Plus de 80 articles affiliés à Mila acceptés à NeurIPS 2025

Plus de 80 articles de chercheur·euse·s affilié·e·s à Mila ont été acceptés à la conférence principale de NeurIPS 2025, la plus grande conférence de recherche en intelligence artificielle au monde.

Parmi ces publications, quinze ont reçu la mention de poster vedette (spotlight), dont une a été sélectionnée pour une présentation orale, un honneur réservé aux recherches les plus novatrices.

Voici les publications mises en valeur à NeurIPS 2025 comprenant au moins un·e auteur·e affilié·e à Mila. 

La liste entière des articles affiliés à Mila se trouve en bas de page.

Présentation orale

• State Entropy Regularization for Robust Reinforcement Learning by Yonatan Ashlag, Uri Koren, Mirco Mutti, Esther Derman, Pierre-Luc Bacon, Shie Mannor

Posters en vedette (spotlight)

Developper des IA robustes pour le monde réel

• THUNDER: Tile-level Histopathology image UNDERstanding benchmark by Pierre Marza, Leo Fillioux, Sofiène Boutaj, Kunal Mahatha, Christian Desrosiers, Pablo Piantanida, Jose Dolz, Stergios Christodoulidis, and Maria Vakalopoulou
• Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring by Yuyan Chen, Nico Lang, B. Christian Schmidt, Aditya Jain, Yves Basset, Sara Beery, Maxim Larrivée, David Rolnick

Comprendre la «boîte noire»

• Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning by Navita Goyal, Hal Daumé III, Alexandre Drouin, and Dhanya Sridhar
• Distributional Training Data Attribution: What do Influence Functions Sample? by Bruno Kacper Mlodozeniec, Isaac Reid, Samuel Power, David Krueger, Murat A Erdogdu, Richard E. Turner, Roger Baker Grosse
• Caption This, Reason That: VLMs Caught in the Middle by Zihan Weng, Lucas Gomez, Taylor Whittington Webb, and Pouya Bashivan

Avancées en apprentissage par renforcement

• State Entropy Regularization for Robust Reinforcement Learning by Yonatan Ashlag, Uri Koren, Mirco Mutti, Esther Derman, Pierre-Luc Bacon, Shie Mannor
• Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning by Roger Creus Castanyer, Johan Obando-Ceron, Lu Li, Pierre-Luc Bacon, Glen Berseth, Aaron Courville, and Pablo Samuel Castro
• Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs by Mehran Shakerinava, Siamak Ravanbakhsh, and Adam Oberman
• A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search by Arnav Kumar Jain, Vibhakar Mohta, Subin Kim, Atiksh Bhardwaj, Juntao Ren, Yunhai Feng, Sanjiban Choudhury, Gokul Swamy
• Plasticity as the Mirror of Empowerment by David Abel, Michael Bowling, André Barreto, Will Dabney, Shi Dong, Steven Hansen, Anna Harutyunyan, Khimya Khetarpal, Clare Lyle, Razvan Pascanu, Georgios Piliouras, Doina Precup, Jonathan Richens, Mark Rowland, Tom Schaul, Satinder Singh

Percées sur les modèles de diffusion

• Progressive Inference-Time Annealing of Diffusion Models by Tara Akhound-Sadegh, Jungyoon Lee, Avishek Joey Bose, Valentin De Bortoli, Arnaud Doucet, Michael M. Bronstein, Dominique Beaini, Siamak Ravanbakhsh, Kirill Neklyudov, and Alexander Tong
• Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning by Jaesik Yoon, Hyeonseo Cho, Yoshua Bengio, and Sungjin Ahn

Repousser les fondements de l'apprentissage automatique

• Dimension-adapted Momentum Outscales SGD by Damien Ferbach, Katie Everett, Gauthier Gidel, Elliot Paquette, and Courtney Paquette
• Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers by Florence Regol, Joseph Cotnareanu, Theodore Glavas, and Mark Coates
• On Traceability in 𝓵𝑝 Stochastic Convex Optimization by Sasha Voitovych, Mahdi Haghifam, Idan Attias, Gintare Karolina Dziugaite, Roi Livni, Daniel M. Roy

