From July 6 to July 11, 2026, dozens of Mila researchers will attend the Forty-Third International Conference on Machine Learning (ICML 2026) in Seoul, South Korea. This year, they will share 82 scientific papers at the main conference and dozens more during workshops, showcasing their groundbreaking AI research to peers from all around the world.
Here is a list of papers accepted at ICML 2026 that contain at least one Mila-affiliated author:
Spotlight (Top 2% of accepted papers at ICML)
- A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots - Vincent Guan, Lazar Atanackovic, Kirill Neklyudov
- Autoregressive Boltzmann Generators - Danyal Rehman, Charlie Tan, Yoshua Bengio, Joey Bose, Alexander Tong
- MIRA: A Score for Conditional Distribution Accuracy and Model Comparison - Sammy Sharief, Justine Zeghal, Gabriel Missael Barco, Pablo Lemos, Yashar Hezaveh, Laurence Perreault-Levasseur
- OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration - Shaobo Wang, Xuan Ouyang, Tianyi Xu, Yuzheng Hu, Jialin Liu, Guo Chen, Tianyu Zhang, Junhao Zheng, Kexin Yang, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang
- Position: Irresponsible AI: big tech’s influence on AI research and associated impacts - Alex Hernandez-Garcia, Alexandra Volokhova, Ezekiel Williams, Dounia Shaaban Kabakibo, Mélisande Teng
- Position: Modular Memory is the Key to Continual Learning Agents - Vaggelis Dorovatas, Malte Schwerin, Andrew Bagdanov, Lucas Caccia, Antonio Carta, Laurent Charlin, CITEC Barbara Hammer, Tyler Hayes, Timm Hess, Christopher Kanan, Dhireesha Kudithipudi, Xialei Liu, Vincenzo Lomonaco, Jorge Mendez-Mendez, Darshan Patil, Ameya Pandurang Prabhu, Elisa Ricci, Tinne Tuytelaars, Gido M van de Ven, Liyuan Wang, Joost van de Weijer, Jonghyun Choi, Martin Mundt, Rahaf Aljundi
- Recurrent Structural Policy Gradient for Partially Observable Mean Field Games - Clarisse Wibault, Sebastian Towers, Tiphaine Wibault, Juan Duque, Johannes Forkel, George Whittle, Andreas Schaab, Chiyuan Wang, Yucheng Yang, Michael A Osborne, Benjamin Moll, Jakob Foerster
- Reinforced Sequential Monte Carlo for Amortised Sampling - Sanghyeok Choi, Sarthak Mittal, Víctor Elvira, Jinkyoo Park, Esmeralda S. Whitammer
- Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity - Aneri Muni, Vincent Taboga, Esther Derman, Pierre-Luc Bacon, Erick Delage
- Stable Deep Reinforcement Learning via Isotropic Gaussian Representations - Ali Saheb pasand, Johan Obando-Ceron, Aaron Courville, Pouya Bashivan, Pablo Samuel Castro
- TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior - Gül Sena Altıntaş, Malikeh Ehghaghi, Brian Lester, Fengyuan Liu, Wanru Zhao, Marco Ciccone, Colin Raffel
- Training Diffusion Language Models for Black-Box Optimization - Zipeng Sun, Can Chen, Ye Yuan, Haolun Wu, Jiayao Gu, Christopher Pal, Xue Liu
- What Makes Value Learning Efficient in Residual Reinforcement Learning? Guozheng Ma, Lu Li, Haoyu Wang, Zixuan Liu, Pierre-Luc Bacon, Dacheng Tao
Main Conference
- Privileged Information Distillation for Language Models - Emiliano Penaloza, Dheeraj Vattikonda, Nicolas Gontier, Alexandre Lacoste, Laurent Charlin, Massimo Caccia
- Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions - Matthew Riemer, Tommaso Tosato, Maximilian Puelma Touzel, Amin Memarian, Guillaume Dumas, Glen Berseth, Irina Rish
- Position: Benchmarks for Vision–Language Models in Urban Perception Should Be Reliability-Aware and Negotiated - Rashid Mushkani
- Operationalizing the Superficial Alignment Hypothesis via Task Complexity - Tomás Vergara Browne, Darshan Patil, Ivan Titov, Siva Reddy, Tiago Pimentel, Marius Mosbach
