NeurIPS 2025 Past Other

UniReps: 3rd Edition of the Workshop on Unifying Representations in Neural Models

UniReps2025

Submission deadline
Aug 30, 2025, 14:20 UTC
imported from OpenReview — check the website for extensions
Submission portal
OpenReview
Notes
Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).

Accepted papers (116)

Fetched from OpenReview (v2) on 2026-06-10.

  1. A Circular Argument: Does RoPE need to be Equivariant for Vision?

    Chase van de Geijn, Timo Lüddecke, Polina Turishcheva, Alexander S. Ecker · PDF
  2. A second-order perspective on linear mode connectivity modulo permutations

    Beatrix Benkő · PDF
  3. All In: Bridging Input Feature Spaces Towards Graph Foundation Models

    Moshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua, Bruno Ribeiro, Carola-Bibiane Schönlieb · PDF
  4. An Empirical Study of Task and Feature Correlations in the Reuse of Pre-trained Models

    Jama Hussein Mohamud, Willie Brink · PDF
  5. An Empirical Study on Unifying JEPA and Language Supervision for Visual Representation Learning

    Shixuan Liu, Daniel A Li, Yiwei Lyu, Akhil Kondepudi, Honglak Lee, Todd C Hollon · PDF
  6. Analyze the Neurons, not the Embeddings: Understanding When and Where LLM Representations Align with Humans

    Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson, Katherine Metcalf, Skyler Seto, Barry-John Theobald · PDF
  7. Any-Subgroup Equivariant Networks via Symmetry Breaking

    Abhinav Goel, Derek Lim, Hannah Lawrence, Stefanie Jegelka, Ningyuan Huang · PDF
  8. Better Representations, Better Speech BCIs: a Multitask Approach

    Tommaso Boccato, Michał Olak, Jamie Oliver, Chadwick Boulay, Spencer Kellis, Matteo Ferrante · PDF
  9. Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models

    Sharut Gupta, Shobhita Sundaram, Chenyu Wang, Stefanie Jegelka, Phillip Isola · PDF
  10. Beyond [cls]: Exploring the true potential of Masked Image Modeling representations

    Marcin Przewięźlikowski, Randall Balestriero, Wojciech Jasiński, Marek Śmieja, Bartosz Michał Zieliński · PDF
  11. Bias-driven Alignment of Linear and ReLU Networks

    Jirko Rubruck, Kai Jappe Sandbrink, Christopher Summerfield, Andrew M Saxe, Devon Jarvis · PDF
  12. Blinded by Language: Multimodal LLMs Underuse Their Vision Backbone

    Haider Al-Tahan, Randall Balestriero, Mark Ibrahim · PDF
  13. Brain–Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage

    Angela Lopez-Cardona, Sebastian Idesis, Mireia Masias Bruns, Sergi Abadal, Ioannis Arapakis · PDF
  14. Bridging Large Gaps in Neural Network Representations with Model Stitching

    Neil Traft · PDF
  15. Building expertise through task-specific representational alignment in biological and artificial neural networks

    Ashug Gurijala, Michael Nguyen Jr, John O'Doherty, Sneha Aenugu · PDF
  16. Clifford Algebraic Rotor Embeddings : Maybe embeddings should start to CARE

    Sameeksha Sriram, Timo Lüddecke, Ayush Paliwal, Alexander S. Ecker, Chase van de Geijn · PDF
  17. Condition-Dependent Representational Alignment between Whisper and the Human Speech Network

    Chia-Chun Dan Hsu, Francis Pingfan Chien, Rong Chao, Ching Chih Sung, Yu-Te Wang, Po-Jang Hsieh, Yu Tsao · PDF
  18. Context-Aware World Models for Task-Agnostic Control

    Busra Tugce Gurbuz, Hafez Ghaemi, Christopher C Pack, Shahab Bakhtiari, Eilif B. Muller · PDF
  19. Contrastive Representations for Temporal Reasoning

    Alicja Ziarko, Michał Bortkiewicz, Michał Zawalski, Benjamin Eysenbach, Piotr Miłoś · PDF
  20. Cross-Modal Representational Alignment with LLM Priors for Image Generation

    Mykola Vysotskyi, Zahar Kohut, Anna-Alina Bondarets, Taras Rumezhak, Volodymyr Karpiv · PDF
  21. Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries

    Alexander Beiser, Flavio Martinelli, Wulfram Gerstner, Johanni Brea · PDF
  22. Data symmetries generate drifting similarity matrices in manifold-tiling neural codes

    Farhad Pashakhanloo, Jacob A Zavatone-Veth · PDF
  23. Dead Feature Counts in Sparse Autoencoders Predict Underlying Deep Q Networks' Effectiveness

    Coleman DuPlessie · PDF
  24. Decoding Projections From Frozen Random Weights in Autoencoders: What Information Do They Encode?