Liste complète des publications affiliées à Mila

Conférence principale

• Amortized Sampling with Transferable Normalizing Flows : Charlie B. Tan, Majdi Hassan, Leon Klein, Saifuddin Syed, Dominique Beaini, Michael M. Bronstein, Alexander Tong, Kirill Neklyudov
• Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection: Litao Li, Leo Song, Steven Ding, Benjamin C. M. Fung, Philippe Charland
• Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning: Navita Goyal, Hal Daumé III, Alexandre Drouin, Dhanya Sridhar
• Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation: Bailey Trang, Parham Saremi, Alan Q. Wang, Fangrui Huang, Zahra Tehrani Nasab, Amar Kumar, Tal Arbel, Li Fei-Fei, Ehsan Adeli
• From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization: Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger, Gintare Karolina Dziugaite, Michael Curtis Mozer, Eleni Triantafillou
• Generalizable, real-time neural decoding with hybrid state-space models: Avery Hee-Woon Ryoo, Nanda H Krishna, Ximeng Mao, Mehdi Azabou, Eva L Dyer, Matthew G Perich, Guillaume Lajoie
• Know Thyself by Knowing Others: Learning Neuron Identity from Population Context: Vinam Arora, Divyansha Lachi, Ian Jarratt Knight, Mehdi Azabou, Blake Aaron Richards, Cole Lincoln Hurwitz, Josh Siegle, Eva L Dyer
• LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs: Ran Li, Hao Wang, Chengzhi Mao
• ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training: Adel Nabli, Louis Fournier, Pierre ERBACHER, Louis Serrano, Eugene Belilovsky, Edouard Oyallon
• Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic Estimators: Lucas Berry, David Meger
• Learning Task-Agnostic Representations through Multi-Teacher Distillation: Philippe Formont, Maxime DARRIN, Banafsheh Karimian, Eric Granger, Jackie CK Cheung, Ismail Ben Ayed, Mohammadhadi Shateri, Pablo Piantanida
• Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers: Florence Regol, Joseph Cotnareanu, Theodore Glavas, Mark J. Coates
• System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts: Xiaoqiang Wang, Suyuchen Wang, Yun Zhu, Bang Liu
• Detecting High-Stakes Interactions with Activation Probes: Alex McKenzie, Urja Pawar, Phil Blandfort, William Bankes, David Krueger, Ekdeep Singh Lubana, Dmitrii Krasheninnikov
• Dimension-adapted Momentum Outscales SGD: Damien Ferbach, Katie Everett, Gauthier Gidel, Elliot Paquette, Courtney Paquette
• Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning: Roger Creus Castanyer, Johan Samir Obando Ceron, Li Li, Pierre-Luc Bacon, Glen Berseth, Aaron C. Courville, Pablo Samuel Castro
• Increasing the Utility of Synthetic Images through Chamfer Guidance: Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari Hemmat, Melissa Hall, Jakob Verbeek, Adriana Romero, Michal Drozdzal
• Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities: Tara Akhound-Sadegh, Jungyoon Lee, Avishek Joey Bose, Valentin De Bortoli, Arnaud Doucet, Michael M. Bronstein, Dominique Beaini, Siamak Ravanbakhsh, Kirill Neklyudov, Alexander Tong
• FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency: Yifei Su, Ning Liu, Dong Chen, Zhen Zhao, Kun Wu, Meng Li, Zhiyuan Xu, Zhengping Che, Jian Tang
• Adaptive Inference-Time Scaling via Cyclic Diffusion Search: Gyubin Lee, Bao N Nguyen Truong, Jaesik Yoon, Dongwoo Lee, Minsu Kim, Yoshua Bengio, Sungjin Ahn
• Tracing the representation geometry of language models from pretraining to post-training: Melody Zixuan Li, Kumar Krishna Agrawal, Arna Ghosh, Komal Kumar Teru, Adam Santoro, Guillaume Lajoie, Blake Aaron Richards
• Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning: Jiashun Liu, Zihao Wu, Johan Samir Obando Ceron, Pablo Samuel Castro, Aaron C. Courville, Ling Pan
• Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation: Sangmin Bae, Yujin Kim, Reza Bayat, Sungnyun Kim, Jiyoun Ha, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Aaron C. Courville, Se-Young Yun
• Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training: Brian R. Bartoldson, Siddarth Venkatraman, James Diffenderfer, Moksh Jain, Tal Ben-Nun, Seanie Lee, Minsu Kim, Johan Samir Obando Ceron, Yoshua Bengio, Bhavya Kailkhura
