17666
Position: $C^*$-Algebraic Machine Learning $-$ Moving in a New Direction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17667-17679
Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17680-17696
Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17697-17718
GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17719-17733
Understanding MLP-Mixer as a wide and sparse MLP
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17734-17758
MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17759-17782
LoRA+: Efficient Low Rank Adaptation of Large Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17783-17806
From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17807-17841
Deep Neural Room Acoustics Primitive
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17842-17857
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17858-17876
Distributed Bilevel Optimization with Communication Compression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17877-17920
ReDiffuser: Reliable Decision-Making Using a Diffuser with Confidence Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17921-17933
Domain-wise Data Acquisition to Improve Performance under Distribution Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17934-17945
Quantum Algorithm for Online Exp-concave Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17946-17971
Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query Complexity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:17972-18009
The Effect of Weight Precision on the Neuron Count in Deep ReLU Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18010-18018
Ambiguity-Aware Abductive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18019-18042
Instruction Tuning for Secure Code Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18043-18062
Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18063-18080
SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18081-18093
Robust Multi-Task Learning with Excess Risks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18094-18114
DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18115-18132
DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18133-18154
Differentially Private Sum-Product Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18155-18173
Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18174-18204
Learning Useful Representations of Recurrent Neural Network Weight Matrices
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18205-18227
Position: Why We Must Rethink Empirical Research in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18228-18247
Randomized Confidence Bounds for Stochastic Partial Monitoring
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18248-18283
Listening to the noise: Blind Denoising with Gibbs Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18284-18304
Balanced Resonate-and-Fire Neurons
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18305-18323
Understanding Diffusion Models by Feynman’s Path Integral
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18324-18351
RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18352-18373
Learning Surrogates for Offline Black-Box Optimization via Gradient Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18374-18393
Estimating Unknown Population Sizes Using the Hypergeometric Distribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18394-18408
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18409-18438
Position: Is machine learning good or bad for the natural sciences?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18439-18453
Sparse Dimensionality Reduction Revisited
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18454-18469
Two Tales of Single-Phase Contrastive Hebbian Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18470-18488
Verifying message-passing neural networks via topology-based bounds tightening
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18489-18514
$\bfΦ_\textrmFlow$: Differentiable Simulations for PyTorch, TensorFlow and Jax
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18515-18546
Criterion Collapse and Loss Distribution Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18547-18567
Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18568-18610
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18611-18633
Enhancing Sufficient Dimension Reduction via Hellinger Correlation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18634-18647
Diversified Batch Selection for Training Acceleration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18648-18667
Model-based Reinforcement Learning for Confounded POMDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18668-18710
A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18711-18737
Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18738-18748
Weisfeiler Leman for Euclidean Equivariant Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18749-18784
Graph Neural PDE Solvers with Conservation and Similarity-Equivariance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18785-18814
Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18815-18832
Classification Under Strategic Self-Selection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18833-18858
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18859-18881
Recovering the Pre-Fine-Tuning Weights of Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18882-18904
Equilibrium of Data Markets with Externality
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18905-18925
A Persuasive Approach to Combating Misinformation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18926-18943
Multi-Sender Persuasion: A Computational Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18944-18971
Efficient Mixture Learning in Black-Box Variational Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18972-18991
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18992-19022
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19023-19042
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19043-19061
Loss Shaping Constraints for Long-Term Time Series Forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19062-19084
Careful with that Scalpel: Improving Gradient Surgery with an EMA
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19085-19100
Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19101-19122
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19123-19152
Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19153-19164
Q-value Regularized Transformer for Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19165-19181
HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19182-19197
An Information Theoretic Approach to Interaction-Grounded Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19198-19215
Accelerated Speculative Sampling Based on Tree Monte Carlo
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19216-19251
SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19252-19282
InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19283-19303
Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19304-19326
On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19327-19343
Improving Interpretation Faithfulness for Vision Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19344-19370
Multigroup Robustness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19371-19401
Provable Privacy with Non-Private Pre-Processing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19402-19437
Case-Based or Rule-Based: How Do Transformers Do the Math?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19438-19474
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19475-19490
Bayesian Design Principles for Offline-to-Online Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19491-19515
High-Performance Temporal Reversible Spiking Neural Networks with $\mathcalO(L)$ Training Memory and $\mathcalO(1)$ Inference Cost
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19516-19530
Accelerating Transformer Pre-training with 2:4 Sparsity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19531-19543
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19544-19572
ReconBoost: Boosting Can Achieve Modality Reconcilement
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19573-19597
Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19598-19621
NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19622-19634
Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19635-19659
In-context Convergence of Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19660-19722
Near-Linear Time Approximation Algorithms for k-means with Outliers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19723-19756
Contrastive Predict-and-Search for Mixed Integer Linear Programs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19757-19771
Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19772-19797
DiffDA: a Diffusion model for weather-scale Data Assimilation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19798-19815
Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19816-19870
In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19871-19885
InstructSpeech: Following Speech Editing Instructions via Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19886-19903
Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19904-19928
AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19929-19948
CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19949-19972
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:19973-20003
Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20004-20022
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20023-20042
An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20043-20062
MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20063-20072
On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20073-20095
Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20096-20110
Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20111-20133
Quasi-Monte Carlo Features for Kernel Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20134-20165
Position: TrustLLM: Trustworthiness in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20166-20270
MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20271-20309
How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20310-20330
Conformal Prediction for Deep Classifier via Label Ranking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20331-20347
Interaction-based Retrieval-augmented Diffusion Models for Protein-specific 3D Molecule Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20348-20364
Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20365-20381
Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20382-20412
An Embodied Generalist Agent in 3D World
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20413-20451
InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20452-20473
Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20474-20489
Faster Adaptive Decentralized Learning Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20490-20525
Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense Framework
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20526-20558
Faster Sampling via Stochastic Gradient Proximal Sampler
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20559-20596
Position: Open-Endedness is Essential for Artificial Superhuman Intelligence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20597-20616
Position: The Platonic Representation Hypothesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20617-20642
Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20643-20659
Make-A-Shape: a Ten-Million-scale 3D Shape Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20660-20681
Residual Quantization with Implicit Neural Codebooks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20682-20699
Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20700-20721
Deep Networks Always Grok and Here is Why
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20722-20745
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20746-20767
Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20768-20792
Vanilla Bayesian Optimization Performs Great in High Dimensions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20793-20817
On Positivity Condition for Causal Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20818-20841
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20842-20870
Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20871-20888
EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20889-20907
Smooth Min-Max Monotonic Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20908-20923
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20924-20954
From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20955-20982
Understanding the Learning Dynamics of Alignment with Human Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20983-21006
Zero-Shot Reinforcement Learning via Function Encoders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21007-21019
PASOA- PArticle baSed Bayesian Optimal Adaptive design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21020-21046
Nesting Particle Filters for Experimental Design in Dynamical Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21047-21068
PAGER: Accurate Failure Characterization in Deep Regression Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21069-21082
Online Linear Regression in Dynamic Environments via Discounting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21083-21120
Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21121-21147
Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21148-21169
Learning to Reach Goals via Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21170-21195
R2E: Turning any Github Repository into a Programming Agent Environment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21196-21224
On the sample complexity of conditional independence testing with Von Mises estimator with application to causal discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21225-21240
Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21241-21265
Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21266-21288
Visual Representation Learning with Stochastic Frame Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21289-21305
LoRA Training in the NTK Regime has No Spurious Local Minima
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21306-21328
Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21329-21372
Bringing Motion Taxonomies to Continuous Domains via GPLVM on Hyperbolic manifolds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21373-21409
PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21410-21429
Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21430-21485
Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21486-21501
Repeat After Me: Transformers are Better than State Space Models at Copying
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21502-21521
An Information-Theoretic Analysis of In-Context Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21522-21554
Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21555-21576
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21577-21605
Advancing Dynamic Sparse Training by Exploring Optimization Opportunities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21606-21619
ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21620-21647
Towards Efficient Exact Optimization of Language Model Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21648-21671
Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21672-21718
Discrete Latent Perspective Learning for Segmentation and Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21719-21730
Simulation-Based Inference with Quantile Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21731-21752
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21753-21767
Chain-of-Thought Predictive Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21768-21790
Pre-Training Protein Bi-level Representation Through Span Mask Strategy On 3D Protein Chains
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21791-21805
NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21806-21823
Conditional Common Entropy for Instrumental Variable Testing and Partial Identification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21824-21843
ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21844-21878
On the Origins of Linear Representations in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21879-21911
Federated Optimization with Doubly Regularized Drift Correction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21912-21945
HexGen: Generative Inference of Large Language Model over Heterogeneous Environment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21946-21961
Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21962-21987
Tabular Insights, Visual Impacts: Transferring Expertise from Tables to Images
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:21988-22009
Generalized Neural Collapse for a Large Number of Classes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22010-22041
SuDA: Support-based Domain Adaptation for Sim2Real Hinge Joint Tracking with Flexible Sensors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22042-22061
Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22062-22074
Homomorphism Counts for Graph Neural Networks: All About That Basis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22075-22098
LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22099-22114
On the Maximal Local Disparity of Fairness-Aware Classifiers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22115-22144
What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22145-22159
Emergent Representations of Program Semantics in Language Models Trained on Programs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22160-22184
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22185-22209
An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22210-22243
Language Models as Semantic Indexers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22244-22259
Position: What Can Large Language Models Tell Us about Time Series Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22260-22276
AlphaFold Meets Flow Matching for Generating Protein Ensembles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22277-22303
FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22304-22325
Model-Based Minimum Bayes Risk Decoding for Text Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22326-22347
Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22348-22370
Graph Generation with Diffusion Mixture
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22371-22405
Experts Don’t Cheat: Learning What You Don’t Know By Predicting Pairs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22406-22464
Learning to Infer Generative Template Programs for Visual Concepts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22465-22490
Learning Coverage Paths in Unknown Environments with Deep Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22491-22508
IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22509-22529
Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22530-22550
Position: Benchmarking is Limited in Reinforcement Learning Research
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22551-22569
Watermark Stealing in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22570-22593
Hypergraph-enhanced Dual Semi-supervised Graph Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22594-22604
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22605-22623
Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22624-22642
Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22643-22671
Unsupervised Episode Generation for Graph Meta-learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22672-22695
PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22696-22709
Leveraging VLM-Based Pipelines to Annotate 3D Objects
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22710-22747
PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22748-22770
Surprisingly Strong Performance Prediction with Neural Graph Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22771-22816
EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22817-22839
Beyond the Calibration Point: Mechanism Comparison in Differential Privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22840-22860
Replicable Learning of Large-Margin Halfspaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22861-22878
Tell, Don’t Show: Language Guidance Eases Transfer Across Domains in Images and Videos
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22879-22894
Position: LLMs Can’t Plan, But Can Help Planning in LLM-Modulo Frameworks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22895-22907
A Geometric Explanation of the Likelihood OOD Detection Paradox
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22908-22935
Learning Decision Trees and Forests with Algorithmic Recourse
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22936-22962
C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:22963-23000
Think Before You Act: Decision Transformers with Working Memory
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23001-23021
Certifiably Byzantine-Robust Federated Conformal Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23022-23057
Neural Tangent Kernels for Axis-Aligned Tree Ensembles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23058-23081
Position: On the Societal Impact of Open Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23082-23104
Adaptive Robust Learning using Latent Bernoulli Variables
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23105-23122
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23123-23144
On Stronger Computational Separations Between Multimodal and Unimodal Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23145-23158
On the Generalization of Equivariant Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23159-23186
Infinite-Horizon Distributionally Robust Regret-Optimal Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23187-23214
Challenges and Considerations in the Evaluation of Bayesian Causal Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23215-23237
Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23238-23255
Position: Embracing Negative Results in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23256-23265
Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23266-23290
Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choice
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23291-23323
First-Order Manifold Data Augmentation for Regression Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23324-23342
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23343-23366