    Nancy Thomas, Keshav Ramani, Annita Vapsi, Daniel Borrajo · PDF
  25. DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining

    Bryan Rodas, Natalie Montesino, Jakob Ambsdorf, David Klindt, Randall Balestriero · PDF
  26. Distinguishing probabilistic from non-probabilistic neural representations

    Ishan Kalburge, Máté Lengyel · PDF
  27. Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum

    Wenquan Lu, Jiaqi Zhang, Hugues Van Assel, Randall Balestriero · PDF
  28. DocQIR-Emb: Document Image Retrieval with Multi-lingual Question Query

    Chih-Hui Ho, Giovanna Carreira Marinho, Felipe Viana, Varad Pimpalkhute, Rodolfo Luis Tonoli, Andre Von Zuben · PDF
  29. Echo of Bayes: Learned Memory Functions Can Recover Belief States

    Juan Liévano-Karim, Peter Koepernik, George Konidaris, Cameron Allen · PDF
  30. Enhancing Multimodal Product Retrieval in E-Commerce by Reversing Typographic Attacks

    Janet Jenq, Hongda Shen · PDF
  31. Equivalences between network modularity and diverse low-dimensional representations

    Mikail Rubinov · PDF
  32. Escaping Plato’s Cave: JAM for Aligning Independently Trained Vision and Language Models

    Hyoseo Yoon, Been Kim, Yisong Yue · PDF
  33. Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis

    Valentina Lilova, Toyesh Chakravorty, Julian I. Bibo, Emma Boccaletti, Brandon Li, Lívia Baxová, Cees G. M. Snoek, Mohammadreza Salehi · PDF
  34. Exact Learning Dynamics of Bottlenecked and Wide Deep Linear Networks

    Clémentine Carla Juliette Dominé · PDF
  35. Exploring Augmentation-Driven Invariances for Graph Self-supervised Learning in Spatial Omics

    Lovro Rabuzin, Michel Tarnow, Valentina Boeva · PDF
  36. Finding Fingerprints of Out-Of-Distribution Failures from In-Distribution Geometry

    Chi-Ning Chou, Artem Kirsanov, Yao-Yuan Yang, SueYeon Chung · PDF
  37. From Aggregation to Guidance: Strategies for Personalized Federated Fine-Tuning of Foundation Models

    Mikołaj Piórczyński, Wojciech Łapacz, Xinyu Li, Chang Liu, Abby Turner, Artur Dubrawski · PDF
  38. GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace

    Mikołaj Sacha, Hammad Jafri, Mattie Terzolo, Ayan Sinha, Andrew Rabinovich · PDF
  39. Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders

    Ege Erdogan, Ana Lucic · PDF
  40. Hand-Engineered Image-Computable Models Can Still Outperform DNNs in V1 Similarity

    Tanish Mendki, Sudhanshu Srivastava, Ansh Soni · PDF
  41. Human-like individual differences emerge from random weight initializations in neural networks

    Herrick Fung, Apurva Ratan Murty, Doby Rahnev · PDF
  42. Improving Generation Quality of Long-Tailed Diffusion via Disentangled Latent Representations

    Esther Rodriguez, Monica Welfert, Samuel McDowell, Nathan Stromberg, Julian Antolin Camarena, Lalitha Sankar · PDF
  43. Interpreting convolutional neural networks to study wide-field amacrine cell inhibition in the retina

    Michaela Vystrčilová, Shashwat Sridhar, Max F Burg, Tim Gollisch, Alexander S. Ecker · PDF
  44. Learning Resilient Molecular Representations with Dynamic Multi-Modal Fusion

    Indra Priyadarsini, Seiji Takeda, Lisa Hamada, Sina Klampt, Takao Moriyama · PDF
  45. Learning using switching synaptic plasticity rules

