![[UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models Logo]](/v322/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 322: UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, 06 December 2025, San Diego Convention Center, San Diego, USA
[edit]
Editors: Marco Fumero, Clementine Domine, Zorah L"ahner, Irene Cannistraci, Bo Zhao, Alex Williams
Preface of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:1-9
[abs][Download PDF]
Enhancing Multimodal Product Retrieval in E-Commerce by Reversing Typographic Attacks
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:10-29
On Defining Neural Averaging
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:30-44
An Empirical Study on Unifying JEPA and Language Supervision for Visual Representation Learning
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:45-56
Mice to Machines: Neural Representations from Visual Cortex for Domain Generalization
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:57-69
Representing Neural Network Layers as Linear Operations via Koopman Operator Theory
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:70-80
Brain–Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:81-101
MultiPersona-Align: Zero-Shot Multi-Subject Personalized Image Generation with Layout-Guidance via Dual Representation Alignment
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:102-114
Interpreting convolutional neural networks to study wide-field amacrine cell inhibition in the retina
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:115-128
Bridging Large Gaps in Neural Network Representations with Model Stitching
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:129-139
Any-Subgroup Equivariant Networks via Symmetry Breaking
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:140-158
Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:159-167
Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:168-182
DocQIR-Emb: Document Image Retrieval with Multi-lingual Question Query
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:183-198
Improving Generation Quality of Long-Tailed Diffusion via Disentangled Latent Representations
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:199-211
Quantum Relational Knowledge Distillation
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:212-234
Cross-Modal Representational Alignment with LLM Priors for Image Generation
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:235-247
Unifying Vision-Language Latents for Zero-label Image Caption Enhancement
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:248-261
Superposition in Graph Neural Networks
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:262-274
Neural Correlates of Language Models Are Specific to Human Language
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:275-289
Evaluating Foundation Models’ 3D Understanding Through Multi-View Correspondence Analysis
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:290-316
Weight Weaving: Parameter Pooling for Data-Free Model Merging
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:317-329
SemCLIP: A Semantic Memory-Aligned Vision Language Model
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:330-341
Superposition disentanglement of neural representations reveals hidden alignment
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:342-359
GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:360-373
An Empirical Study of Task and Feature Correlations in the Reuse of Pre-trained Models
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:374-384
Dead Feature Counts in Sparse Autoencoders Predict Underlying Deep Q Networks’ Effectiveness
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:385-397
On Task Vectors and Gradients
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:398-417
TextIT: Inference-Time Representation Alignment for Improved Visual Text Generation in Diffusion Models
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:418-430
Exploring Augmentation-Driven Invariances for Graph Self-supervised Learning in Spatial Omics
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:431-445
Escaping Plato’s Cave: JAM for Aligning Independently Trained Vision and Language Models
; Proceedings of UniReps: the Third Edition of the Workshop on Unifying Representations in Neural Models, PMLR 322:446-458
subscribe via RSS