• Entropy Rectifying Guidance for Diffusion and Flow Models: Tariq Berrada, Adriana Romero, Michal Drozdzal, Jakob Verbeek, Karteek Alahari
• The Promise of RL for Autoregressive Image Editing: Saba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodriguez, Sai Rajeswar, Siva Reddy, Christopher Pal, Benno Krojer, Aishwarya Agrawal
• Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning: Jaesik Yoon, Hyeonseo Cho, Yoshua Bengio, Sungjin Ahn
• Energy Loss Functions for Physical Systems: Sékou-Oumar Kaba, Kusha Sareen, Daniel Levy, Siamak Ravanbakhsh
• RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis: Robin Yadav, Qi Yan, Guy Wolf, Avishek Joey Bose, Renjie Liao
• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding: Ahmed Masry, Juan A. Rodriguez, Tianyu Zhang, Suyuchen Wang, Chao Wang, Aarash Feizi, Akshay Kalkunte Suresh, Abhay Puri, Xiangru Jian, Pierre-Andre Noel, Sathwik Tejaswi Madhusudhan, Marco Pedersoli, Bang Liu, Nicolas Chapados, Yoshua Bengio, Enamul Hoque, Christopher Pal, Issam Hadj Laradji, David Vazquez, Perouz Taslakian, Spandana Gella, Sai Rajeswar
• Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks: Gavin McCracken, Gabriela Moisescu-Pareja, Vincent Létourneau, Doina Precup, Jonathan Love
• Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning: Yash Jhaveri, Harley Wiltzer, Patrick Shafto, Marc G. Bellemare, David Meger
• State Entropy Regularization for Robust Reinforcement Learning: Yonatan Ashlag, Uri Koren, Mirco Mutti, Esther Derman, Pierre-Luc Bacon, Shie Mannor
• FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks: Luca Della Libera, Francesco Paissan, Yusuf Cem Sübakan, Mirco Ravanelli
• POCO: Scalable Neural Forecasting through Population Conditioning: Yu Duan, Hamza Tahir Chaudhry, Misha B. Ahrens, Christopher D Harvey, Matthew G Perich, Karl Deisseroth, Kanaka Rajan
• Distributional Training Data Attribution: What do Influence Functions Sample?: Bruno Mlodozeniec, Isaac Reid, Samuel Power, David Krueger, Murat A Erdogdu, Richard E. Turner, Roger Baker Grosse
• Understanding Adam Requires Better Rotation Dependent Assumptions: Tianyue H. Zhang, Lucas Maes, Alan Milligan, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Damien Scieur, Simon Lacoste-Julien, Charles Guille-Escuret
• Caption This, Reason That: VLMs Caught in the Middle: Zihan Weng, Lucas Gomez, Taylor Whittington Webb, Pouya Bashivan
• Object-centric Binding in Contrastive Language-Image Pretraining: Rim Assouel, Pietro Astolfi, Florian Bordes, Michal Drozdzal, Adriana Romero
• Seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models: Hafez Ghaemi, Eilif Benjamin Muller, Shahab Bakhtiari
• TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses: Sahar Dastani, Ali Bahri, Gustavo Adolfo Vargas Hakim, Moslem Yazdanpanah, Mehrdad Noori, David Osowiechi, Samuel Barbeau, Ismail Ben Ayed, Herve Lombaert, Christian Desrosiers
• Plasticity as the Mirror of Empowerment: David Abel, Michael Bowling, Andre Barreto, Will Dabney, Shi Dong, Steven Stenberg Hansen, Anna Harutyunyan, Khimya Khetarpal, Clare Lyle, Razvan Pascanu, Georgios Piliouras, Doina Precup, Jonathan Richens, Mark Rowland, Tom Schaul, Satinder Singh
• How to Train Your LLM Web Agent: A Statistical Diagnosis: Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza, Hadi Nekoei, Thibault Le Sellier de Chezelles, Megh Thakkar, Nicolas Gontier, Miguel Muñoz-Mármol, Sahar Omidi Shayegan, Stefania Raimondo, Xue Liu, Alexandre Drouin, Alexandre Piché, Laurent Charlin, Alexandre Lacoste, Massimo Caccia
• Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs: Mehran Shakerinava, Siamak Ravanbakhsh, Adam Oberman
• Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention: Zhihao Zhan, Jianan Zhao, Zhaocheng Zhu, Jian Tang
• Tight Lower Bounds and Improved Convergence in Performative Prediction: Pedram Khorsandi, Rushil Gupta, Mehrnaz Mofakhami, Simon Lacoste-Julien, Gauthier Gidel
• Planning and Learning in Average Risk-aware MDPs: Weikai Wang, Erick Delage
• Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery: Mélisande Teng, Arthur Ouaknine, Etienne Laliberté, Yoshua Bengio, David Rolnick, Hugo Larochelle