Pluvial Flood Emulation with Hydraulics-informed Message Passing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23367-23390
Accelerating Convergence in Bayesian Few-Shot Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23391-23406
An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23407-23429
DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23430-23448
Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23449-23531
A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23532-23546
Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23547-23576
Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23577-23621
Tuning-Free Stochastic Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23622-23661
Debating with More Persuasive LLMs Leads to More Truthful Answers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23662-23733
Off-policy Evaluation Beyond Overlap: Sharp Partial Identification Under Smoothness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23734-23757
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23758-23780
Can Machines Learn the True Probabilities?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23781-23804
Gaussian Plane-Wave Neural Operator for Electron Density Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23805-23824
LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23825-23842
CARTE: Pretraining and Transfer for Tabular Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23843-23866
Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23867-23900
SqueezeLLM: Dense-and-Sparse Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23901-23923
Active Label Correction for Semantic Segmentation with Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23924-23940
ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23941-23971
Hybrid Neural Representations for Spherical Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23972-23985
Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:23986-24014
Learning to Explore for Stochastic Gradient MCMC
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24015-24039
Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24040-24058
Double-Step Alternating Extragradient with Increasing Timescale Separation for Finding Local Minimax Points: Provable Improvements
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24059-24093
Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24094-24109
Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24110-24136
Clustered Federated Learning via Gradient-based Partitioning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24137-24193
Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24194-24209
Demystifying SGD with Doubly Stochastic Gradients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24210-24247
Learning to Scale Logits for Temperature-Conditional GFlowNets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24248-24270
Attribute Based Interpretable Evaluation Metrics for Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24271-24293
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24294-24326
EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24327-24341
Scaling Beyond the GPU Memory Limit for Large Mixture-of-Experts Model Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24342-24353
Risk-Sensitive Policy Optimization via Predictive CVaR Policy Gradient
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24354-24369
An LLM Compiler for Parallel Function Calling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24370-24391
Data-Efficient Molecular Generation with Hierarchical Textual Inversion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24392-24414
Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24415-24436
Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24437-24457
Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24458-24485
USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24486-24508
Polynomial-based Self-Attention for Table Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24509-24526
Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24527-24561
Discovering Features with Synergistic Interactions in Multiple Views
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24562-24583
An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural Network
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24584-24657
One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24658-24673
Do Topological Characteristics Help in Knowledge Distillation?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24674-24693
A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24694-24712
The Merit of River Network Topology for Neural Flood Forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24713-24725
From Neurons to Neutrons: A Case Study in Interpretability
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24726-24748
Conformal Prediction with Learned Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24749-24769
Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24770-24807
Environment Design for Inverse Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24808-24828
What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24829-24858
Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24859-24871
DistiLLM: Towards Streamlined Distillation for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24872-24895
Provably Scalable Black-Box Variational Inference with Structured Variational Families
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24896-24931
Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24932-24963
Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:24964-25015
Estimating Barycenters of Distributions with Neural Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25016-25041
AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25042-25057
On Convergence of Incremental Gradient for Non-convex Smooth Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25058-25086
Logistic Variational Bayes Revisited
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25087-25104
VideoPoet: A Large Language Model for Zero-Shot Video Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25105-25124
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25125-25148
Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25149-25175
ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25176-25190
The Computational Complexity of Finding Second-Order Stationary Points
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25191-25225
Information-Directed Pessimism for Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25226-25264
Understanding and Diagnosing Deep Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25265-25275
Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25276-25301
convSeq: Fast and Scalable Method for Detecting Patterns in Spike Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25302-25312
Privacy Profiles for Private Selection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25313-25332
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25333-25369
Consistent Long-Term Forecasting of Ergodic Dynamical Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25370-25395
A General Online Algorithm for Optimizing Complex Performance Metrics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25396-25425
CLLMs: Consistency Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25426-25440
KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25441-25474
PcLast: Discovering Plannable Continuous Latent States
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25475-25493
Sobolev Space Regularised Pre Density Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25494-25533
Implicit meta-learning may lead language models to trust more reliable sources
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25534-25559
Geometry-Aware Instrumental Variable Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25560-25582
Understanding the Effects of Iterative Prompting on Truthfulness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25583-25602
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25603-25622
Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25623-25641
Mean Estimation in the Add-Remove Model of Differential Privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25642-25661
No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25662-25681
Efficient Value Iteration for s-rectangular Robust Markov Decision Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25682-25725
Minimum Norm Interpolation Meets The Local Theory of Banach Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25726-25754
Prospective Side Information for Latent MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25755-25783
On The Complexity of First-Order Methods in Stochastic Bilevel Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25784-25811
TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25812-25843
Dynamic Spectral Clustering with Provable Approximation Guarantee
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25844-25870
Collective Certified Robustness against Graph Injection Attacks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25871-25891
Position: Evolving AI Collectives Enhance Human Diversity and Enable Self-Regulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25892-25912
Invariant Risk Minimization Is A Total Variation Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25913-25935
Privately Learning Smooth Distributions on the Hypercube by Projections
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25936-25975
A Neural-Preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25976-25994
Sub-token ViT Embedding via Stochastic Resonance Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:25995-26006
Single-Model Attribution of Generative Models Through Final-Layer Inversion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26007-26042
Towards Understanding Inductive Bias in Transformers: A View From Infinity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26043-26069
Modeling Caption Diversity in Contrastive Vision-Language Pretraining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26070-26084
Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26085-26151
Generalized Sobolev Transport for Probability Measures on a Graph
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26152-26174
Robust Inverse Graphics via Probabilistic Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26175-26198
Knowledge Graphs Can be Learned with Just Intersection Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26199-26214
Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26215-26240
Run-Time Task Composition with Safety Semantics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26241-26258
Chasing Convex Functions with Long-term Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26259-26289
Generalization Analysis of Deep Non-linear Matrix Completion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26290-26360
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26361-26378
Stationary Latent Weight Inference for Unreliable Observations from Online Test-Time Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26379-26395
A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26396-26415
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26416-26438
Fundamental Benefit of Alternating Updates in Minimax Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26439-26514
DataFreeShield: Defending Adversarial Attacks without Training Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26515-26545
SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26546-26567
Recurrent Early Exits for Federated Learning with Heterogeneous Clients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26568-26588
PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26589-26620
Learning to Continually Learn with the Bayesian Principle
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26621-26639
Graph Neural Networks with a Distribution of Parametrized Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26640-26660
Pausing Policy Learning in Non-stationary Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26661-26685
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26686-26714
Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26715-26730
Drug Discovery with Dynamic Goal-aware Fragments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26731-26751
Supervised Matrix Factorization: Local Landscape Analysis and Applications
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26752-26788
Defining Neural Network Architecture through Polytope Structures of Datasets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26789-26836
Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26837-26855
3D Geometric Shape Assembly via Efficient Point Cloud Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26856-26873
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26874-26901
StrWAEs to Invariant Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26902-26928
Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26929-26947
Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26948-26975
Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26976-26990
Behavior Generation with Latent Actions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26991-27008
Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27009-27036
Rethinking the Flat Minima Searching in Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27037-27071
BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27072-27093
STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27094-27117
Sign Rank Limitations for Inner Product Graph Decoders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27118-27136
A Geometric Decomposition of Finite Games: Convergence vs. Recurrence under Exponential Weights
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27137-27173
Langevin Policy for Safe Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27174-27190
Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27191-27214
An Independence-promoting Loss for Music Generation with Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27215-27229
Improving Gradient-Guided Nested Sampling for Posterior Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27230-27253
Winner-takes-all learners are geometry-aware conditional density estimators
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27254-27287
Online Isolation Forest
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27288-27298
Cell2Sentence: Teaching Large Language Models the Language of Biology
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27299-27325
Eluder-based Regret for Stochastic Contextual MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27326-27350
Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27351-27375
Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27376-27398
DetKDS: Knowledge Distillation Search for Object Detectors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27399-27416
Denoising Autoregressive Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27417-27438
Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27439-27456
Improving Neural Logic Machines via Failure Reflection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27457-27473
Critical windows: non-asymptotic theory for feature emergence in diffusion models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27474-27498
Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27499-27514
GiLOT: Interpreting Generative Language Models via Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27515-27530
Completing Visual Objects via Bridging Generation and Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27531-27546
Evolving Subnetwork Training for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27547-27562
Data Poisoning Attacks against Conformal Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27563-27574
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27575-27588
Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27589-27614
Full-Atom Peptide Design based on Multi-modal Flow Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27615-27640
Positive and Unlabeled Learning with Controlled Probability Boundary Fence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27641-27652
FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27653-27674
Debiased Distribution Compression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27675-27731
Improving Context Understanding in Multimodal Large Language Models via Multimodal Composition Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27732-27751
RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27752-27770
Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27771-27790
Automated Statistical Model Discovery with Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27791-27807
Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27808-27821
Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27822-27845
Graph Structure Extrapolation for Out-of-Distribution Generalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27846-27874
Value-Evolutionary-Based Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27875-27889
Image Clustering with External Guidance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27890-27902
VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27903-27919
Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27920-27941
Accelerating Convergence of Score-Based Diffusion Models, Provably
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27942-27954
Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27955-27968
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27969-28017
Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28018-28039
Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28040-28059
Neural Collapse in Multi-label Learning with Pick-all-label Loss
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28060-28094
A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28095-28111
Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28112-28131
A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28132-28145
Learning Shadow Variable Representation for Treatment Effect Estimation under Collider Bias
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28146-28163
Configurable Mirror Descent: Towards a Unification of Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28164-28203
Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28204-28221
A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28222-28242
Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28243-28258
Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28259-28277
Preventing Model Collapse in Gaussian Process Latent Variable Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28278-28308
A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28309-28342
Concentration Inequalities for General Functions of Heavy-Tailed Random Variables
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28343-28367
Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28368-28386
Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28387-28402
Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28403-28420
PID: Prompt-Independent Data Protection Against Latent Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28421-28447
A Contextual Combinatorial Bandit Approach to Negotiation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28448-28465
Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28466-28479
Evaluating Quantized Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28480-28524
The WMDP Benchmark: Measuring and Reducing Malicious Use with Unlearning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28525-28550
Graph Neural Network Explanations are Fragile
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28551-28567
When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28568-28596
DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28597-28609
Privacy Preserving Adaptive Experiment Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28610-28629
Combining Experimental and Historical Data for Policy Evaluation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28630-28656
LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28657-28672
DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28673-28687
Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28688-28705
Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28706-28716
VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28717-28733
How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28734-28783
What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28784-28829
OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28830-28869
Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28870-28889
Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28890-28904
The Good, The Bad, and Why: Unveiling Emotions in Generative AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28905-28934
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28935-28948
Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider Bias
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28949-28964
Towards Realistic Model Selection for Semi-supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28965-28977
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28978-28988
Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28989-29021
Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29022-29062
Towards efficient deep spiking neural networks construction with spiking activity based pruning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29063-29073
FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29074-29095
Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29096-29111
Statistical Properties of Robust Satisficing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29112-29127
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29128-29163
PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29164-29180
IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29181-29200
KernelWarehouse: Rethinking the Design of Dynamic Convolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29201-29221
GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29222-29233
Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29234-29265
Seesaw: Compensating for Nonlinear Reduction with Linear Computations for Private Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29266-29277
Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29278-29323
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29324-29372
Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29373-29389
From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29390-29405
Feel-Good Thompson Sampling for Contextual Dueling Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29406-29426
EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29427-29447
Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29448-29460
DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29461-29488
Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29489-29510
Kepler codebook
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29511-29530
Receptive Fields As Experts in Convolutional Neural Architectures
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29531-29544
Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29545-29559
Graph External Attention Enhanced Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29560-29574
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29575-29620
Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29621-29643
Single-Trajectory Distributionally Robust Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29644-29666
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29667-29681
Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29682-29699
Scalable Multiple Kernel Clustering: Learning Clustering Structure from Expectation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29700-29719
On the Error-Propagation of Inexact Hotelling’s Deflation for Principal Component Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29720-29747
Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29748-29781
Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29782-29794
Graph Geometry-Preserving Autoencoders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29795-29815
Momentum Particle Maximum Likelihood
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29816-29871
An Effective Dynamic Gradient Calibration Method for Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29872-29889
Equivariant Diffusion for Crystal Structure Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29890-29913
Revisiting the Role of Language Priors in Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29914-29934
Non-confusing Generation of Customized Concepts in Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29935-29948
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29949-29973
Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29974-29991
Learning to Model the World With Language
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:29992-30017
Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30018-30041
Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30042-30079
Selecting Large Language Model to Fine-tune via Rectified Scaling Law
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30080-30107
Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30108-30134
Dual Operating Modes of In-Context Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30135-30188
HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30189-30210
SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30211-30226
Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30227-30251
On Hypothesis Transfer Learning of Functional Linear Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30252-30285
Smoothness Adaptive Hypothesis Transfer Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30286-30316
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30317-30345
GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30346-30361
Distributionally Robust Data Valuation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30362-30391
A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30392-30426
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30427-30439
Autonomous Sparse Mean-CVaR Portfolio Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30440-30456
Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30457-30478
Smooth Tchebycheff Scalarization for Multi-Objective Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30479-30509
PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30510-30528
Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30529-30545
Plug-in Performative Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30546-30565
Position: A Call to Action for a Human-Centered AutoML Paradigm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30566-30584
Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30585-30609
Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30610-30629
Scaling Tractable Probabilistic Circuits: A Systems Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30630-30646
Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30647-30668
Orthogonal Bootstrap: Efficient Simulation of Input Uncertainty
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30669-30701
Graph Distillation with Eigenbasis Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30702-30717
Adaptive Text Watermark for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30718-30737
Enhancing Adversarial Robustness in SNNs with Sparse Gradients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30738-30754
ReLU Network with Width $d+\mathcalO(1)$ Can Achieve Optimal Approximation Rate
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30755-30788
Graph Adversarial Diffusion Convolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30789-30806
Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30807-30841
Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30842-30872
Unifying Image Processing as Visual Prompting Question Answering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30873-30891
ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30892-30907
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30908-30928
Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30929-30945
PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30946-30964
Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30965-30997
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30998-31014
Decoding-time Realignment of Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31015-31031
DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31032-31047
Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31048-31061
Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31062-31079
PAPM: A Physics-aware Proxy Model for Process Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31080-31105
ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31106-31118
On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31119-31130
Online Speculative Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31131-31146
Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential Privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31147-31164
Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31165-31185
Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31186-31261
Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31262-31292
StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31293-31311
Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31312-31325
Stereo Risk: A Continuous Modeling Approach to Stereo Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31326-31343
Multi-Source Conformal Inference Under Distribution Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31344-31382
From Generalization Analysis to Optimization Designs for State Space Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31383-31405
Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31406-31424
Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31425-31450
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31451-31463
Differentiable Combinatorial Scheduling at Scale
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31464-31476
Characterizing ResNet’s Universal Approximation Capability
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31477-31515
Convergence of Online Learning Algorithm for a Mixture of Multiple Linear Regressions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31516-31540
Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31541-31565
Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution Strategy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31566-31596
Position: Foundation Agents as the Paradigm Shift for Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31597-31613
Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31614-31628
Revisiting Context Aggregation for Image Matting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31629-31644
Amortized Equation Discovery in Hybrid Dynamical Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31645-31668
KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31669-31690
Floating Anchor Diffusion Model for Multi-motif Scaffolding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31691-31708
Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric Factorization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31709-31727
Fast Decision Boundary based Out-of-Distribution Detector
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31728-31746
Class-Imbalanced Graph Learning without Class Rebalancing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31747-31772
Generative Marginalization Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31773-31807
Federated Representation Learning in the Under-Parameterized Regime
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31808-31843
How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31844-31865
Causal Discovery via Conditional Independence Testing with Proxy Variables
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31866-31889
Perfect Alignment May be Poisonous to Graph Contrastive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31890-31916
Entropy-Reinforced Planning with Large Language Models for Drug Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31917-31932
New Sample Complexity Bounds for Sample Average Approximation in Heavy-Tailed Stochastic Programming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31933-31948
Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31949-31963
Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31964-31993
Differentiable Model Scaling using Differentiable Topk
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31994-32014
Symmetric Matrix Completion with ReLU Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32015-32040
DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32041-32061
TimeX++: Learning Time-Series Explanations with Information Bottleneck
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32062-32082
LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32083-32099
DoRA: Weight-Decomposed Low-Rank Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32100-32121
High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32122-32138
Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32139-32172
Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32173-32183
Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32184-32200
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32201-32223
Correlation-Induced Label Prior for Semi-Supervised Multi-Label Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32224-32238
Causality Based Front-door Defense Against Backdoor Attack on Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32239-32252
Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32253-32267
Building Socially-Equitable Public Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32268-32286
In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32287-32307
Minimizing $f$-Divergences by Interpolating Velocity Fields
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32308-32331
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32332-32344
Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32345-32368
Timer: Generative Pre-trained Transformers Are Large Time Series Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32369-32399
SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32400-32420
DFD: Distilling the Feature Disparity Differently for Detectors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32421-32430
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32431-32454
Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32455-32470
On the Last-Iterate Convergence of Shuffling Gradient Methods
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32471-32508
FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32509-32551
Pairwise Alignment Improves Graph Domain Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32552-32575
Neural Operators with Localized Integral and Differential Kernels
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32576-32594
A Tensor Decomposition Perspective on Second-order RNNs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32595-32611
Coarse-To-Fine Tensor Trains for Compact Visual Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32612-32642
Restoring balance: principled under/oversampling of data for optimal classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32643-32670
Position: The Causal Revolution Needs Scientific Pragmatism
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32671-32679
Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32680-32690
Position: A Safe Harbor for AI Evaluation and Red Teaming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32691-32710
Position: Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32711-32725
Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32726-32758
Large Scale Dataset Distillation with Domain Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32759-32780
Attention Meets Post-hoc Interpretability: A Mathematical Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32781-32800
Non-Vacuous Generalization Bounds for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32801-32818
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32819-32848
Optimal Differentially Private Model Training with Public Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32849-32903
How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32904-32923
Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32924-32938
HumanTOMATO: Text-aligned Whole-body Motion Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32939-32977
Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32978-32989
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:32990-33006
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33007-33056
Open-Domain Text Evaluation via Contrastive Distribution Methods
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33057-33068
EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33069-33088
Rethinking Transformers in Solving POMDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33089-33112
CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33113-33146
NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33147-33159
FiT: Flexible Vision Transformer for Diffusion Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33160-33176
Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33177-33195
Disguised Copyright Infringement of Latent Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33196-33218
OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33219-33242
DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33243-33253
SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33254-33269
Scaling Laws for Fine-Grained Mixture of Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33270-33288
Projecting Molecules into Synthesizable Chemical Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33289-33304
PGODE: Towards High-quality System Dynamics Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33305-33328
Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33329-33382
OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33383-33410
Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33411-33431
Position: Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33432-33465
Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33466-33485
Potential Based Diffusion Motion Planning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33486-33510
Cluster-Aware Similarity Diffusion for Instance Retrieval
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33511-33532
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33533-33557
RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33558-33574
Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33575-33593
Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33594-33623
Efficient and Effective Time-Series Forecasting with Spiking Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33624-33637
Cross-Domain Policy Adaptation by Capturing Representation Mismatch
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33638-33663
Sampling is as easy as keeping the consistency: convergence guarantee for Consistency Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33664-33685
Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33686-33729
Rethinking Decision Transformer via Hierarchical Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33730-33745
Better Locally Private Sparse Estimation Given Multiple Samples Per User
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33746-33776
Learning Modality Knowledge Alignment for Cross-Modality Transfer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33777-33793
Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33794-33810
Outlier-aware Slicing for Post-Training Quantization in Vision Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33811-33825
X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33826-33838
Neighboring Perturbations of Knowledge Editing on Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33839-33854
Do Transformer World Models Give Better Policy Gradients?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33855-33879
Differentiable Distributionally Robust Optimization Layers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33880-33901
CKGConv: General Graph Convolution with Continuous Kernels
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33902-33924
Reward Shaping for Reinforcement Learning with An Assistant Reward Agent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33925-33939
LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33940-33962
Fast Peer Adaptation with Context-aware Exploration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33963-33982
HarmonyDream: Task Harmonization Inside World Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:33983-34007
High-dimensional Linear Bandits with Knapsacks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34008-34037
SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34038-34052
The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34053-34074
Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34075-34093
A Provable Decision Rule for Out-of-Distribution Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34094-34114
Prospector Heads: Generalized Feature Attribution for Large Models & Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34115-34144
Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34145-34160
Faithfulness Measurable Masked Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34161-34202
On the Hardness of Probabilistic Neurosymbolic Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34203-34218
Random Latent Exploration for Deep Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34219-34252
Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34253-34280
Split-and-Denoise: Protect large language model inference with local differential privacy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34281-34302
tinyBenchmarks: evaluating LLMs with fewer examples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34303-34326
SCoRe: Submodular Combinatorial Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34327-34349
Position: Data-driven Discovery with Large Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34350-34382
LASER: Linear Compression in Wireless Distributed Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34383-34416
Auto-Regressive Next-Token Predictors are Universal Learners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34417-34431
Self-Composing Policies for Scalable Continual Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34432-34460
Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34461-34498
Measures of diversity and space-filling designs for categorical data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34499-34528
COPAL: Continual Pruning in Large Language Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34529-34542
Minimum-Norm Interpolation Under Covariate Shift
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34543-34585
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34586-34602
Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34603-34629
Submodular framework for structured-sparse optimal transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34630-34653
Large Language Models are Geographically Biased
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34654-34669
Position: Graph Foundation Models Are Already Here
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34670-34692
Towards General Neural Surrogate Solvers with Specialized Neural Accelerators
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34693-34711
$H$-Consistency Guarantees for Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34712-34737
Regression with Multi-Expert Deferral
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34738-34759
No-Regret Reinforcement Learning in Smooth MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34760-34789
Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34790-34821
Quantum Theory and Application of Contextual Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34822-34845
Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34846-34865
A Unified View of FANOVA: A Comprehensive Bayesian Framework for Component Selection and Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34866-34894
Expand-and-Cluster: Parameter Recovery of Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34895-34919
Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34920-34948
Using AI Uncertainty Quantification to Improve Human Decision-Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34949-34960
On the Tractability of SHAP Explanations under Markovian Distributions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34961-34986
Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:34987-35012
On the Consistency of Kernel Methods with Dependent Observations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35013-35038
Online Variational Sequential Monte Carlo
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35039-35062
Amortized Variational Deep Kernel Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35063-35078
Hieros: Hierarchical Imagination on Structured State Space Sequence World Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35079-35103
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35104-35137
Sampling in Unit Time with Kernel Fisher-Rao Flow
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35138-35162
