Yoshua Bengio

Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization

Shengchao Liu, Hannan Xu, Yan Ai, Huanxin Li, Yoshua Bengio, Harry Guo

机构 * Université de Montréal（蒙特利尔大学） ； University of Oxford（牛津大学） ； University College London（伦敦大学学院） ； Mila - Québec AI Institute（魁北克人工智能研究所） ； CIFAR AI Chair（CIFAR人工智能 chair） ； University of Ottawa（渥太华大学） ； National Research Council Canada（加拿大国家研究理事会） 纠错

Torsional-GFN: a conditional conformation generator for small molecules

Alexandra Volokhova, Léna Néhale Ezzine, Piotr Gaiński, Luca Scimeca, Emmanuel Bengio, Prudencio Tossou, Yoshua Bengio, Alex Hernandez-Garcia

机构 * Mila -- Quebec AI Institute（魁北克AI研究所） ； Jagiellonian University（雅盖隆大学） ； Valence Labs, Recursion（Valence实验室，Recursion） ； CIFAR（卡尔加里大学人工智能与计算机科学研究院） 纠错

Comments The two first authors are Alexandra Volokhova and Léna Néhale Ezzine, with equal contribution

Divergent Creativity in Humans and Large Language Models

Antoine Bellemare-Pepin, François Lespinasse, Philipp Thölke, Yann Harel, Kory Mathewson, Jay A. Olson, Yoshua Bengio, Karim Jerbi

Comments First two and last listed authors are corresponding authors. The first two listed authors contributed equally to this work

The Singapore Consensus on Global AI Safety Research Priorities

Yoshua Bengio, Tegan Maharaj, Luke Ong, Stuart Russell, Dawn Song, Max Tegmark, Lan Xue, Ya-Qin Zhang, Stephen Casper, Wan Sie Lee, Sören Mindermann, Vanessa Wilfred, Vidhisha Balachandran, Fazl Barez, Michael Belinsky, Imane Bello, Malo Bourgon, Mark Brakel, Siméon Campos, Duncan Cass-Beggs, Jiahao Chen, Rumman Chowdhury, Kuan Chua Seah, Jeff Clune, Juntao Dai, Agnes Delaborde, Nouha Dziri, Francisco Eiras, Joshua Engels, Jinyu Fan, Adam Gleave, Noah Goodman, Fynn Heide, Johannes Heidecke, Dan Hendrycks, Cyrus Hodes, Bryan Low Kian Hsiang, Minlie Huang, Sami Jawhar, Wang Jingyu, Adam Tauman Kalai, Meindert Kamphuis, Mohan Kankanhalli, Subhash Kantamneni, Mathias Bonde Kirk, Thomas Kwa, Jeffrey Ladish, Kwok-Yan Lam, Wan Lee Sie, Taewhi Lee, Xiaojian Li, Jiajun Liu, Chaochao Lu, Yifan Mai, Richard Mallah, Julian Michael, Nick Moës, Simon Möller, Kihyuk Nam, Kwan Yee Ng, Mark Nitzberg, Besmira Nushi, Seán O hÉigeartaigh, Alejandro Ortega, Pierre Peigné, James Petrie, Benjamin Prud'Homme, Reihaneh Rabbany, Nayat Sanchez-Pi, Sarah Schwettmann, Buck Shlegeris, Saad Siddiqui, Aradhana Sinha, Martín Soto, Cheston Tan, Dong Ting, William Tjhi, Robert Trager, Brian Tse, Anthony Tung K. H., Vanessa Wilfred, John Willes, Denise Wong, Wei Xu, Rongwu Xu, Yi Zeng, HongJiang Zhang, Djordje Žikelić

Comments Final report from the "2025 Singapore Conference on AI (SCAI)" held April 26: https://www.scai.gov.sg/2025/scai2025-report

Geometric Signatures of Compositionality Across a Language Model's Lifetime

Jin Hwa Lee, Thomas Jiralerspong, Lei Yu, Yoshua Bengio, Emily Cheng

机构 * University College London（伦敦大学学院） ； Université de Montréal（蒙特利尔大学） ； Mila（Mila研究院） ； University of Toronto（多伦多大学） ； Universitat Pompeu Fabra（庞培法布拉大学） 纠错

Comments Published at ACL 2025

Can a Bayesian Oracle Prevent Harm from an Agent?