• On Traceability in $\ell_p$ Stochastic Convex Optimization: Sasha Voitovych, MAHDI HAGHIFAM, Idan Attias, Gintare Karolina Dziugaite, Roi Livni, Daniel M. Roy
• Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models: Nicolas Roux, Bellemare Marc-Emmanuel, Jonathan Lebensold, Arnaud Bergeron, Joshua Greaves, Alexandre Fréchette, Carolyne Pelletier, Eric Thibodeau-Laufer, Sándor Tóth, Sam Work
• Rendering-Aware Reinforcement Learning for Vector Graphics Generation: Juan A. Rodriguez, Haotian Zhang, Abhay Puri, Rishav Pramanik, Aarash Feizi, Pascal Wichmann, Arnab Kumar Mondal, Mohammad Reza Samsami, Rabiul Awal, Perouz Taslakian, Spandana Gella, Sai Rajeswar, David Vazquez, Christopher Pal, Marco Pedersoli
• Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models: Vineet Jain, Kusha Sareen, Mohammad Pedramfar, Siamak Ravanbakhsh
• Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models: Samuel Lavoie, Michael Noukhovitch, Aaron C. Courville
• Learning to Solve Complex Problems via Dataset Decomposition: Wanru Zhao, Lucas Caccia, Zhengyan Shi, Minseon Kim, Weijia Xu, Xingdi Yuan, Alessandro Sordoni, Marc-Alexandre Côté
• Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision: Chenshuang Zhang, Kang Zhang, Joon Son Chung, In So Kweon, Junmo Kim, Chengzhi Mao
• Discovering Data Structures: Nearest Neighbor Search and Beyond: Omar Salemohamed, Laurent Charlin, Shivam Garg, Vatsal Sharan, Gregory Valiant
• SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents: Wanxin Tian, Shijie Zhang, Kevin Zhang, Xiaowei Chi, Chun-Kai Fan, Junyu Lu, Yulin Luo, Qiang Zhou, Yiming Zhao, Ning Liu, Siyu Lin, Zhiyuan Qin, Xiaozhu Ju, Shanghang Zhang, Jian Tang
• Geometry-Aware Edge Pooling for Graph Neural Networks: Katharina Limbeck, Lydia Mezrag, Guy Wolf, Bastian Rieck
• Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning: Ghada Sokar, Pablo Samuel Castro
• C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning: Antonios Valkanas, Soumyasundar Pal, Pavel Rumiantsev, Yingxue Zhang, Mark J. Coates
• Causal Climate Emulation with Bayesian Filtering: Sebastian Hickman, Ilija Trajković, Julia Kaltenborn, Francis Pelletier, Alexander T Archibald, Yaniv Gurwicz, Peer Nowack, David Rolnick, Julien Boussard
• A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search: Arnav Kumar Jain, Vibhakar Mohta, Subin Kim, Atiksh Bhardwaj, Juntao Ren, Yunhai Feng, Sanjiban Choudhury, Gokul Swamy
• Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference: Stephen Zhao, Aidan Li, Rob Brekelmans, Roger Grosse
• From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers: Praneet Suresh, Jack Stanley, Sonia Joseph, Luca Scimeca, Danilo Bzdok
• Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments: Riley Simmons-Edler, Ryan P Badman, Felix Baastad Berg, Raymond Chua, John J Vastola, Joshua Lunger, William Qian, Kanaka Rajan
• REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects: Yassine El Ouahidi, Jonathan Lys, Philipp Thölke, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon, Karim Jerbi, Giulia Lioi
• Scalable and Cost-Efficient de Novo Template-Based Molecular Generation: Piotr Gaiński, Oussama Boussif, Andrei Rekesh, Dmytro Shevchuk, Ali Parviz, Mike Tyers, Robert A. Batey, Michał Koziarski
• Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization: Andrés Guzmán-Cordero, Felix Dangel, Gil Goldshlager, Marius Zeinhofer
• PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion: Linlian Jiang, Rui Ma, Li Gu, Ziqiang Wang, Xinxin Zuo and Yang Wang
• New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results: Francesco Orabona, Ryan D'Orazio
• Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction: Nadhir Hassen, Zhen Zhang, Johan W. Verjans
• Majority of the Bests: Improving Best-of-N via Bootstrapping: Amin Rakhsha, Kanika Madan, Tianyu Zhang, Amir-massoud Farahmand, Amir Khasahmadi
• Random Forest Autoencoders for Guided Representation Learning: Adrien Aumon, Shuang Ni, Myriam Lizotte, Guy Wolf, Kevin R. Moon, Jake S. Rhodes
• Dimensionality Mismatch Between Brains and Artificial Neural Networks: Santiago Galella, Maren Wehrheim, Matthias Kaschube
• PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning: Mingqi Wu · Qiang Sun · Archer Yang