Joint Composite Latent Space Bayesian Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35163-35180
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35181-35224
Deep Fusion: Efficient Network Training via Pre-trained Initializations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35225-35239
Incremental Topological Ordering and Cycle Detection with Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35240-35254
Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35255-35266
Roping in Uncertainty: Robustness and Regularization in Markov Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35267-35295
Copyright Traps for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35296-35309
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35310-35323
O$n$ Learning Deep O($n$)-Equivariant Hyperspheres
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35324-35339
Position: Tensor Networks are a Valuable Asset for Green AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35340-35353
OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35354-35377
Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35378-35403
Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35404-35469
Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35470-35491
The Illusion of State in State-Space Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35492-35506
Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35507-35527
How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35528-35545
Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35546-35569
Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35570-35589
DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35590-35606
Rethinking Momentum Knowledge Distillation in Online Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35607-35622
Efficient World Models with Context-Aware Tokenization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35623-35638
Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35639-35646
CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35647-35663
FlowMM: Generating Materials with Riemannian Flow Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35664-35686
Can Implicit Bias Imply Adversarial Robustness?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35687-35718
Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35719-35743
RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35744-35778
Prodigy: An Expeditiously Adaptive Parameter-Free Learner
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35779-35804
From Inverse Optimization to Feasibility to ERM
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35805-35828
Provable Interactive Learning with Hindsight Instruction Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35829-35850
Position: Intent-aligned AI Systems Must Optimize for Agency Preservation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35851-35875
Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35876-35891
TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35892-35909
Error Feedback Can Accurately Compress Preconditioners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35910-35933
Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35934-35967
Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:35968-36011
OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36012-36028
Language Models with Conformal Factuality Guarantees
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36029-36047
Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36048-36071
A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36072-36087
Slot Abstractors: Toward Scalable Abstract Visual Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36088-36105
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36106-36159
Learning Optimal Deterministic Policies with Stochastic Policy Gradients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36160-36211
A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36212-36228
Lookbehind-SAM: k steps back, 1 step forward
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36229-36248
Causal Representation Learning Made Identifiable by Grouping of Observational Variables
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36249-36293
Position: Future Directions in the Theory of Graph Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36294-36307
Position: Levels of AGI for Operationalizing Progress on the Path to AGI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36308-36321
Gibbs Sampling of Continuous Potentials on a Quantum Computer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36322-36371
Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36372-36418
Privacy Attacks in Decentralized Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36419-36433
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36434-36454
On the Second-Order Convergence of Biased Policy Gradient Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36455-36485
Controlled Decoding from Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36486-36503
SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36504-36530
SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36531-36576
Active Preference Learning for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36577-36590
Is Kernel Prediction More Powerful than Gating in Convolutional Neural Networks?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36591-36604
Truly No-Regret Learning in Constrained MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36605-36653
Aligning Transformers with Weisfeiler-Leman
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36654-36704
Position: Optimization in SciML Should Employ the Function Space Geometry
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36705-36722
Individual Fairness in Graph Decomposition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36723-36742
Nash Learning from Human Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36743-36768
Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36769-36796
Turnstile $\ell_p$ leverage score sampling with applications
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36797-36828
Learning to Route Among Specialized Experts for Zero-Shot Generalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36829-36846
Autoformalizing Euclidean Geometry
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36847-36893
BAGEL: Bootstrapping Agents by Guiding Exploration with Language
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36894-36910
Factored-Reward Bandits with Intermediate Observations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36911-36952
Best Arm Identification for Stochastic Rising Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36953-36989
GATE: How to Keep Out Intrusive Neighbors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:36990-37015
Test-Time Regret Minimization in Meta Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37016-37040
Saliency strikes back: How filtering out high frequencies improves white-box explanations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37041-37075
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37076-37096
Diffusion Rejection Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37097-37121
LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37122-37140
Learning in Deep Factor Graphs with Gaussian Belief Propagation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37141-37163
Don’t be so Negative! Score-based Generative Modeling with Oracle-assisted Guidance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37164-37187
Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37188-37212
Slicing Mutual Information Generalization Bounds for Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37213-37236
PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37237-37259
Density Ratio Estimation with Doubly Strong Robustness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37260-37276
Solving Poisson Equations using Neural Walk-on-Spheres
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37277-37292
Time Weaver: A Conditional Time Series Generation Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37293-37320
PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37321-37341
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37342-37364
Box Facets and Cut Facets of Lifted Multicut Polytopes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37365-37375
Equivariant Deep Weight Space Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37376-37395
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37396-37412
Stable Differentiable Causal Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37413-37445
SelfVC: Voice Conversion With Iterative Refinement using Self Transformations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37446-37460
A Computational Framework for Solving Wasserstein Lagrangian Flows
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37461-37485
On The Fairness Impacts of Hardware Selection in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37486-37507
Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37508-37530
Score-Based Causal Discovery of Latent Variable Causal Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37531-37552
Measuring Stochastic Data Complexity with Boltzmann Influence Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37553-37569
Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37570-37616
A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37617-37648
PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37649-37666
Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37667-37682
Multiplicative Weights Update, Area Convexity and Random Coordinate Descent for Densest Subgraph Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37683-37706
On Least Square Estimation in Softmax Gating Mixture of Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37707-37735
Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37736-37760
Generative Conditional Distributions by Neural (Entropic) Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37761-37775
PIDformer: Transformer Meets Control Theory
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37776-37797
Differentially private exact recovery for stochastic block models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37798-37839
Novel Spectral Algorithms for the Partial Credit Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37840-37878
Sliced Wasserstein with Random-Path Projecting Directions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37879-37899
On The Statistical Complexity of Offline Decision-Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37900-37928
NExT: Teaching Large Language Models to Reason about Code Execution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37929-37956
On the Nonlinearity of Layer Normalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37957-37998
Risk-Sensitive Reward-Free Reinforcement Learning with CVaR
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:37999-38017
How Transformers Learn Causal Structure with Gradient Descent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38018-38070
Online Cascade Learning for Efficient Inference over Streams
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38071-38090
Compositional Text-to-Image Generation with Dense Blob Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38091-38116
Nearest Neighbour Score Estimators for Diffusion Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38117-38144
Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38145-38186
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38187-38206
REMEDI: Corrective Transformations for Improved Neural Entropy Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38207-38236
Indirectly Parameterized Concrete Autoencoders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38237-38252
Understanding the Impact of Introducing Constraints at Inference Time on Generalization Error
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38253-38263
Risk Aware Benchmarking of Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38264-38297
Test-Time Model Adaptation with Only Forward Passes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38298-38315
Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38316-38343
GFlowNet Training by Policy Gradients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38344-38380
Multi-Fidelity Residual Neural Processes for Scalable Surrogate Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38381-38394
RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38395-38408
Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38409-38425
DITTO: Diffusion Inference-Time T-Optimization for Music Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38426-38447
$f$-Divergence Based Classification: Beyond the Use of Cross-Entropy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38448-38473
Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38474-38494
In value-based deep reinforcement learning, a pruned network is a good network
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38495-38519
Mixtures of Experts Unlock Parameter Scaling for Deep RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38520-38540
On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38541-38561
Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38562-38598
The Perception-Robustness Tradeoff in Deterministic Image Restoration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38599-38638
Linear Explanations for Individual Neurons
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38639-38662
Adaptive Proximal Gradient Methods Are Universal Without Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38663-38682
SILVER: Single-loop variance reduction and application to federated learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38683-38739
Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38740-38761
Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38762-38778
Deep Stochastic Mechanics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38779-38814
Variational Linearized Laplace Approximation for Bayesian Deep Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38815-38836
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38837-38863
Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38864-38884
Towards Modular LLMs by Building and Reusing a Library of LoRAs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38885-38904
Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38905-38918
Differentiable Mapper for Topological Optimization of Data Representation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38919-38936
Structured Chemistry Reasoning with Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38937-38952
Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38953-38982
MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:38983-39008
Listenable Maps for Audio Classifiers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39009-39021
Implicit Representations via Operator Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39022-39041
Bayesian Program Learning by Decompiling Amortized Knowledge
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39042-39055
Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39056-39086
Counterfactual Image Editing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39087-39101
MALIBO: Meta-learning for Likelihood-free Bayesian Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39102-39134
$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39135-39153
Feedback Loops With Language Models Drive In-Context Reward Hacking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39154-39200
Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic Optimizations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39201-39275
RMIB: Representation Matching Information Bottleneck for Matching Text Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39276-39291
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39292-39307
Auto-Encoding Morph-Tokens for Multimodal LLM
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39308-39323
Model-Free Robust $φ$-Divergence Reinforcement Learning Using Both Offline and Online Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39324-39363
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39364-39399
BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39400-39415
Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39416-39447
Trainable Transformer in Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39448-39492
Position: A Call for Embodied AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39493-39508
Arrows of Time for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39509-39528
Position: Topological Deep Learning is the New Frontier for Relational Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39529-39555
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39556-39586
Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39587-39615
The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39616-39642
The Linear Representation Hypothesis and the Geometry of Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39643-39666
Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39667-39681
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39682-39701
Mean-field Chaos Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39702-39736
Foundation Policies with Hilbert Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39737-39761
SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39762-39780
Position: Automatic Environment Shaping is the Next Frontier in RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39781-39792
Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39793-39812
BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39813-39833
State-Free Inference of State-Space Models: The *Transfer Function* Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39834-39860
Variational Inference with Coverage Guarantees in Simulation-Based Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39861-39888
Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39889-39907
Optimal Ridge Regularization for Out-of-Distribution Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39908-39954
PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39955-39971
Estimating Canopy Height at Scale
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39972-39988
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:39989-40014
Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40015-40033
In-Context Unlearning: Language Models as Few-Shot Unlearners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40034-40050
Graph Automorphism Group Equivariant Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40051-40077
Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40078-40091
Exploiting Code Symmetries for Learning Program Semantics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40092-40113
Modeling Language Tokens as Functionals of Semantic Fields
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40114-40128
Data-free Neural Representation Compression with Riemannian Neural Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40129-40144
BetterV: Controlled Verilog Generation with Discriminative Guidance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40145-40153
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40154-40184
Knowledge Distillation with Auxiliary Variable
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40185-40199
UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40200-40214
eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40215-40257
Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40258-40270
UPOCR: Towards Unified Pixel-Level OCR Interface
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40271-40294
Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40295-40330
FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40331-40346
Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40347-40370
A Subquadratic Time Algorithm for Robust Sparse Mean Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40371-40396
CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40397-40413
Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40414-40438
The Relative Value of Prediction in Algorithmic Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40439-40460
Interpreting and Improving Diffusion Models from an Optimization Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40461-40483
Mechanistic Neural Networks for Scientific Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40484-40501
Bayesian Regret Minimization in Offline Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40502-40522
Prompting a Pretrained Transformer Can Be a Universal Approximator
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40523-40550
Discovering Environments with XRM
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40551-40569
Transport of Algebraic Structure to Latent Embeddings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40570-40591
Neural NeRF Compression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40592-40610
Cross-view Masked Diffusion Transformers for Person Image Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40611-40641
When is Transfer Learning Possible?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40642-40666
Controllable Prompt Tuning For Balancing Group Distributional Robustness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40667-40687
Particle Denoising Diffusion Sampler
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40688-40724
Federated Continual Learning via Prompt-based Dual Knowledge Transfer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40725-40739
Detecting Influence Structures in Multi-Agent Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40740-40761
Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40762-40794
Structure-based drug design by denoising voxel grids
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40795-40812
Extracting Training Data From Document-Based VQA Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40813-40826
Contrasting Multiple Representations with the Multi-Marginal Matching Gap
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40827-40842
diff History for Neural Language Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40843-40868
Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40869-40885
Adaptive Conformal Inference by Betting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40886-40907
Mechanistic Design and Scaling of Hybrid Architectures
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40908-40950
Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40951-40981
Robust Data-driven Prescriptiveness Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40982-40999