- Privileged Information Distillation for Language Models - Emiliano Penaloza, Dheeraj Vattikonda, Nicolas Gontier, Alexandre Lacoste, Laurent Charlin, Massimo Caccia
- PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling - Xinyu Yuan, Xixian Liu, Ya Shi Zhang, Zuobai Zhang, Hongyu Guo, Jian Tang
- Deep neural networks divide and conquer dihedral multiplication - Sihui Wei, Gavin McCracken, Gabriela Moisescu-Pareja, Harley Wiltzer, Doina Precup, Irina Rish, Jonathan Love
- Position: Time to Close The Validation Gap in LLM Social Simulations - Maximilian Puelma Touzel, Sneheel Sarangi, Aurélien Bück-Kaeffer, Zachary Yang, Jean-François Godbout, Reihaneh Rabbany
- MuLoCo: Muon is a Practical Inner Optimizer for DiLoCo - Benjamin Thérien, Xiaolong Huang, Aaron Defazio, Irina Rish, Eugene Belilovsky
- Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent - Hiroki Naganuma, Shagun Gupta, Youssef Briki, Ioannis Mitliagkas, Irina Rish, Parameswaran Raman, Hao-Jun Shi
- LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs - Benno Krojer, Perampalli Shravan Nayak, Oscar Mañas, Vaibhav Adlakha, Desmond Elliott, Siva Reddy, Marius Mosbach
- Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data - Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite, Ioannis Mitliagkas
- From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging - Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite
- Grokking Finite-Dimensional Algebra - Pascal Jr Tikeng Notsawo, Guillaume Dumas, Guillaume Rabusseau
- Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization? - Semih Cantürk, Thomas Sabourin, Frederik Wenkel, Michael Perlmutter, Guy Wolf
- Stabilizing Native Low-Rank LLM Pretraining - Paul Janson, Edouard Oyallon, Eugene Belilovsky
- Dynamics and representation structure of local approximations to gradient-based learning in linear recurrent neural networks - Ezekiel Williams, Alexandre Payeur, Guillaume Lajoie
- Inverting Data Transformations via Diffusion Sampling - Jinwoo Kim, Sékou-Oumar Kaba, Jiyun Park, Seunghoon Hong, Siamak Ravanbakhsh
- Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization - Yonghan Yang, Ye Yuan, Zipeng Sun, Linfeng Du, Bowei He, Haolun Wu, Can Chen, Xue Liu
- Position: Causality is Key for Interpretability Claims to Generalise - Shruti Joshi, Aaron Mueller, David Klindt, Wieland Brendel, Dhanya Sridhar, Patrik Reizinger
- DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone - Vaibhav Singh, Oleksiy Ostapenko, Pierre-André Noël, Eugene Belilovsky, Torsten Scholak
- Accelerated and Stable Convergence with Anchored Generalized Optimistic Method - Motahareh Sohrabi, Jianxin You, Simon Lacoste-Julien, Eduard Gorbunov, Gauthier Gidel
- Position: Prompts for Public-Sector LLMs Should Be Governed as Commons - Rashid Mushkani
- A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness - Leo Schwinn, Moritz Ladenburger, Tim Beyer, Mehrnaz Mofakhami, Gauthier Gidel, Stephan Günnemann
- Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models - Zhilong Zhang, Haoxiang Ren, Yihao Sun, Yifei Sheng, Haonan Wang, Zhichao Wu, Haoxin Lin, Pierre-Luc Bacon, Yang Yu
- The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning - Donghang Wu, Tianyu Zhang, Yuxin Li, Hexin Liu, Chen Chen, EngSiong Chng, Yoshua Bengio
- Position: LLM-Safety Evaluations Lack Robustness - Tim Beyer, Sophie Xhonneux, Simon Geisler, Gauthier Gidel, Leo Schwinn, Stephan Günnemann
- Active Attacks: Red-teaming LLMs via Adaptive Environments - Taeyoung Yun, Pierre-Luc St-Charles, Jinkyoo Park, Yoshua Bengio, Minsu Kim
- On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning - Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau, Sebastien Lachapelle