Dataset and Benchmark Track

• MiNT: Multi-Network Transfer Benchmark for Temporal Graph Learning: Kiarash Shamsi, Tran Gia Bao Ngo, Razieh Shirzadkhani, Shenyang Huang, Farimah Poursafaei, Poupak Azad, Reihaneh Rabbany, Baris Coskunuzer, Guillaume Rabusseau, Cuneyt Gurcan Akcora
• Meta-World+: An Improved, Standardized, RL Benchmark: Reginald McLean, Evangelos Chatzaroulas, Luc McCutcheon, Frank Röder, Tianhe Yu, Zhanpeng He, K.R. Zentner, Ryan Julian, J K Terry, Isaac Woungang, Nariman Farsad, Pablo Samuel Castro
• NAVIX: Scaling MiniGrid Environments with JAX: Eduardo Pignatelli, Jarek Luca Liesen, Robert Tjarko Lange, Chris Lu, Pablo Samuel Castro, Laura Toni
• GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction: Eya Cherif, Arthur Ouaknine, Luke A. Brown, Phuong D. Dao, Kyle R Kovach, Bing Lu, Daniel Mederer, Hannes Feilhauer, Teja Kattenborn, David Rolnick
• Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring: Yuyan Chen, Nico Lang, B. Christian Schmidt, Aditya Jain, Yves Basset, Sara Beery, Maxim Larrivée, David Rolnick
• THUNDER: Tile-level Histopathology image UNDERstanding benchmark: Pierre Marza, Leo Fillioux, Sofiène Boutaj, KUNAL MAHATHA, Christian Desrosiers, Pablo Piantanida, Jose Dolz, Stergios Christodoulidis, Maria Vakalopoulou
• OpenLex3D: A Tiered Benchmark for Open-Vocabulary 3D Scene Representations: Christina Kassab, Sacha Morin, Martin Büchner, Matias Mattamala, Kumaraditya Gupta, Abhinav Valada, Liam Paull, Maurice Fallon
• Generating Creative Chess Puzzles: Xidong Feng, Vivek Veeriah, Marcus Chiam, Michael D Dennis, Federico Barbero, Johan Obando-Ceron, Jiaxin Shi, Satinder Singh, Shaobo Hou, Nenad Tomasev, Tom Zahavy

Position Paper Track

• Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor: Alexandra Olteanu, Su Lin Blodgett, Agathe Balayn, Angelina Wang, Fernando Díaz, Flavio Calmon, Margaret Mitchell, Michael Ekstrand, Reuben Binns, Solon Barocas
• Neither Valid Nor Reliable? Investigating the Use of LLMs as Judges: Khaoula Chehbouni, Mohammed Haddou, Jackie CK Cheung, Golnoosh Farnadi

Competition Paper Track

• The 2025 PNPL competition: Speech detection and phoneme classification in the LibriBrain dataset: Gilad Landau, Miran Özdogan, Gereon Elvers, Francesco Mantegna, Pratik Somaiya, Dulhan Jayalath, Luisa Kurth, Teyun Kwon, Brendan Shillingford, Greg Farquhar, Minqi Jiang, Karim Jerbi, Hamza Abdelhedi, Yorguin Mantilla Ramos, Caglar Gulcehre, Mark Woolrich, Natalie Voets, Oiwi Parker Jones