Stochastic Optimization with Arbitrary Recurrent Data Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41000-41038
Learning Multiple Secrets in Mastermind
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41039-41051
MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41052-41063
The Entropy Enigma: Success and Failure of Entropy Minimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41064-41085
Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41086-41118
Autoencoding Conditional Neural Processes for Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41119-41143
Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41144-41162
Learning a Diffusion Model Policy from Rewards via Q-Score Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41163-41182
Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41183-41203
Unsupervised Domain Adaptation for Anatomical Structure Detection in Ultrasound Images
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41204-41220
Amortizing Pragmatic Program Synthesis with Rankings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41221-41234
Learning to Remove Cuts in Integer Linear Programming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41235-41255
On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41256-41279
Hierarchical Novelty Detection via Fine-Grained Evidence Allocation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41280-41302
Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41303-41339
Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41340-41356
ByMI: Byzantine Machine Identification with False Discovery Rate Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41357-41382
Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41383-41415
Ensemble Pruning for Out-of-distribution Generalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41416-41429
Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41430-41455
ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41456-41472
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41473-41497
Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41498-41516
Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41517-41535
Feasible Reachable Policy Iteration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41536-41556
Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41557-41581
Learning High-Order Relationships of Brain Regions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41582-41603
To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41604-41643
Transferring Knowledge From Large Foundation Models to Small Downstream Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41644-41657
Complexity Matters: Feature Learning in the Presence of Spurious Correlations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41658-41697
Compute Better Spent: Replacing Dense Layers with Structured Matrices
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41698-41716
Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41717-41748
MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41749-41768
Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41769-41786
Learning Constraints from Offline Demonstrations via Superior Distribution Correction Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41787-41803
Augmenting Decision with Hypothesis in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41804-41820
Multiply-Robust Causal Change Attribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41821-41840
Decomposable Submodular Maximization in Federated Setting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41841-41866
A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41867-41885
Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41886-41926
Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41927-41958
Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41959-41981
In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41982-42008
Understanding Inter-Concept Relationships in Concept-Based Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42009-42025
STEER: Assessing the Economic Rationality of Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42026-42047
WARM: On the Benefits of Weight Averaged Reward Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42048-42073
Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42074-42103
Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42104-42126
Position: The Reasonable Person Standard for AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42127-42137
Generalization to New Sequential Decision Making Tasks with In-Context Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42138-42158
Challenges in Training PINNs: A Loss Landscape Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42159-42191
Unveiling Privacy, Memorization, and Input Curvature Links
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42192-42212
Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42213-42244
Fair Federated Learning via the Proportional Veto Core
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42245-42257
Provably Robust DPO: Aligning Language Models with Noisy Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42258-42274
Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42275-42331
Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42332-42364
Position: Understanding LLMs Requires More Than Statistical Generalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42365-42390
Optimal Batched Linear Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42391-42416
TabLog: Test-Time Adaptation for Tabular Data Using Logic Rules
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42417-42427
Hybrid Inverse Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42428-42448
Rejuvenating image-GPT as Strong Visual Representation Learners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42449-42461
CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42462-42483
Plug-and-Play image restoration with Stochastic deNOising REgularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42484-42520
Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42521-42542
Position: Technical Research and Talent is Needed for Effective AI Governance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42543-42557
SparQ Attention: Bandwidth-Efficient LLM Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42558-42583
Early Time Classification with Accumulated Accuracy Gap Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42584-42600
Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42601-42619
Universal Gradient Methods for Stochastic Convex Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42620-42646
Position: Key Claims in LLM Research Have a Long Tail of Footnotes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42647-42665
LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42666-42690
Position: Mission Critical – Satellite Data is a Distinct Modality in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42691-42706
Position: Application-Driven Innovation in Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42707-42718
One-Shot Strategic Classification Under Unknown Costs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42719-42741
Modelling Microbial Communities with Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42742-42765
Neural operators meet conjugate gradients: The FCG-NO method for efficient PDE solving
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42766-42782
Position: Amazing Things Come From Having Many Good Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42783-42795
Generalizing Orthogonalization for Models with Non-Linearities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42796-42817
Rolling Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42818-42835
Explorations of Self-Repair in Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42836-42855
Gambling-Based Confidence Sequences for Bounded Random Vectors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42856-42869
Operator SVD with Neural Networks via Nested Low-Rank Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42870-42905
Tandem Transformers for Inference Efficient LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42906-42917
Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42918-42946
Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42947-42975
Fast Adversarial Attacks on Language Models In One GPU Minute
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42976-42998
Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:42999-43023
I/O Complexity of Attention, or How Optimal is FlashAttention?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43024-43042
An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43043-43059
Second-Order Uncertainty Quantification: A Distance-Based Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43060-43076
Learning from Integral Losses in Physics Informed Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43077-43111
Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43112-43141
Predictive Coding beyond Correlations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43142-43179
Proactive Detection of Voice Cloning with Localized Watermarking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43180-43196
Stay on Topic with Classifier-Free Guidance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43197-43234
How do Transformers Perform In-Context Autoregressive Learning ?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43235-43254
Differentially Private Representation Learning via Image Captioning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43255-43275
Transformers, parallel computation, and logarithmic depth
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43276-43327
Promoting External and Internal Equities Under Ex-Ante/Ex-Post Metrics in Online Resource Allocation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43328-43345
A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43346-43367
Sparse and Structured Hopfield Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43368-43388
Meta Evidential Transformer for Few-Shot Open-Set Recognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43389-43406
EvIL: Evolution Strategies for Generalisable Imitation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43407-43421
A sampling theory perspective on activations for implicit neural representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43422-43444
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43445-43460
Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43461-43476
A fast algorithm to simulate nonlinear resistive networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43477-43503
A Fixed-Point Approach for Causal Generative Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43504-43541
MoMo: Momentum Models for Adaptive Learning Rates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43542-43570
Parallel Affine Transformation Tuning of Markov Chain Monte Carlo
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43571-43607
Incentivized Learning in Principal-Agent Bandit Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43608-43631
Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43632-43648
DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43649-43684
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43685-43704
Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43705-43722
Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43723-43741
Regularized Q-learning through Robust Averaging
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43742-43764
Implicit Representations for Constrained Image Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43765-43790
Online Learning with Bounded Recall
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43791-43803
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43804-43827
Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43828-43861
Asymptotics of Learning with Deep Structured (Random) Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43862-43894
Simultaneous identification of models and parameters of scientific simulators
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43895-43927
In-Context Learning Agents Are Asymmetric Belief Updaters
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43928-43946
Towards Scalable and Versatile Weight Space Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43947-43966
Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43967-43985
Differentiability and Optimization of Multiparameter Persistent Homology
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:43986-44011
Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-Multinomials
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44012-44037
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44038-44059
Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44060-44092
Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44093-44135
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44136-44189
Retrieval-Augmented Score Distillation for Text-to-3D Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44190-44211
Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44212-44223
Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44224-44243
Decomposing and Editing Predictions by Modeling Model Computation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44244-44292
A Multimodal Automated Interpretability Agent
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44293-44321
Evaluation of Trajectory Distribution Predictions with Energy Score
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44322-44341
The Balanced-Pairwise-Affinities Feature Transform
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44342-44357
DNCs Require More Planning Steps
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44358-44377
Improved Generalization of Weight Space Networks via Augmentations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44378-44393
On Online Experimentation without Device Identifiers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44394-44412
Improved Dimensionality Dependence for Zeroth-Order Optimisation over Cross-Polytopes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44413-44428
On Multi-Armed Bandit with Impatient Arms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44429-44473
Language Generation with Strictly Proper Scoring Rules
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44474-44488
Learning Decision Policies with Instrumental Variables through Double Machine Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44489-44514
How Far Can Fairness Constraints Help Recover From Biased Data?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44515-44544
Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44545-44564
Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44565-44602
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44603-44627
Reducing sequential change detection to sequential estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44628-44642
Exploring the Complexity of Deep Neural Networks through Functional Equivalence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44643-44664
Variational Learning is Effective for Large Deep Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44665-44686
Thermometer: Towards Universal Calibration for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44687-44711
Position: Do pretrained Transformers Learn In-Context by Gradient Descent?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44712-44740
Adaptive Stabilization Based on Machine Learning for Column Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44741-44758
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44759-44773
Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44774-44799
ReLUs Are Sufficient for Learning Implicit Neural Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44800-44814
Rate-Optimal Policy Optimization for Linear Markov Decision Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44815-44837
Double Momentum Method for Lower-Level Constrained Bilevel Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44838-44864
OT-CLIP: Understanding and Generalizing CLIP via Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44865-44886
LCA-on-the-Line: Benchmarking Out of Distribution Generalization with Class Taxonomies
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44887-44908
Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44909-44959
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44960-44990
Why Larger Language Models Do In-context Learning Differently?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44991-45013
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45014-45039
Neural-Kernel Conditional Mean Embeddings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45040-45059
Causal Discovery with Fewer Conditional Independence Tests
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45060-45078
Statistical Test for Attention Maps in Vision Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45079-45096
Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45097-45113
Allocation Requires Prediction Only if Inequality Is Low
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45114-45153
Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45154-45182
Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45183-45227
WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in Cancer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45228-45243
TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45244-45257
Towards a Better Theoretical Understanding of Independent Subnetwork Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45258-45285
Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45286-45314
Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45315-45328
IOI: Invisible One-Iteration Adversarial Attack on No-Reference Image- and Video-Quality Metrics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45329-45352
InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45353-45405
Embarrassingly Parallel GFlowNets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45406-45431
On the Unexpected Effectiveness of Reinforcement Learning for Sequential Recommendation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45432-45450
Learning from Memory: Non-Parametric Memory Augmented Self-Supervised Learning of Visual Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45451-45467
Deletion-Anticipative Data Selection with a Limited Budget
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45468-45507
Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45508-45524
Latent variable model for high-dimensional point process with structured missingness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45525-45543
Domain Generalisation via Imprecise Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45544-45570
Finite Time Logarithmic Regret Bounds for Self-Tuning Regulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45571-45636
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45637-45662
Representation Surgery: Theory and Practice of Affine Steering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45663-45680
PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45681-45695
Byzantine Resilient and Fast Federated Few-Shot Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45696-45706
Parallelized Spatiotemporal Slot Binding for Videos
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45707-45733
What’s the score? Automated Denoising Score Matching for Nonlinear Diffusions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45734-45758
SAPG: Split and Aggregate Policy Gradients
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45759-45772
In-Context Reinforcement Learning for Variable Action Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45773-45793
Subhomogeneous Deep Equilibrium Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45794-45812
Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45813-45834
Inexact Newton-type Methods for Optimisation with Nonnegativity Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45835-45882
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45883-45905
Probabilistic Modeling of Interpersonal Coordination Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45906-45921
On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45922-45954
SPADE: Sparsity-Guided Debugging for Deep Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45955-45987
Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:45988-46018
Hybrid Reinforcement Learning from Offline Observation Alone
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46019-46049
Multimodal Prototyping for cancer survival prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46050-46073
SurfPro: Functional Protein Design Based on Continuous Surface
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46074-46088
OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46089-46120
Sparse is Enough in Fine-tuning Pre-trained Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46121-46135
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46136-46155
Unveiling the Dynamics of Information Interplay in Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46156-46167
Position: Leverage Foundational Models for Black-Box Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46168-46180
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46181-46237
Latent Logic Tree Extraction for Event Sequence Explanation from LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46238-46258
Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46259-46279
Position: A Roadmap to Pluralistic Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46280-46302
Position: Opportunities Exist for Machine Learning in Magnetic Fusion Energy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46303-46322
Offline Actor-Critic Reinforcement Learning Scales to Large Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46323-46350
CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46351-46374
Contextual Feature Selection with Conditional Stochastic Gates
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46375-46392
The Fundamental Limits of Least-Privilege Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46393-46411
Diffusion Models Encode the Intrinsic Dimension of Data Manifolds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46412-46440
Grokking Group Multiplication with Cosets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46441-46467
Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46468-46494
Dirichlet Flow Matching with Applications to DNA Sequence Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46495-46513
Partial Optimality in the Linear Ordering Problem
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46514-46529