    Denis Turcu, Jonathan Cornford, Sven Dorkenwald, Stefan Mihalas · PDF
  46. Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs

    Stefan Horoi, Sangwoo Cho, Supriyo Chakraborty, Shi-Xiong Zhang, Sambit Sahu, Guy Wolf, Genta Indra Winata · PDF
  47. LevyScore: A Fast Sample-Wise Confidence Score of Pretrained Joint Embedding Model

    Lucas Maes, Damien Scieur, Randall Balestriero · PDF
  48. Linear Maps for Cross-Model Finetuning Transfer

    Darrin O'Brien, Dhikshith Gajulapalli, Pranay Rishi Nalem, Alexander Ramsey, Eric Xia · PDF
  49. Linear Recurrent Networks Approximate Optimal Filtering in Hidden Markov Models

    Andrew Mah, Alex H Williams · PDF
  50. LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures

    Hai Huang, Yann LeCun, Randall Balestriero · PDF
  51. Look, Then Speak: Social Tokens for Grounding LLMs in Visual Interactions

    Kathy Garcia, Vighnesh Subramaniam, Boris Katz, Brian Cheung · PDF
  52. Low-Rank Successor Representations Capture Human-Like Generalization

    Eva Yi Xie, Nathaniel D. Daw, Benjamin Eysenbach · PDF
  53. MASS: MoErging through Adaptive Subspace Selection

    Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo, Maria Sofia Bucarelli, Simone Scardapane, Fabrizio Silvestri, Iacopo Masi, Emanuele Rodolà · PDF
  54. Measure Before You Look: Grounding Embeddings Through Manifold Metrics

    César Miguel Valdez Córdova, Matthew Scicluna, Shuang Ni, Smita Krishnaswamy, Simon Gravel, Guy Wolf · PDF
  55. Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks

    Ann Huang, Satpreet Harcharan Singh, Flavio Martinelli, Kanaka Rajan · PDF
  56. Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Families

    Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla · PDF
  57. Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling

    Andrea Ceni, Alessio Gravina, Carola-Bibiane Schönlieb, Claudio Gallicchio, Davide Bacciu, Moshe Eliasof · PDF
  58. Mice to Machines: Neural Representations from Visual Cortex for Domain Generalization

    Ahmed Rashid Qazi, Hamd Jalil, Asim Iqbal · PDF
  59. Misalignment Between Vision-Language Representations in Vision-Language Models

    Yonatan Gideoni, Yoav Gelberg, Tim G. J. Rudner, Yarin Gal · PDF
  60. MultiPersona-Align: Zero-Shot Multi-Subject Personalized Image Generation with Layout-Guidance via Dual Representation Alignment

    Veddhanth Chakravarthy, Samir Kumar das mohapatra, Chandrakala S · PDF
  61. Neural Correlates of Language Models Are Specific to Human Language

    Iñigo Parra · PDF
  62. Neural Embedding Alignment Reveals Nonlinear Latent Transformations across Brain Regions

    Hanfei Cao, Mikio Christian Aoi, Stephen L Keeley · PDF
  63. NeuroFusion: A Unified Framework for Generalized Visual Stimulus Decoding from fMRI Across Datasets and Subjects

    Muhammad Kashif, Matteo Ferrante, Nicola Toschi · PDF
  64. Neuron-Level Linguistic Selectivity in LLMs via a Classifier-Free Framework

    Linyang He, Nima Mesgarani · PDF
  65. No Clustering, No Routing: How Transformers Actually Process Rare Tokens

    Jing Liu · PDF
  66. On Defining Neural Averaging

    Su Hyeong Lee, Richard Ngo · PDF
  67. On Task Vectors and Gradients

    Luca Zhou, Daniele Solombrino, Donato Crisostomi, Maria Sofia Bucarelli, Giuseppe Alessio D'Inverno, Fabrizio Silvestri, Emanuele Rodolà · PDF
  68. On the Identifiability of Latent Action Policies

    Sebastien Lachapelle · PDF
  69. On the Impact of Topological Regularization on Geometrical and Topological Alignment in Autoencoders: An Empirical Study

    Samuel Graepler, Nico Scherf, Anna Wienhard, Diaaeldin Taha · PDF
  70. On the Training Dynamics of Contrastive Learning with Imbalanced Feature Distributions: A Theoretical Study of Feature Learning