Workshops

• DeLLMphi: A Multi-Turn Method for Multi-Agent Forecasting: Andrew Robert Williams, Martin Weiss, Victoria Feere, Nasim Rahaman, Hugo Larochelle
• A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy: Maxime Heuillet, Rishika Bhagwatkar, Jonas Ngnawe, Yann Batiste Pequignot, Alexandre Larouche, Christian Gagné, Irina Rish, Ola Ahmad, Audrey Durand
• Higher-order Component Attribution via Kolmogorov-Arnold Networks: Samy Mammeri, Christian Gagné
• Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling: Jonas Ngnawe, Maxime Heuillet, Sabyasachi Sahoo, Yann Batiste Pequignot, Frederic Precioso, Christian Gagné
• WebArena Verified: Reliable Evaluation for Web Agents: Amine El hattami, Megh Thakkar, Nicolas Chapados, Christopher Pal
• Consistent Synthetic Sequences Unlock Structural Diversity in Fully Atomistic De Novo Protein Design: Danny Reidenbach, Zhonglin Cao, Zuobai Zhang, Kieran Didi, Tomas Geffner, Guoqing Zhou, Jian Tang, Christian Dallago, Arash Vahdat, Emine Kucukbenli, Karsten Kreis
• Benchmarking Machine Learning Potentials for Crystal Structure Relaxation: Kowen Woo, Prashant Govindarajan, A. Chandar
• How to Get Your LLM to Generate Challenging Problems for Evaluation: Arkil Patel, Siva Reddy, Dzmitry Bahdanau
• Beyond Naive Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs: Arjun Ashok, Andrew Robert Williams, Vincent Zhihao Zheng, Irina Rish, Nicolas Chapados, Étienne Marcotte, Valentina Zantedeschi, Alexandre Drouin
• FEval-TTC: Fair Evaluation Protocol for Test-Time Compute: Pavel Rumiantsev, Soumyasundar Pal, Yingxue Zhang, Mark J. Coates
• Why all roads don't lead to Rome: Representation geometry varies across the human visual cortical hierarchy: Arna Ghosh, Zahraa Chorghay, Shahab Bakhtiari, Blake Aaron Richards
• Inferring dynamical features from neural data through joint learning of latents factors and weights: Anirudh Gururaj Jamkhandi, Ali Korojy, Olivier Codol, Guillaume Lajoie, Matthew G Perich
• Self-Supervised Learning from Structural Invariance: Yipeng Zhang, Hafez Ghaemi, Jungyoon Lee, Laurent Charlin
• Measure Before You Look: Grounding Embeddings Through Manifold Metrics: César Miguel Valdez Córdova, Matthew Scicluna, Shuang Ni, Smita Krishnaswamy, Simon Gravel, Guy Wolf
• Reasoning with Preference Constraints: A Benchmark for Language Models in Many-to-One Matching Markets: Marylou Fauchard, Florian Carichon, Margarida Carvalho, Golnoosh Farnadi
• Are Large Language Models Good Temporal Graph Learners?: Shenyang Huang, Ali Parviz, Emma Kondrup, Zachary Yang, Zifeng Ding, Michael M. Bronstein, Reihaneh Rabbany, Guillaume Rabusseau
• Towards Democratizing LLMs: Investigating Multilingual Mixture-of-Experts Models: Aditi Khandelwal, Marius Mosbach, Verna Dankers, Siva Reddy, Golnoosh Farnadi
• Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models: Istabrak Abbes, Gopeshh Subbaraj, Matthew D Riemer, Nizar Islah, Benjamin Thérien, Tsuguchika Tabaru, Hiroaki Kingetsu, A. Chandar, Irina Rish
• Intrinsic Meets Extrinsic Fairness: Assessing the Downstream Impact of Bias Mitigation in Large Language Models: Mina Arzaghi, Alireza Dehghanpour Farashah, Florian Carichon, Golnoosh Farnadi
• AInstein: Can AI Rediscover Scientific Concepts from First Principles?: Shambhavi Mishra, Gaurav Sahu, Marco Pedersoli, Laurent Charlin, Jose Dolz, Christopher Pal
• Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework: Clea Chataigner, Rebecca Ma, Prakhar Ganesh, Afaf Taïk, Elliot Creager, Golnoosh Farnadi