Towards Compositionality in Concept Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46530-46555
Learning to Intervene on Concept Bottlenecks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46556-46571
QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46572-46590
Private Truly-Everlasting Robust-Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46591-46604
ReGAL: Refactoring Programs to Discover Generalizable Abstractions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46605-46624
RLVF: Learning from Verbal Feedback without Overgeneralization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46625-46656
Causal Inference from Competing Treatments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46657-46691
Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46692-46721
Designing Decision Support Systems using Counterfactual Prediction Sets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46722-46744
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46745-46771
Learning from Streaming Data when Users Choose
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46772-46803
From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46804-46822
Compositional Image Decomposition with Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46823-46842
Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46843-46867
Revealing Vision-Language Integration in the Brain with Multimodal Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46868-46890
Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46891-46925
Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46926-46941
ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46942-46956
Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46957-46987
Representing Molecules as Random Walks Over Interpretable Grammars
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46988-47016
Constrained Reinforcement Learning Under Model Mismatch
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47017-47032
DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47033-47055
Online Algorithms with Uncertainty-Quantified Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47056-47077
LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47078-47104
Online Adaptive Anomaly Thresholding with Confidence Sequences
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47105-47132
Learning Graph Representation via Graph Entropy Maximization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47133-47158
FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47159-47173
Regression Learning with Limited Observations of Multivariate Outcomes and Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47174-47197
video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47198-47217
Learning High-Frequency Functions Made Easy with Sinusoidal Positional Encoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47218-47233
Learning Latent Dynamic Robust Representations for World Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47234-47260
Self-cognitive Denoising in the Presence of Multiple Noisy Label Sources
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47261-47279
BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47280-47304
On a Combinatorial Problem Arising in Machine Teaching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47305-47313
Interpretable Deep Clustering for Tabular Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47314-47330
Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional Distance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47331-47344
A Minimaximalist Approach to Reinforcement Learning from Human Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47345-47377
Fast Sampling-Based Sketches for Tensors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47378-47395
Sample Complexity Bounds for Estimating Probability Divergences under Invariances
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47396-47417
A Universal Class of Sharpness-Aware Minimization Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47418-47440
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47441-47474
Mean-field Analysis on Two-layer Neural Networks from a Kernel Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47475-47509
Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47510-47534
Codebook Features: Sparse and Discrete Interpretability for Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47535-47563
Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47564-47578
Community-Invariant Graph Contrastive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47579-47606
Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47607-47626
Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47627-47648
Information Flow in Self-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47649-47666
OTMatch: Improving Semi-Supervised Learning with Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47667-47680
Post-hoc Part-Prototype Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47681-47693
Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47694-47724
Generalized Preference Optimization: A Unified Approach to Offline Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47725-47742
Rethinking Optimization and Architecture for Tiny Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47743-47756
Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47757-47777
Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47778-47799
Accelerating Parallel Sampling of Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47800-47818
Membership Inference Attacks on Diffusion Models via Quantile Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47819-47829
StrokeNUWA—Tokenizing Strokes for Vector Graphic Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47830-47845
SSL4Q: Semi-Supervised Learning of Quantum Data with Application to Quantum State Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47846-47864
Finite Smoothing Algorithm for High-Dimensional Support Vector Machines and Quantile Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47865-47884
MathScale: Scaling Instruction Tuning for Mathematical Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47885-47900
QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47901-47911
MLI Formula: A Nearly Scale-Invariant Solution with Noise Perturbation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47912-47928
Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47929-47947
Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47948-47964
Quantum Positional Encodings for Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47965-47996
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:47997-48018
SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48019-48037
Bayesian Adaptation of Network Depth and Width for Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48038-48061
Position: What makes an image realistic?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48062-48076
A New Branch-and-Bound Pruning Framework for $\ell_0$-Regularized Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48077-48096
Beyond Individual Input for Deep Anomaly Detection on Tabular Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48097-48123
Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48124-48138
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48139-48153
MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48154-48185
Liouville Flow Importance Sampler
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48186-48210
Ranking-based Client Imitation Selection for Efficient Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48211-48225
Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48226-48279
Copula-Nested Spectral Kernel Network
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48280-48294
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48295-48320
FRAPPÉ: A Group Fairness Framework for Post-Processing Everything
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48321-48343
Faster Maximum Inner Product Search in High Dimensions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48344-48361
Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48362-48368
How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48369-48389
Position: Do Not Explain Vision Models Without Context
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48390-48403
An Analysis of Linear Time Series Forecasting Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48404-48427
Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48428-48452
Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48453-48467
Causal Effect Identification in LiNGAM Models with Latent Confounders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48468-48493
Stereographic Spherical Sliced Wasserstein Distances
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48494-48564
Inferring the Long-Term Causal Effects of Long-Term Treatments from Short-Term Experiments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48565-48577
Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48578-48607
Editing Partially Observable Networks via Graph Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48608-48629
QuIP$#$: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48630-48656
Predictive Linear Online Tracking for Unknown Targets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48657-48694
Overcoming the Optimizer’s Curse: Obtaining Realistic Prescriptions from Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48695-48712
Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48713-48727
Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48728-48767
Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48768-48790
An Empirical Study Into What Matters for Calibrating Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48791-48808
Coactive Learning for Large Language Models using Implicit User Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48809-48822
An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48823-48836
ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48837-48854
Matroid Semi-Bandits in Sublinear Time
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48855-48877
Improving Antibody Humanness Prediction using Patent Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48878-48891
Feedback Efficient Online Fine-Tuning of Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48892-48918
Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48919-48937
Reward-Free Kernel-Based Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48938-48956
Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48957-48975
Position: Why Tabular Foundation Models Should Be a Research Priority
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48976-48993
Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48994-49007
Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49008-49028
Proactive DP: A Multiple Target Optimization Framework for DP-SGD
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49029-49077
On the Independence Assumption in Neurosymbolic Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49078-49097
When Representations Align: Universality in Representation Learning Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49098-49121
Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49122-49136
Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49137-49170
Discovering Mixtures of Structural Causal Models from Time Series Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49171-49202
Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49203-49225
Optimization without Retraction on the Random Generalized Stiefel Manifold
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49226-49248
A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49249-49309
Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49310-49344
Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49345-49367
Code as Reward: Empowering Reinforcement Learning with VLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49368-49387
Topological Neural Networks go Persistent, Equivariant, and Continuous
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49388-49407
CuTS: Customizable Tabular Synthetic Data Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49408-49433
On a Neural Implementation of Brenier’s Polar Factorization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49434-49454
To the Max: Reinventing Reward in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49455-49470
Imitation Learning in Discounted Linear MDPs without exploration assumptions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49471-49505
Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49506-49522
Position: Will we run out of data? Limits of LLM scaling based on human-generated data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49523-49544
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49545-49557
CF-OPT: Counterfactual Explanations for Structured Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49558-49579
Parameter Estimation in DAGs from Incomplete Data via Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49580-49604
Optimal Transport for Structure Learning Under Missing Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49605-49626
ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49627-49654
A Language Model’s Guide Through Latent Space
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49655-49687
Convergence of Some Convex Message Passing Algorithms to a Fixed Point
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49688-49697
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49698-49716
Deconstructing the Goldilocks Zone of Neural Network Initialization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49717-49732
ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49733-49787
Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49788-49807
Trustless Audits without Revealing Data or Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49808-49821
Log Neural Controlled Differential Equations: The Lie Brackets Make A Difference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49822-49844
Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49845-49866
SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49867-49889
AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49890-49920
VinT-6D: A Large-Scale Object-in-hand Dataset from Vision, Touch and Proprioception
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49921-49940
Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49941-49956
Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49957-49972
S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49973-49990
Non-stationary Online Convex Optimization with Arbitrary Delays
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:49991-50011
Towards Unified Multi-granularity Text Detection with Interactive Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50012-50025
Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50026-50042
One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50043-50064
On Universally Optimal Algorithms for A/B Testing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50065-50091
Adversarially Robust Hypothesis Transfer Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50092-50117
Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50118-50142
Non-parametric Online Change Point Detection on Riemannian Manifolds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50143-50162
A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50163-50207
Executable Code Actions Elicit Better LLM Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50208-50232
Revisiting the Power of Prompt for Visual Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50233-50247
TVE: Learning Meta-attribution for Transferable Vision Explainer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50248-50267
Localizing Task Information for Improved Model Merging and Compression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50268-50287
Adaptively Learning to Select-Rank in Online Platforms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50288-50312
Imitation Learning from Purified Demonstrations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50313-50331
Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50332-50352
An Efficient Maximal Ancestral Graph Listing Algorithm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50353-50378
Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50379-50399
Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50400-50418
Optimal Kernel Quantile Learning with Random Features
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50419-50452
MEMORYLLM: Towards Self-Updatable Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50453-50466
Identification and Estimation for Nonignorable Missing Data: A Data Fusion Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50467-50488
Understanding Heterophily for Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50489-50529
Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50530-50560
EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50561-50579
Mollification Effects of Policy Gradient Methods
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50580-50598
Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50599-50621
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50622-50649
Optimal Kernel Choice for Score Function-based Causal Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50650-50668
Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50669-50682
Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50683-50710
Total Variation Floodgate for Variable Importance Inference in Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50711-50725
In-context Learning on Function Classes Unveiled for Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50726-50745
MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50746-50765
StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50766-50793
Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50794-50806
Highway Value Iteration Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50807-50821
Improving Generalization in Offline Reinforcement Learning via Adversarial Data Splitting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50822-50839
Visual Transformer with Differentiable Channel Selection: An Information Bottleneck Inspired Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50840-50858
An Iterative Min-Min Optimization Method for Sparse Bayesian Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50859-50873
Graph As Point Set
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50874-50901
Open Ad Hoc Teamwork with Cooperative Game Theory
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50902-50930
Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50931-50943
Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50944-50959
Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50960-50991
On Discrete Prompt Optimization for Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50992-51011
A Global Geometric Analysis of Maximal Coding Rate Reduction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51012-51040
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51041-51062
A Dual-module Framework for Counterfactual Estimation over Time
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51063-51085
MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51086-51104
EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51105-51123
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51124-51160
Transforming and Combining Rewards for Aligning Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51161-51176
TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51177-51191
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51192-51213
Pi-DUAL: Using privileged information to distinguish clean from noisy labels
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51214-51236
Sample Average Approximation for Conditional Stochastic Optimization with Dependent Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51237-51254
InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51255-51272
A Fine-grained Analysis of Fitted Q-evaluation: Beyond Parametric Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51273-51302
Probabilistic Constrained Reinforcement Learning with Formal Interpretability
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51303-51327
Efficient Online Set-valued Classification with Bandit Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51328-51347
LLM-Empowered State Representation for Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51348-51375
Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51376-51395
How to Trace Latent Generative Model Generated Images without Artificial Watermark?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51396-51414
Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51415-51441
Generalization Analysis of Stochastic Weight Averaging with General Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51442-51464
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51465-51483
RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51484-51501
Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51502-51522
Integrated Hardware Architecture and Device Placement Search
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51523-51545
AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51546-51568
Benchmarking Deletion Metrics with the Principled Explanations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51569-51595
CW Complex Hypothesis for Image Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51596-51613
Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51614-51649
A New Theoretical Perspective on Data Heterogeneity in Federated Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51650-51700
FADAS: Towards Federated Adaptive Asynchronous Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51701-51733
Open-Vocabulary Calibration for Fine-tuned CLIP
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51734-51754
Probabilistic Subgoal Representations for Hierarchical Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51755-51770
Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51771-51824
A Hierarchical Adaptive Multi-Task Reinforcement Learning Framework for Multiplier Circuit Design
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51825-51853
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51854-51912
Defense against Model Extraction Attack by Bayesian Active Watermarking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51913-51935
RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51936-51983
Quality-Diversity with Limited Resources
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51984-52001