    Haixu Liao, Yating Zhou, Songyang Zhang, Shuai Zhang · PDF
  71. One Question at a Time: A Semantic Bottleneck for Interpretable Visual Brain Decoding from fMRI

    Sara Cammarota, Matteo Ferrante, Nicola Toschi · PDF
  72. Perspective: Summary Statistics of Learning

    Jacob A Zavatone-Veth, Blake Bordelon, Cengiz Pehlevan · PDF
  73. Phase codes emerge in recurrent neural networks optimized for modular arithmetic

    Keith Thomas Murray · PDF
  74. Quantifying information stored in synaptic connections rather than in firing activities of neural networks

    Xinhao Fan, Shreesh P Mysore · PDF
  75. Quantum Relational Knowledge Distillation

    Chen-Yu Liu, Kuan-Cheng Chen, Keisuke Murota, Samuel Yen-Chi Chen, Enrico Rinaldi · PDF
  76. R²-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation

    Zhen Wu, Ritam Dutt, Luke M. Breitfeller, Armineh Nourbakhsh, Siddharth Parekh, Carolyn Rose · PDF
  77. Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization

    Yilun Kuang, Yash Dagade, Deep Chakraborty, Erik Learned-Miller, Randall Balestriero, Tim G. J. Rudner, Yann LeCun · PDF
  78. Relational Representation Learning

    Lucas Maes, Ian K Hajra, Arnesh Batra, Hugues Van Assel, Damien Scieur, Randall Balestriero · PDF
  79. Representing Neural Network Layers as Linear Operations via Koopman Operator Theory

    Nishant Suresh Aswani, Saif Jabari, Muhammad Shafique · PDF
  80. Rethinking Objectives for Multi-View and Multi-Modal Contrastive Learning

    Panagiotis Koromilas, Efthymios Georgiou, Giorgos Bouritsas, Theodoros Giannakopoulos, Mihalis Nicolaou, Yannis Panagakis · PDF
  81. Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models

    Sayam Goyal, Brad Peters, María Emilia Granda, Akshath Vijayakumar Narmadha, Dharunish Yugeswardeenoo, Callum Stuart McDougall, Sean O'Brien, Ashwinee Panda, Kevin Zhu, Cole Blondin · PDF
  82. Self-Supervised Learning from Structural Invariance

    Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee, Laurent Charlin · PDF
  83. SemCLIP: A Semantic Memory-Aligned Vision Language Model

    Tanveer F Syeda-Mahmood, Niharika S. D'Souza, Ken C. L. Wong, Raziuddin Mahmood, Luyao Shi, Ashutosh Jadhav, Satyananda Kashyap, David Beymer · PDF
  84. Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior

    Eric Zhang, Daniel Aarao Reis Arturi, Andrew Adrian Ansah, Kevin Zhu, Ashwinee Panda, Aishwarya Balwani · PDF
  85. Signatures of the Auditory Cortex Reveal Discrepancies Across Speech Recognition Models

    Gasser Elbanna, Ivy Brundege, Josh Mcdermott · PDF
  86. SoftStep: learning instance-wise similarity functions between neural representations

    Aviad Susman, Baihan Lin, mayte suarez-farinas, Joseph T Colonel · PDF
  87. Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces

    Bahareh Tolooshams, Ailsa Shen, Anima Anandkumar · PDF
  88. Spectral Insights into Data-Oblivious Critical Layers in Large Language Models

    Xuyuan Liu, Lei Hsiung, Yaoqing Yang, Yujun Yan · PDF
  89. Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks

    Leonid Pogorelyuk, Niels Leif Bracher, Aaron Verkleeren, Lars Kühmichel, Stefan T. Radev · PDF
  90. stable-pretraining: Foundation Model Research Made Simple

    Randall Balestriero, Hugues Van Assel, Sami BuGhanem, Lucas Maes · PDF
  91. Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation

    Chenruo Liu, Hongjun Liu, Zeyu Lai, Yiqiu Shen, Chen Zhao, Qi Lei · PDF
  92. Superposition disentanglement of neural representations reveals hidden alignment

    André Longon, David Klindt, Meenakshi Khosla · PDF
  93. Superposition in Graph Neural Networks