• Unifying Mechanistic Interpretations of Neural Networks Trained on Modular Addition: Gabriela Moisescu-Pareja, Gavin McCracken, Vincent Létourneau, Doina Precup, Jonathan Love
• Conditional Adversarial Random Forest for Synthetic Electronic Health Record Generation: Cynthia Garcia Ybarra, Christian Gagné
• Reward the Reward Designer: Making Reinforcement Learning Useful for Clinical Decision Making: Sumana Basu, Adriana Romero, Doina Precup
• CrediBench: Building Web-Scale Network Datasets for Information Integrity: Emma Kondrup, Sebastian Sabry, Hussein Abdallah, Zachary Yang, James Zhou, Kellin Pelrine, Jean-François Godbout, Michael M. Bronstein, Reihaneh Rabbany, Shenyang Huang
• Graph Dreamer: Temporal Graph World Models for Sample-Efficient and Generalisable Reinforcement Learning: Anaïs Berkes, Donna Vakalis, Yoshua Bengio, David Rolnick
• Towards a generalizable, unified framework for multimodal neural decoding: Nanda H Krishna, Mathys Loiselle, Avery Hee-Woon Ryoo, Matthew G Perich, Guillaume Lajoie
• Accelerated Inorganic Materials Design with Generative AI Agents: Izumi Takahara, Teruyasu Mizoguchi, Bang Liu
• Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study: Lena Podina, Alex Hernandez-Garcia, Christina Humer, Alexandre AGM Duval, Victor Schmidt, Ali Ramlaoui, Shahana Chatterjee, Yoshua Bengio, David Rolnick, Félix Therrien
• Concept-based Steering of Large Language Models for Conditional Molecular Generation: Jeremy Qin, Rushil Gupta, Boris Knyazev, Yang Zhang, Glen Berseth, Bang Liu
• Context-Aware World Models for Task Agnostic Control: Busra Tugce Gurbuz, Hafez Ghaemi, Christopher Pack, Shahab Bakhtiari, Eilif Muller
• A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search: Arnav Kumar Jain, Vibhakar Mohta, Subin Kim, Atiksh Bhardwaj, Juntao Ren, Yunhai Feng, Sanjiban Choudhury, Gokul Swamy
• Transformer Embeddings for Fast Microlensing Inference: Nolan Smyth, Laurence Perreault-Levasseur, Yashar Hezaveh
• Neural Deprojection of Galaxy Stellar Mass Profiles: M. J. Yantovski-Barth, Hengyue Zhang, Nolan Smyth, Connor Stone, Yashar Hezaveh, Laurence Perreault-Levasseur, Martin Bureau
• Object-Centric Agentic Robot Policies: Sacha Morin, Kumaraditya Gupta, Mahtab Sandhu, Charlie Gauthier, Francesco Argenziano, Kirsty Ellis, Liam Paull
• Influence Functions for Efficient Data Selection in Reasoning: Prateek Humane, Paolo Cudrano, Daniel Z. Kaplan, Matteo Matteucci, Supriyo Chakraborty, Irina Rish
• Irresponsible AI: big tech's influence on AI research and associated impacts: Alex Hernández-García, Alexandra Volokhova, Ezekiel Williams, Dounia Shaaban Kabakibo
• Relative Trajectory Balance is equivalent to Trust-PCL: Tristan Deleu, Padideh Nouri, Yoshua Bengio, Doina Precup
• Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control: Thomas Jiralerspong, Berton Earnshaw, Jason Hartford, Yoshua Bengio, Luca Scimeca
• On Fairness of Task Arithmetic: The Role of Task Vectors: Laura Gomezjurado Gonzalez , Hiroki Naganuma, Kotaro Yoshida, Takafumi Horie, Yuji Naraki, Ryotaro Shimizu
• Dense Backpropagation Improves Training for Sparse Mixture-of-Experts: Ashwinee Panda, Vatsal Baherwani, Zain Sarwar, Benjamin Thérien, Sambit Sahu, Tom Goldstein, Supriyo Chakraborty
• Lyapunov–function-based framework for smooth strongly convex strongly concave min–max optimization algorithms: Mansi Rankawat, Damien Scieur, Simon Lacoste-Julien
• Fixed-Order Lexicographic Optimization via the lambda-ladder Exponential Loss: Diego Calanzone & Arielle Gazze, Pierre-Luc Bacon
• DStruct2Design: Data Structure Driven Generative Floor Plan Design via RLVR: Luis Lara, ZhiHao Luo, Aristides Milios, Aditya Sharma, Ge Ya Luo, Christopher Beckham, Florian Golemo, Christopher Pal