Probability Distribution of Hypervolume Improvement in Bi-objective Bayesian Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52002-52018
Vision Transformers as Probabilistic Expansion from Learngene
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52019-52032
Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52033-52063
Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52064-52082
Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52083-52098
Learning with Adaptive Resource Allocation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52099-52116
Taylor Videos for Action Recognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52117-52133
An Empirical Study of Realized GNN Expressiveness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52134-52155
Calibration Bottleneck: Over-compressed Representations are Less Calibratable
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52156-52170
Benign Overfitting in Adversarial Training of Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52171-52232
FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52233-52246
Exploring Intrinsic Dimension for Vision-Language Model Pruning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52247-52259
Knowledge-aware Reinforced Language Models for Protein Directed Evolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52260-52273
Boximator: Generating Rich and Controllable Motions for Video Synthesis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52274-52289
Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52290-52308
Diffusion Language Models Are Versatile Protein Learners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52309-52333
Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52334-52360
Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52361-52371
Mapping the Multiverse of Latent Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52372-52402
Reinforcement Learning and Regret Bounds for Admission Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52403-52427
Learning to Compile Programs to Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52428-52471
Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52472-52483
Exploiting Human-AI Dependence for Learning to Defer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52484-52499
Learning Pseudo-Contractive Denoisers for Inverse Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52500-52524
Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52525-52558
MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52559-52572
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52573-52587
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52588-52610
Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52611-52631
Magicoder: Empowering Code Generation with OSS-Instruct
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52632-52657
Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52658-52679
Position: AI/ML Influencers Have a Place in the Academic Process
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52680-52694
SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52695-52719
Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52720-52743
Cross-domain Open-world Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52744-52761
Diffusion-based Missing-view Generation With the Application on Incomplete Multi-view Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52762-52778
Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52779-52800
From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52801-52818
Provable Contrastive Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52819-52838
Distributional Bellman Operators over Mean Embeddings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52839-52868
On the Asymptotic Distribution of the Minimum Empirical Risk
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52869-52902
Stability-Informed Initialization of Neural Ordinary Differential Equations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52903-52914
QuRating: Selecting High-Quality Data for Training Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52915-52971
Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52972-52993
A Distributional Analogue to the Successor Representation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:52994-53016
Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53017-53038
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53039-53078
Fundamental Limitations of Alignment in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53079-53112
Expressivity and Generalization: Fragment-Biases for Molecular GNNs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53113-53139
Unified Training of Universal Time Series Forecasting Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53140-53164
Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53165-53201
Coresets for Multiple $\ell_p$ Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53202-53233
Reweighted Solutions for Weighted Low Rank Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53234-53250
Optimizing Watermarks for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53251-53269
Repoformer: Selective Retrieval for Repository-Level Code Completion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53270-53290
Theoretical insights for diffusion guidance: A case study for Gaussian mixture models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53291-53327
Adaptive Accompaniment with ReaLchords
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53328-53345
Ditto: Quantization-aware Secure Inference of Transformers upon MPC
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53346-53365
NExT-GPT: Any-to-Any Multimodal LLM
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53366-53397
Understanding Stochastic Natural Gradient Variational Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53398-53421
FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53422-53442
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53443-53470
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53471-53514
Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53515-53541
PointMC: Multi-instance Point Cloud Registration based on Maximal Cliques
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53542-53552
Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53553-53570
Borda Regret Minimization for Generalized Linear Dueling Bandits
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53571-53596
DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53597-53618
Surface-VQMAE: Vector-quantized Masked Auto-encoders on Molecular Surfaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53619-53634
Learning Causal Relations from Subsampled Time Series with Two Time-Slices
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53635-53655
AND: Audio Network Dissection for Interpreting Deep Acoustic Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53656-53680
Transolver: A Fast Transformer Solver for PDEs on General Geometries
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53681-53705
Confidence-aware Contrastive Learning for Selective Classification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53706-53729
Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53730-53756
VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53757-53775
Learning Divergence Fields for Shift-Robust Graph Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53776-53792
Profile Reconstruction from Private Sketches
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53793-53816
Policy Learning for Balancing Short-Term and Long-Term Rewards
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53817-53846
Learning to Predict Mutational Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53847-53859
A Theory of Fault-Tolerant Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53860-53869
Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53870-53891
Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53892-53908
Detecting Any instruction-to-answer interaction relationship:Universal Instruction-to-Answer Navigator for Med-VQA
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53909-53927
Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53928-53943
Mitigating Label Noise on Graphs via Topological Sample Selection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53944-53972
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53973-53998
HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53999-54014
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54015-54029
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54030-54048
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54049-54063
Unbiased Multi-Label Learning from Crowdsourced Annotations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54064-54081
Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54082-54103
LESS: Selecting Influential Data for Targeted Instruction Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54104-54132
SMaRt: Improving GANs with Score Matching Regularity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54133-54155
Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54156-54177
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54178-54190
Delving into the Convergence of Generalized Smooth Minimax Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54191-54211
Differentially Private Post-Processing for Fair Regression
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54212-54235
Towards Neural Architecture Search through Hierarchical Generative Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54236-54254
Towards a Self-contained Data-driven Global Weather Forecasting Framework
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54255-54275
Category-Aware Active Domain Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54276-54287
Improved Operator Learning by Orthogonal Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54288-54299
Improving Transformers with Dynamically Composable Multi-Head Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54300-54318
Uniformly Stable Algorithms for Adversarial Training and Beyond
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54319-54340
Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54341-54362
Efficient Contrastive Learning for Fast and Accurate Inference on Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54363-54381
CCM: Real-Time Controllable Visual Content Creation Using Text-to-Image Consistency Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54382-54401
Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54402-54413
Learning to Explore in POMDPs with Informational Rewards
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54414-54429
Automating the Selection of Proxy Variables of Unmeasured Confounders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54430-54459
FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54460-54474
Improving SAM Requires Rethinking its Optimization Formulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54475-54487
Implicit Bias of AdamW: $\ell_∞$-Norm Constrained Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54488-54510
Local Causal Structure Learning in the Presence of Latent Variables
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54511-54530
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54531-54560
MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54561-54575
Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54576-54589
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54590-54613
Reflected Flow Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54614-54634
Federated Neuro-Symbolic Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54635-54655
Less is More: on the Over-Globalizing Problem in Graph Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54656-54672
HelmFluid: Learning Helmholtz Dynamics for Interpretable Fluid Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54673-54697
SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54698-54714
Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54715-54754
Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54755-54776
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54777-54791
A General Framework for Sequential Decision-Making under Adaptivity Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54792-54830
Parameter-Dependent Competitive Analysis for Online Capacitated Coverage Maximization through Boostings and Attenuations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54831-54851
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54852-54865
Stochastic Bandits with ReLU Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54866-54887
Intersectional Unfairness Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54888-54917
Semantic-Aware Human Object Interaction Image Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54918-54932
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54933-54961
Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54962-54982
Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54983-54998
Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity Theory
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:54999-55014
Equivariant Graph Neural Operator for Modeling 3D Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55015-55032
Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55033-55047
BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55048-55075
Conformal prediction for multi-dimensional time series by ellipsoidal sets
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55076-55099
Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55100-55111
Meta-Reinforcement Learning Robust to Distributional Shift Via Performing Lifelong In-Context Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55112-55125
Prompt-guided Precise Audio Editing with Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55126-55143
Low-Rank Similarity Mining for Multimodal Dataset Distillation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55144-55161
Robust Inverse Constrained Reinforcement Learning under Model Misspecification
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55162-55185
Soft Prompt Recovers Compressed LLMs, Transferably
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55186-55203
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55204-55224
Adaptive Group Personalization for Federated Mutual Transfer Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55225-55240
Robust Universal Adversarial Perturbations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55241-55266
Learning Exceptional Subgroups by End-to-End Maximizing KL-Divergence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55267-55285
Pricing with Contextual Elasticity and Heteroscedastic Valuation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55286-55304
Principled Preferential Bayesian Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55305-55336
Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55337-55347
SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55348-55370
Libra: Building Decoupled Vision System on Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55371-55388
A Sparsity Principle for Partially Observable Causal Representation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55389-55433
Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55434-55464
Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55465-55489
Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55490-55500
Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55501-55524
Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55525-55546
Iterative Regularized Policy Optimization with Imperfect Demonstrations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55547-55568
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55569-55594
Offline Multi-Objective Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55595-55624
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55625-55655
Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55656-55681
FairProof : Confidential and Certifiable Fairness for Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55682-55705
Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55706-55738
Balancing Similarity and Complementarity for Federated Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55739-55758
Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55759-55777
Exploring the LLM Journey from Cognition to Expression with Linear Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55778-55796
A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55797-55813
Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55814-55838
Handling Heterogeneous Curvatures in Bandit LQR Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55839-55858
Foundations of Testing for Finite-Sample Causal Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55859-55900
Retrieval Across Any Domains via Large-scale Pre-trained Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55901-55912
Reducing Balancing Error for Causal Inference via Optimal Transport
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55913-55927
Do Efficient Transformers Really Save Computation?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55928-55947
Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55948-55960
Sample-Efficient Multiagent Reinforcement Learning with Reset Replay
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55961-55975
DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55976-55997
A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55998-56032
Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56033-56046
Latent Space Symmetry Discovery
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56047-56070
Guidance with Spherical Gaussian Constraint for Conditional Diffusion
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56071-56095
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56096-56108
Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56109-56138
SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56139-56155
Small-loss Adaptive Regret for Online Convex Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56156-56195
Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56196-56215
Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56216-56234
Position: Towards Implicit Prompt For Text-To-Image Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56235-56250
Position: Towards Unified Alignment Between Agents, Humans, and Environment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56251-56275
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56276-56297
Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56298-56318
ILILT: Implicit Learning of Inverse Lithography Technologies
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56319-56331
Representation Surgery for Multi-Task Model Merging
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56332-56356
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56357-56381
Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56382-56396
Exploration and Anti-Exploration with Distributional Random Network Distillation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56397-56421
UniAudio: Towards Universal Audio Generation with Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56422-56447
Explain Temporal Black-Box Models via Functional Decomposition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56448-56464
Position: Video as the New Language for Real-World Decision Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56465-56484
ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56485-56500
Gated Linear Attention Transformers with Hardware-Efficient Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56501-56523
Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56524-56541
Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56542-56593
How Graph Neural Networks Learn: Lessons from Training Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56594-56623
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56624-56664
Neuro-Symbolic Temporal Point Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56665-56680
One Meta-tuned Transformer is What You Need for Few-shot Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56681-56703
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56704-56721
Accelerating Look-ahead in Bayesian Optimization: Multilevel Monte Carlo is All you Need
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56722-56748
MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56749-56792
Mol-AE: Auto-Encoder Based Molecular Representation Learning With 3D Cloze Test Objective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56793-56811
What is Dataset Distillation Learning?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56812-56834
Protein Conformation Generation via Force-Guided SE(3) Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56835-56859
Empowering Graph Invariance Learning with Deep Spurious Infomax
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56860-56884
Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56885-56913
Mobile Attention: Mobile-Friendly Linear-Attention for Vision Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56914-56926
Socialized Learning: Making Each Other Better Through Multi-Agent Collaboration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56927-56945
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56946-56965
EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56966-56981
Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:56982-57017
Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57018-57032
StableMask: Refining Causal Masking in Decoder-only Transformer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57033-57052
Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textitIrreversibly$ and $\textitMonotonically$ Impairs “Difficult" Downstream Tasks in LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57053-57068
Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57069-57084
High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57085-57100
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57101-57115
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57116-57198
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57199-57216
Uncertainty Estimation by Density Aware Evidential Deep Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57217-57243
Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57244-57314
FRAG: Frequency Adapting Group for Diffusion Video Editing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57315-57330
Breadth-First Exploration on Adaptive Grid for Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57331-57349
When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57350-57366
SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57367-57383
Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57384-57414