- PGT: Procedurally Generated Tasks for improving fine-grained understanding in MLLMs - Rim Assouel, Amir Bar, Michal Drozdzal, Adriana Romero-Soriano
- Learning from Pairwise Preferences in Long-Term Decision Problems - Jonathan Colaco Carr, Prakash Panangaden, Doina Precup, Benjamin Van Roy
- Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection - Fatemeh Pesaran zadeh, Seyeon Choi, Xing Han Lù, Siva Reddy, Gunhee Kim
- Localized, High-resolution Geographic Representations with Slepian Functions - Arjun Rao, Ruth Crasto, Tessa Ooms, David Rolnick, Konstantin Klemmer, Marc Rußwurm
- Balancing plasticity and stability with Fast and Slow Successor Features - Raymond Chua, Doina Precup, Blake Richards
- At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization - Praneet Suresh, Jack Stanley, Sonia Joseph, Luca Scimeca, Danilo Bzdok
- Quantifying LLM Attention-Head Stability: Implications for Circuit Universality - Karan Bali, Jack Stanley, Praneet Suresh, Danilo Bzdok
- When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents - Jaylen Jones, Zhehao Zhang, Yuting Ning, Eric Fosler-Lussier, Pierre-Luc St-Charles, Yoshua Bengio, Dawn Song, Yu Su, Huan Sun
- Conditionally Site-Independent Neural Evolution of Antibody Sequences - Stephen Lu, Aakarsh Vermani, Kohei Sanno, Jiarui Lu, Frederick Matsen, Milind Jagota, Yun Song
- V1: Unifying Generation and Self-Verification for Parallel Reasoners - Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia (Shirley) Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki, Rishabh Tiwari, Long (Tony) Lian, Yucheng Lu, Boyi Li, Alane Suhr, Ben Athiwaratkun, Kurt Keutzer
- Interpreting Physics in Video World Models - Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake Richards, Michael Rabbat
- Benchmarking World-Model Learning with Environment-Level Queries - Archana Warrier, Dat Nguyen, Michelangelo Naim, Moksh Jain, Yichao Liang, Karen Schroeder, Cambridge Yang, Josh Tenenbaum, Sebastian Vollmer, Kevin Ellis, Zenna Tavares
- Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning - Yivan Zhang, Ziyan Luo, Manuel Baltieri
- Attention with Routed-Memory for Learnable Sparse Control - QIUHAO Zeng, Jerry Huang, Peng Lu, Ruiyi Fang, Gezheng Xu, Zihao Jing, Yufei Cui, Charles X. Ling, Gang Niu, Boyu Wang
- Position: Interpretability Can Be Actionable - Hadas Orgad, Fazl Barez, Tal Haklay, Isabelle Lee, Marius Mosbach, Anja Reusch, Naomi Saphra, Byron Wallace, Sarah Wiegreffe, Eric Wong, Ian Tenney, Mor Geva
- From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax Optimization - Mansi Rankawat, Michael Muehlebach, Simon Lacoste-Julien, Damien Scieur
- Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation - Zhichao Wu, Junyin Ye, Zhilong Zhang, Yihao Sun, Haoxin Lin, Jiaheng Luo, Haoxiang Ren, lei yuan, Yang Yu
- EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings - Shiva Malay, Perampalli Shravan Nayak, Sagar Davasam, Srinivas Sunkara, Sai Rajeswar Mudumba
- Discovering Differences in Strategic Behavior between Humans and LLMs - Caroline L Wang, Daniel Kasenberg, Kimberly Stachenfeld, Pablo Samuel Castro
- Position: Preparing for AI Systems That Deceive Developers - Fengyu Duan, Xudong Pan, Yawen Duan, Adam Gleave, Ranjie Duan, Jianfeng Cao, Wenqi Chen, Yinpeng Dong, Jiarun Dai, Jie Fu, Xudong Guo, Tianxing He, Geng Hong, Naying HU, Xiaojian Li, Dongrui Liu, Chaochao Lu, Sören Mindermann, Peng XU, Yang Zhang, Chen Zheng, Brian Tse, Min Yang, Xia Hu
- GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation - Ye Zhu, Kaleb Newman, Johannes Lutzeyer, Adriana Romero-Soriano, Michal Drozdzal, Olga Russakovsky