• Cross-Temporal Attention Fusion (CTAF) for Multimodal Physiological Signals in Self-Supervised Learning: Arian Khorasani, Théophile Demazure
• The Promise of RL for Autoregressive Image Editing: Saba Ahmadi, Rabiul Awal, Ankur Sikarwar, Amirhossein Kazemnejad, Ge Ya Luo, Juan A. Rodriguez, Sai Rajeswar, Siva Reddy, Christopher Pal, Benno Krojer, Aishwarya Agrawal
• Aligning Compound AI Systems via System-level DPO: Xiangwen Wang, Yibo Jacky Zhang, Zhoujie Ding, Katherine Tsai, Haolun Wu, Sanmi Koyejo
• An Empirical Study of Task and Feature Correlations in the Reuse of Pre-trained Models: Jama Hussein Mohamud, Willie Brink
• FACTS: Fast, Accurate, and Privacy-Compliant Table Summarization via Offline Template Generation: Ye Yuan, Mohammad Amin Shabani, Siqi Liu
• The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLMs: Nikolaus Howe, Micah Carroll
• A Probabilistic U-Net Approach to Downscaling Climate Simulations: Maryam Alipourhajiagha, Pierre-Louis Lemaire, Youssef Diouane, Julie Carreau
• Localized-Attention-Guided Concept Erasure for Text-to-Image Diffusion Models: Zhuan Shi, Alireza Dehghanpour Farashah, Rik de Vries, Golnoosh Farnadi
• Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models: Gabriel Missael Barco, Ronan Legin, Connor Stone, Yashar Hezaveh, Laurence Perreault-Levasseur
• Long-Horizon Model-Based Offline Reinforcement Learning Without Conservatism: Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
• MIRA: A Score for Conditional Distribution Accuracy and Model Comparison: Sammy Sharief, Justine Zeghal, Gabriel Missael Barco, Pablo Lemos, Yashar Hezaveh, Laurence Perreault-Levasseur
• Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts: Maxime Heuillet, Yufei Cui, Boxing Chen, Audrey Durand, Prasanna Parthasarathi
• VISGate: ROI-Conditioned Dual-Head Encoders that Align Visual Features and Brain Responses: Morteza Mahdiani, Ian Charest
• Towards Robust Unroll Generalization in Learned Optimizers: Xiaolong Huang, Benjamin Thérien, Eugene Belilovsky
• Design and Analysis of Accelerated Algorithms for Temporal Difference Learning using Dynamical Systems: Anushree Rankawat, Pierre-Luc Bacon
• torchgfn: A PyTorch GFlowNet library: Joseph D Viviano, Omar G. Younis, Sanghyeok Choi, Victor Schmidt, Yoshua Bengio, Salem Lahlou
• Inference of Star Formation and Metallicity Histories from Galaxy Spectra with Score-Based Models: Sacha Perry-Fagant, Connor Stone, Yashar Hezaveh, Laurence Perreault-Levasseur
• Multiscale Neural PDE Surrogates for Prediction and Downscaling: Application to Ocean Currents: Abdessamad El Kabid, Loubna Benabbou, Redouane Lguensat, Alex Hernández-García
• Multi-Representation Attention Framework for Underwater Bioacoustic Denoising and Recognition: Amine Razig, Youssef Soulaymani, Loubna Benabbou, Pierre Cauchy
• On the Geometry and Topology of Neural Circuits for Modular Addition: Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer, Colin Daniels, Vincent Létourneau, Jonathan Love
• The Representations of Deep Neural Networks Trained on Dihedral Group Multiplication: Gavin McCracken, Sihui Wei, Gabriela Moisescu-Pareja, Harley Wiltzer, Jonathan Love
• LeMat-GenBench: Bridging the gap between crystal generation and materials discovery: Alexandre Duval, Siddharth Betala, Samuel P. Gleason, Andy Xu, Georgia Channing, Daniel Levy, Ali Ramlaoui, Clémentine Fourrier, Chaitanya K. Joshi, Nikita Kazeev, Sékou-Oumar Kaba, Félix Therrien, Alex Hernández-García, Rocío Mercado, N M Anoop Krishnan