Yoshua Bengio, Michael K. Cohen, Nikolay Malkin, Matt MacDermott, Damiano Fornasiere, Pietro Greiner, Younesse Kaddar

Comments Accepted at UAI 2025 (Uncertainty in Artificial Intelligence). 20 pages, 2 figures. Code available at: https://github.com/saifh-github/conservative-bayesian-public

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

机构 * Mila – Quebec AI Institute（魁北克AI研究所） ； Université de Montréal（蒙特利尔大学） ； McGill University（麦吉尔大学） ； Rubisco AI（Rubisco人工智能） 纠错

A Complexity-Based Theory of Compositionality

Eric Elmoznino, Thomas Jiralerspong, Yoshua Bengio, Guillaume Lajoie

机构 * Mila – Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） 纠错

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Siddarth Venkatraman, Mohsin Hasan, Minsu Kim, Luca Scimeca, Marcin Sendera, Yoshua Bengio, Glen Berseth, Nikolay Malkin

机构 * Mila -- Qu\'ebec AI Institute ； Jagiellonian University ； CIFAR ； University of Edinburgh 纠错

Comments ICML 2025; code: https://github.com/HyperPotatoNeo/Outsourced_Diffusion_Sampling

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets

Zhen Liu, Tim Z. Xiao, Weiyang Liu, Yoshua Bengio, Dinghuai Zhang

机构 * Mila, Université de Montréal（蒙特利尔大学Mila实验室） ； Max Planck Institute for Intelligent Systems - Tübingen（智能系统马克斯·普朗克研究所（图宾根）） ； The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）） ； University of Tübingen（图宾根大学） ； University of Cambridge（剑桥大学） ； Microsoft Research（微软研究院） 纠错

Comments Technical Report (36 pages, 31 figures), Accepted at ICLR 2025

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

Lu Li, Tianyu Zhang, Zhiqi Bu, Suyuchen Wang, Huan He, Jie Fu, Yonghui Wu, Jiang Bian, Yong Chen, Yoshua Bengio

机构 * University of Pennsylvania（宾夕法尼亚大学） ； MILA（蒙特利尔人工智能研究院） ； ServiceNow（ServiceNow公司） ； Amazon AGI（亚马逊人工智能实验室） ； Université de Montréal（蒙特利尔大学） ； HKUST（香港科技大学） ； University of Florida（佛罗里达大学） 纠错

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, Yoshua Bengio

Comments Accepted at ICLR 2025. Original paper name: VCR: Visual Caption Restoration

In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?

Ben Bucknall, Saad Siddiqui, Lara Thurnherr, Conor McGurk, Ben Harack, Anka Reuel, Patricia Paskov, Casey Mahoney, Sören Mindermann, Scott Singer, Vinay Hiremath, Charbel-Raphaël Segerie, Oscar Delaney, Alessandro Abate, Fazl Barez, Michael K. Cohen, Philip Torr, Ferenc Huszár, Anisoara Calinescu, Gabriel Davis Jones, Yoshua Bengio, Robert Trager

Comments Accepted to ACM Conference on Fairness, Accountability, and Transparency (FAccT 2025)

Open Problems in Technical AI Governance

Anka Reuel, Ben Bucknall, Stephen Casper, Tim Fist, Lisa Soder, Onni Aarne, Lewis Hammond, Lujain Ibrahim, Alan Chan, Peter Wills, Markus Anderljung, Ben Garfinkel, Lennart Heim, Andrew Trask, Gabriel Mukobi, Rylan Schaeffer, Mauricio Baker, Sara Hooker, Irene Solaiman, Alexandra Sasha Luccioni, Nitarshan Rajkumar, Nicolas Moës, Jeffrey Ladish, David Bau, Paul Bricman, Neel Guha, Jessica Newman, Yoshua Bengio, Tobin South, Alex Pentland, Sanmi Koyejo, Mykel J. Kochenderfer, Robert Trager