- Evolution Strategies at the Hyperscale - Bidipta Sarkar, Mattie Fellows, Juan Duque, Alistair Letcher, Antonio León Villares, Anya Sims, Clarisse Wibault, Dmitry Samsonov, Dylan Cope, Jarek Liesen, Kang Li, Lukas Seier, Theo Wolf, Uljad Berdica, Valentin Mohl, Alexander D. Goldie, Aaron Courville, Karin Sevegnani, Shimon Whiteson, Jakob Foerster
- When does predictive inverse dynamics outperform behavior cloning? - Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter, Chris Lovett, Somjit Nath, Luis França, Matheus Mendonca, Alex Lamb, Riashat Islam, Siddhartha Sen, John Langford, Katja Hofmann, Sergio Valcarcel Macua
- Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics - Raphael Bernas, Fanny Jourdan, Antonin Poché, Céline Hudelot
- TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions - Farzaneh Heidari, Guillaume Rabusseau
- Grokking Finite-Dimensional Algebra - Pascal Junior Tikeng Notsawo, Guillaume Dumas, Guillaume Rabusseau
- BRIDGE: Predicting Human Task Completion Time From Model Performance - Fengyuan Liu, Jay Gala, Nilaksh, Dzmitry Bahdanau, Siva Reddy, Hugo Larochelle
- The Cost of Commitment in Option-Based Hierarchical RL - Randy Lefebvre, Audrey Durand
- Which heads matter for reasoning? rl-guided kv cache compression - Wenjie Du, Li Jiang, Keda Tao, Xue Liu, Huan Wang
- Overcoming the Modality Gap in Context-Aided Forecasting - Vincent Zhihao Zheng, Étienne Marcotte, Arjun Ashok, Andrew Robert Williams, Lijun Sun, Alexandre Drouin, Valentina Zantedeschi
- Hierarchical Retrieval at Scale: Bridging Interpretability and Efficiency - Shubham Gupta, Zichao Li, Tianyi Chen, Cem Subakan, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi
- Compositional Planning with Jumpy World Models - Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Marc G Bellemare, Alessandro Lazaric, Ahmed Touati
- Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning - Nilaksh, Antoine Clavaud, Mathieu Reymond, François Rivest, Sarath Chandar
- Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors - Hyeonah Kim, Minsu Kim, Celine Roget, Dionessa Biton, Louis Vaillancourt, Yves V. Brun, Yoshua Bengio, Alex Hernandez-Garcia
- Abductive Reasoning with Probabilistic Commonsense - Joseph Cotnareanu, Chiara Roverato, Han Zhou, Didier Chetelat, Yingxue Zhang, Mark Coates
- Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism - Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
- Riemannian MeanFlow - Dongyeop Woo, Marta Skreta, Seonghyun Park, Kirill Neklyudov, Sungsoo Ahn
- Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access - Daniel Ebi, Damien Ernst, Klemens Böhm, Gaspard Lambrechts
- Spectral Flow Matching: Stabilizing Stochastic GFlowNets via Frequency-Domain Regularization - Nadhir Hassen, Johan W. Verjans
- Why Self-Distillation Helps and Hurts: Denoising vs. Signal Forgetting - Mingqi Wu, Archer Yi Yang, Qiang Sun
Workshops
- AI Pluralism and the Worlds It Misses - Rashid Mushkani
- Signal Frequency Imbalance and Ill-Conditioning (HiLD workshop) - Tianyue Zhang, Francis Bach, Frederik Kunstner
- Reparametrizing Shampoo and SOAP for Subspace Basis Updates and BFloat16 Storage (HiLD workshop) - Alan Milligan, Zikun Xu, Simon Lacoste-Julien, Felix Dangel, Wu Lin
- Bifurcation Preservation as a Physics Diagnostic for Neural Phase-Field Surrogates (AI4Physics Workshop) - Alejandro Salinas-Medina, Anisleidy Gonzalez-Mitjans, Xue Liu
- Lacuna: A Research Map for Machine Learning Problem Formulation - Martin Weiss, Alejandro Hernandez, Yacine Mkhinini, Miles Q. Li, Christopher Pal, Hugo Larochelle, Nasim Rahaman
- Signal from Structure: Exploiting Submodular Upper Bounds in Generative Flow Networks (SPIGM workshop) - Alexandre Larouche, Audrey Durand