Towards Resource-friendly, Extensible and Stable Incomplete Multi-view Clustering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57415-57440
Activation-Descent Regularization for Input Optimization of ReLU Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57441-57458
Collage: Light-Weight Low-Precision Strategy for LLM Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57459-57479
Privacy-Preserving Instructions for Aligning Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57480-57506
Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational Autoencoders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57507-57526
Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57527-57543
Enabling Few-Shot Learning with PID Control: A Layer Adaptive Optimizer
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57544-57558
Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57559-57596
Learning Causal Dynamics Models in Object-Oriented Environments
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57597-57638
ViP: A Differentially Private Foundation Model for Computer Vision
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57639-57658
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57659-57677
Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57678-57702
Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57703-57729
MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57730-57754
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57755-57775
Improving Sharpness-Aware Minimization by Lookahead
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57776-57802
A Unified Adaptive Testing System Enabled by Hierarchical Structure Search
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57803-57817
Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57818-57841
Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57842-57870
A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57871-57886
SHINE: Shielding Backdoors in Deep Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57887-57904
Self-Rewarding Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57905-57923
Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57924-57952
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57953-57965
OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:57966-58018
Federated Self-Explaining GNNs with Anti-shortcut Augmentations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58019-58036
How to Leverage Diverse Demonstrations in Offline Imitation Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58037-58067
Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58068-58089
Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58090-58104
Sample as you Infer: Predictive Coding with Langevin Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58105-58121
More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58122-58139
How to Explore with Belief: State Entropy Maximization in POMDPs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58140-58157
See More Details: Efficient Image Super-Resolution by Experts Mining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58158-58173
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58174-58196
Robustly Learning Single-Index Models via Alignment Sharpness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58197-58243
Low-Cost High-Power Membership Inference Attacks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58244-58282
Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58283-58305
Continuous Treatment Effects with Surrogate Outcomes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58306-58328
tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58329-58347
Token-level Direct Preference Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58348-58365
Learning Reward for Robot Skills Using Large Language Models via Self-Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58366-58386
Graph Mixup on Approximate Gromov–Wasserstein Geodesics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58387-58406
Interacting Diffusion Processes for Event Sequence Forecasting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58407-58430
IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58431-58447
Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58448-58469
Robust Learning-Augmented Dictionaries
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58470-58483
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58484-58509
Tight Partial Identification of Causal Effects with Marginal Distribution of Unmeasured Confounders
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58510-58562
DAG-Based Column Generation for Adversarial Team Games
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58563-58578
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58579-58598
Efficient Stochastic Approximation of Minimax Excess Risk Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58599-58630
Discounted Adaptive Online Learning: Towards Better Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58631-58661
Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58662-58679
Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58680-58716
Verification of Machine Unlearning is Fragile
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58717-58738
Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58739-58762
LQER: Low-Rank Quantization Error Reconstruction for LLMs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58763-58779
Random Scaling and Momentum for Non-smooth Non-convex Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58780-58799
Towards Certified Unlearning for Deep Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58800-58818
Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58819-58839
CaM: Cache Merging for Memory-efficient LLMs Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58840-58850
Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58851-58880
MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58881-58896
SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58897-58934
Model-based Reinforcement Learning for Parameterized Action Spaces
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58935-58954
Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58955-58966
Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58967-58983
Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:58984-59002
Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59003-59023
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59024-59041
Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59042-59065
Parameter-Efficient Fine-Tuning with Controls
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59066-59079
Deep Regression Representation Learning with Topology
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59080-59099
Understanding Unimodal Bias in Multimodal Deep Linear Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59100-59125
Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59126-59147
An Interpretable Evaluation of Entropy-based Novelty of Generative Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59148-59172
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59173-59190
S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59191-59209
DPZero: Private Fine-Tuning of Language Models without Backpropagation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59210-59246
Conditional Language Learning with Context
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59247-59263
Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59264-59288
BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59289-59309
Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59310-59328
Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59329-59357
UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59358-59381
Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59382-59402
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59403-59420
Wukong: Towards a Scaling Law for Large-Scale Recommendation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59421-59434
Nonparametric Teaching of Implicit Neural Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59435-59458
Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59459-59489
Sparse-to-dense Multimodal Image Registration via Multi-Task Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59490-59504
Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59505-59519
In-Context Principle Learning from Mistakes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59520-59558
Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59559-59575
Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59576-59600
A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59601-59640
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59641-59669
How Language Model Hallucinations Can Snowball
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59670-59684
Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59685-59699
Online Resource Allocation with Non-Stationary Customers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59700-59730
Flexible Residual Binarization for Image Super-Resolution
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59731-59740
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59741-59758
Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59759-59782
Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59783-59805
Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59806-59826
Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59827-59850
Learning Low-dimensional Latent Dynamics from High-dimensional Observations: Non-asymptotics and Lower Bounds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59851-59896
Matrix Information Theory for Self-Supervised Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59897-59918
Switchable Decision: Dynamic Neural Generation Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59919-59931
Interpreting and Improving Large Language Models in Arithmetic Calculation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59932-59950
Directly Denoising Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59951-59974
Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59975-59991
GroupCover: A Secure, Efficient and Scalable Inference Framework for On-device Model Protection based on TEEs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:59992-60003
Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60004-60020
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60021-60039
Exploring the Benefit of Activation Sparsity in Pre-training
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60040-60056
Causal Representation Learning from Multiple Distributions: A General Setting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60057-60075
FESSNC: Fast Exponentially Stable and Safe Neural Controller
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60076-60098
Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60099-60115
NExT-Chat: An LMM for Chat, Detection and Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60116-60133
Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60134-60178
Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60179-60196
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60197-60219
Generalization Analysis for Multi-Label Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60220-60243
Quantum Algorithms and Lower Bounds for Finite-Sum Optimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60244-60270
PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetition
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60271-60287
MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60288-60304
Lightweight Image Super-Resolution via Flexible Meta Pruning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60305-60314
Offline Training of Language Model Agents with Functions as Learnable Weights
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60315-60335
Efficient Contextual Bandits with Uninformed Feedback Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60336-60358
Efficient Denoising Diffusion via Probabilistic Masking
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60359-60378
Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60379-60395
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60396-60413
Uncertainty-Aware Reward-Free Exploration with General Function Approximation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60414-60445
Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60446-60495
On the Expressive Power of Spectral Invariant Graph Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60496-60526
Position: Social Environment Design Should be Further Developed for AI-based Policy-Making
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60527-60540
Neural Jump-Diffusion Temporal Point Processes
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60541-60557
The Emergence of Reproducibility and Consistency in Diffusion Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60558-60590
Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60591-60604
Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60605-60625
Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60626-60643
Position: Measure Dataset Diversity, Don’t Just Claim It
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60644-60673
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60674-60703
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60704-60748
Image Fusion via Vision-Language Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60749-60765
Learning and Forgetting Unsafe Examples in Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60766-60784
VideoPrism: A Foundational Visual Encoder for Video Understanding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60785-60811
APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60812-60831
Subgoal-based Demonstration Learning for Formal Theorem Proving
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60832-60865
Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60866-60905
Spider: A Unified Framework for Context-dependent Concept Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60906-60926
Rethinking Adversarial Robustness in the Context of the Right to be Forgotten
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60927-60939
Quantum Implicit Neural Representations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60940-60956
Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:60957-61020
A Statistical Theory of Regularization-Based Continual Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61021-61039
Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61040-61071
Gradient-based Visual Explanation for Transformer-based CLIP
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61072-61091
CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61092-61107
Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61108-61120
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61121-61143
When Will Gradient Regularization Be Harmful?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61144-61158
LangCell: Language-Cell Pre-training for Cell Identity Understanding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61159-61185
Optimistic Multi-Agent Policy Gradient
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61186-61202
Clifford-Steerable Convolutional Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61203-61228
3D-VLA: A 3D Vision-Language-Action Generative World Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61229-61245
How Does Goal Relabeling Improve Sample Efficiency?
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61246-61266
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61267-61286
Exploiting Negative Samples: A Catalyst for Cohort Discovery in Healthcare Analytics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61287-61320
Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61321-61348
GPT-4V(ision) is a Generalist Web Agent, if Grounded
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61349-61385
Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61386-61412
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61413-61431
ESM All-Atom: Multi-Scale Protein Language Model for Unified Molecular Modeling
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61432-61453
BAT: Learning to Reason about Spatial Sounds with Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61454-61469
Conformal Predictions under Markovian Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61470-61497
Detecting and Identifying Selection Structure in Sequential Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61498-61525
ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61526-61558
DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61559-61592
On Prompt-Driven Safeguarding for Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61593-61613
Self-Infilling Code Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61614-61648
Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61649-61663
ERQ: Error Reduction for Post-Training Quantization of Vision Transformers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61664-61680
Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61681-61707
Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61708-61726
GNNs Also Deserve Editing, and They Need It More Than Once
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61727-61746
Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61747-61762
Jacobian Regularizer-based Neural Granger Causality
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61763-61782
Differentially Private Worst-group Risk Minimization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61783-61803
MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61804-61824
MD tree: a model-diagnostic tree grown on loss landscape
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61825-61853
On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61854-61884
RoboDreamer: Learning Compositional World Models for Robot Imagination
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61885-61896
MultiMax: Sparse and Multi-Modal Attention Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61897-61912
Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61913-61933
Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61934-61963
Pedestrian Attribute Recognition as Label-balanced Multi-label Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61964-61978
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:61979-62001
Conformalized Adaptive Forecasting of Heterogeneous Trajectories
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62002-62056
Sequential Kernel Goodness-of-fit Testing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62057-62075
RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62076-62087
CurBench: Curriculum Learning Benchmark
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62088-62107
GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62108-62118
Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62119-62137
Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62138-62160
DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62161-62177
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62178-62209
Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62210-62256
Effective Federated Graph Matching
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62257-62293
Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62294-62306
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62307-62331
Iterative Search Attribution for Deep Neural Networks
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62332-62348
Generative Active Learning for Long-tailed Instance Segmentation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62349-62368
Asymmetry in Low-Rank Adapters of Foundation Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62369-62385
Improving Open-Ended Text Generation via Adaptive Decoding
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62386-62404
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62405-62428
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62429-62442
Switched Flow Matching: Eliminating Singularities via Switching ODEs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62443-62475
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62476-62509
Toward Availability Attacks in 3D Point Clouds
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62510-62530
Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62531-62548
Online Learning in Betting Markets: Profit versus Prediction
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62549-62580
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62581-62598
Dynamic Evaluation of Large Language Models by Meta Probing Agents
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62599-62617
CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62618-62637
Language Models Represent Beliefs of Self and Others
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62638-62681
Stealthy Imitation: Reward-guided Environment-free Policy Stealing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62682-62706
Reinformer: Max-Return Sequence Modeling for Offline RL
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62707-62722
COALA: A Practical and Vision-Centric Federated Learning Platform
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62723-62742
GPTSwarm: Language Agents as Optimizable Graphs
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62743-62767
Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62768-62778
Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62779-62802
Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62803-62814
Viewing Transformers Through the Lens of Long Convolutions Layers
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62815-62831
Emergence of In-Context Reinforcement Learning from Noise Distillation
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62832-62846
Symmetry Induces Structure and Constraint of Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62847-62866
Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62867-62891
Fool Your (Vision and) Language Model with Embarrassingly Simple Permutations
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62892-62913
Leveraging Attractor Dynamics in Spatial Navigation for Better Language Parsing
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62914-62933
Hybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62934-62963
Compositional Few-Shot Class-Incremental Learning
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62964-62977
BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62978-62992
Active Statistical Inference
; Proceedings of the 41st International Conference on Machine Learning, PMLR 235:62993-63010
subscribe via RSS