    Lukas Pertl, Han Xuanyuan, Pietro Lio · PDF
  94. SWAT-NN: Simultaneous Weights and Architecture Training for Neural Networks in a Latent Space

    Zitong Huang, Mansooreh Montazerin, Ajitesh Srivastava · PDF
  95. Symmetry-Aware Fully-Amortized Optimization with Scale Equivariant Graph Metanetworks

    Bart Kuipers, Freek Byrman, Daniel Uyterlinde, Alejandro García-Castellanos · PDF
  96. Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks

    Niket Patel, Randall Balestriero · PDF
  97. TextIT: Inference-Time Representation Alignment for Improved Visual Text Generation in Diffusion Models

    Abhikhya Tripathy, Aishwarya Agarwal, Srikrishna Karanam, Balaji Vasan Srinivasan · PDF
  98. The Fragility of Polarity: A Perturbative Analysis of the sign Hypothesis in Sparse Networks

    Arindam Biswas · PDF
  99. The Geometry and Topology of Modular Addition Representations

    Gabriela Moisescu-Pareja, Gavin McCracken, Colin Daniels, Harley Wiltzer, Vincent Létourneau, Jonathan Love · PDF
  100. The Performance Cost of Representational Misalignment

    Sudhanshu Srivastava, Ansh Soni, Meenakshi Khosla · PDF
  101. Topological Alignment of Shared Vision-Language Embedding Space

    Junwon You, Kang Dasol, Jae-Hun Jung · PDF
  102. Towards Interpretable Deep Neural Networks for Tabular Data

    Khawla Elhadri, Jörg Schlötterer, Christin Seifert · PDF
  103. Towards Mitigating Systematics in Large-Scale Surveys via Few-Shot Optimal Transport-Based Feature Alignment

    Sultan Hassan, Sambatra Andrianomena, Benjamin Dan Wandelt · PDF
  104. Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps

    Aditya Ravuri, Neil D Lawrence · PDF
  105. Two-Scale Latent Dynamics for Recurrent-Depth Transformers

    Francesco Pappone, Donato Crisostomi, Emanuele Rodolà · PDF
  106. Understanding Task Transfer in Vision-Language Models

    Bhuvan Sachdeva, Karan Uppal, Abhinav Java, Vineeth N. Balasubramanian · PDF
  107. Unifying Vision-Language Latents for Zero-label Image Caption Enhancement

    Sanghyun Byun, Jung Ick Guack, Mohanad Odema, Baisub Lee, Jacob Song, Woo Seong Chung · PDF
  108. Universal Properties of Activation Sparsity in Modern Large Language Models

    Filip Szatkowski, Patryk Będkowski, Alessio Devoto, Jan Dubiński, Pasquale Minervini, Mikołaj Piórczyński, Simone Scardapane, Bartosz Wójcik · PDF
  109. Universally Converging Representations of Matter Across Scientific Foundation Models

    Sathya Edamadaka, Soojung Yang, Rafael Gomez-Bombarelli · PDF
  110. Unraveling the cognitive patterns of Large Language Models through module communities

    Kushal Raj Bhandari, Pin-Yu Chen, Jianxi Gao · PDF
  111. VISGate: ROI-Conditioned Dual-Head Encoders that Align Visual Features and Brain Responses

    Morteza Mahdiani, Ian Charest · PDF
  112. VQ-Kernels: Unraveling Deep Learning of High-Dimensional Data Geometry

    T Mitchell Roddenberry, Thomas Walker, Ronald R. Coifman, Richard Baraniuk, Randall Balestriero · PDF
  113. Weight Weaving: Parameter Pooling for Data-Free Model Merging

    Levy Chaves, Eduardo Valle, Sandra Avila · PDF
  114. Where does an LLM begin computing an instruction?

    Aditya Pola, Vineeth N. Balasubramanian · PDF
  115. Why and How Auxiliary Tasks Improve JEPA Representations

    Jiacan Yu, Siyi Chen, Mingrui Liu, Nono Horiuchi, Vladimir Braverman, Zicheng Xu, Dan Haramati, Randall Balestriero · PDF
  116. Windsock is Dancing: Adaptive Multimodal Retrieval-Augmented Generation

    Shu Zhao, Tianyi Shen, Nilesh Ahuja, Omesh Tickoo, Vijaykrishnan Narayanan · PDF