- Training Fair Tabular Foundation Models - Patrik Kenfack, Jesse C. Cresswell, Anthony L. Caterini, Samira Ebrahimi Kahou, and Ulrich Aïvodji
- Forecasting Emerges from Auto-Regressive Pretraining: Latent Predictive Structure in Language Models - Alexis Roger, Prateek Humane, Zhenghan Tai, Gwen Legate, Andrei Mircea, Vasilii Feofanov, Irina Rish
- Reusable Low-Rank Subspaces Explain Why Cross-Modal Transfer Adapts with Tiny Updates - Alexis Roger, Prateek Humane, Zhenghan Tai, Gwen Legate, Andrei Mircea, Vasilii Feofanov, Irina Rish
- Language Pretraining Gives Structured Forecasters a Sequential Prior - Zhenghan Tai, Alexis Roger, Prateek Humane, Gwen Legate, Andrei Mircea, Vasilii Feofanov, Irina Rish
- Feature Geometry of Language Models Transfer Across Modalities to Time Series - Prateek Humane, Alexis Roger, Zhenghan Tai, Gwen Legate, Andrei Mircea, Vasilii Feofanov, Irina Rish
- Meta-Merging by Checkpoint Nowcasting - Albert Manuel Orozco Camacho, Boris Knyazev, Eugene Belilovsky, Guy Wolf,
- Drowning in Routine: Signal Dilution in Multi-Turn Agent Training (FAGEN Workshop) - Yann Pernot, Vi Retault
- Merging Adapted Models via Data-Free Covariance Estimation - Marawan Gamal, Derek Tam, Pascal Jr Tikeng Notsawo, Colin Raffel, Guillaume Rabusseau
- Monitoring Access to Piped Water and Sanitation Infrastructure in Africa at Disaggregated Scales Using Satellites Imagery and Self-Supervised Learning (ML4RS workshop) - Othmane Echchabi, Aya Lahlou, Nizar Talty, Tongshu Zheng, Ka Leung Lam
- SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling (AI4Physics Workshop) - Alaina Kolli, Theodoros Xenakis, Utkarsh Utkarsh, Pengfei Cai, Rafael Gomez-Bombarelli, Alan Edelman, Christopher Rackauckas
- Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism (DEMO workshop) - Tianwei Ni, Esther Derman, Vineet Jain, Vincent Taboga, Siamak Ravanbakhsh, Pierre-Luc Bacon
- The Three Regimes of Offline-to-Online Reinforcement Learning (DEMO workshop) - Lu Li, Tianwei Ni, Yihao Sun, Pierre-Luc Bacon
- From Static Policies to Adaptive Priors in Offline Reinforcement Learning (DEMO workshop) - Tianwei Ni, Vineet Jain, Akash Karthikeyan, Pierre-Luc Bacon
- Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization (CoLoRAI workshop) - Laura Gomezjurado Gonzalez ~Laura_Gomezjurado_Gonzalez1 , Tatsuhiro Nakamori, Ganesh Talluri, Ansh Tiwari, Hideyuki Kawashima, Ioannis Mitliagkas, Guillaume Rabusseau, Hiroki Naganuma
- IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs - Florian Carichon, Soumya Sharma, Meaghan J. Girard, Romain Rampa, Golnoosh Farnadi
- Loose Lips: Understanding Privacy Leakage in Agentic Dialogue - Soumya Sharma, Ayana Hussain, Héber Hwang Arcolezi, Ulrich Aïvodji, Spandana Gella, Adriana Romero-Soriano, Golnoosh Farnadi
- Learning from the Right Mistakes: When Do Low-Performing Data Help Offline Policy Gradients? (DEMO workshop) - Jesse Silverberg, Marc G Bellemare, Glen Berseth
- Hidden-State Similarity Predicts Re-Elicitation After Inoculation Prompting (Mech Interp workshop) - Rose Nayoung Kwon, Samy Mammeri, Sabyasachi Sahoo, Christian Gagné, Thomas Jiralerspong
- When Does Interleaving Prevent Emergent Misalignment? (Mech Interp workshop) - Samy Mammeri, Rose Nayoung Kwon, Chen Sun, Sabyasachi Sahoo, Christian Gagné, Thomas Jiralerspong
- Compositional Flow Matching with Factored Velocity Fields (FoGEN workshop) - Avery HW Ryoo, Dane Malenfant, Matthew Perich, Guillaume Lajoie
- NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept Level (Mech Interp workshop) - Milan Bhan, Nicolas Chesneau, Jean-Noel Vittaut, Sarath Chandar, Marie-Jeanne Lesot