Comments Ben Bucknall and Anka Reuel contributed equally and share the first author position

Journal ref Transactions on Machine Learning Research, 2025

Adaptive teachers for amortized samplers

Minsu Kim, Sanghyeok Choi, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, Yoshua Bengio

Comments ICLR 2025, 27 pages, 12 figures

International Scientific Report on the Safety of Advanced AI (Interim Report)

Yoshua Bengio, Sören Mindermann, Daniel Privitera, Tamay Besiroglu, Rishi Bommasani, Stephen Casper, Yejin Choi, Danielle Goldfarb, Hoda Heidari, Leila Khalatbari, Shayne Longpre, Vasilios Mavroudis, Mantas Mazeika, Kwan Yee Ng, Chinasa T. Okolo, Deborah Raji, Theodora Skeadas, Florian Tramèr, Bayo Adekanmbi, Paul Christiano, David Dalrymple, Thomas G. Dietterich, Edward Felten, Pascale Fung, Pierre-Olivier Gourinchas, Nick Jennings, Andreas Krause, Percy Liang, Teresa Ludermir, Vidushi Marda, Helen Margetts, John A. McDermid, Arvind Narayanan, Alondra Nelson, Alice Oh, Gopal Ramchurn, Stuart Russell, Marietje Schaake, Dawn Song, Alvaro Soto, Lee Tiedrich, Gaël Varoquaux, Andrew Yao, Ya-Qin Zhang

Comments Available under the open government license at https://www.gov.uk/government/publications/international-scientific-report-on-the-safety-of-advanced-ai

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles

Luca Scimeca, Alexander Rubinstein, Damien Teney, Seong Joon Oh, Yoshua Bengio

Comments Accepted as a workshop paper at ICLR 2025. arXiv admin note: substantial text overlap with arXiv:2310.02230

Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery

Mélisande Teng, Arthur Ouaknine, Etienne Laliberté, Yoshua Bengio, David Rolnick, Hugo Larochelle

Comments ICLR 2025 ML4RS workshop

A scalable gene network model of regulatory dynamics in single cells

Paul Bertin, Joseph D. Viviano, Alejandro Tejada-Lapuerta, Weixu Wang, Stefan Bauer, Fabian J. Theis, Yoshua Bengio

Comments 42 pages, 10 figures

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri, Akshay Kalkunte, François Savard, Ahmed Masry, Shravan Nayak, Rabiul Awal, Mahsa Massoud, Amirhossein Abaskohi, Zichao Li, Suyuchen Wang, Pierre-André Noël, Mats Leon Richter, Saverio Vadacchino, Shubham Agarwal, Sanket Biswas, Sara Shanian, Ying Zhang, Noah Bolger, Kurt MacDonald, Simon Fauvel, Sathwik Tejaswi, Srinivas Sunkara, Joao Monteiro, Krishnamurthy DJ Dvijotham, Torsten Scholak, Nicolas Chapados, Sepideh Kharagani, Sean Hughes, M. Özsu, Siva Reddy, Marco Pedersoli, Yoshua Bengio, Christopher Pal, Issam Laradji, Spandana Gella, Perouz Taslakian, David Vazquez, Sai Rajeswar

Comments The project is hosted at https://bigdocs.github.io

Journal ref ICLR 2025 https://openreview.net/forum?id=UTgNFcpk0j

Solving Bayesian inverse problems with diffusion priors and off-policy RL

Luca Scimeca, Siddarth Venkatraman, Moksh Jain, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yashar Hezaveh, Laurence Perreault-Levasseur, Yoshua Bengio, Glen Berseth, Nikolay Malkin

Comments Accepted as workshop paper at DeLTa workshop, ICLR 2025. arXiv admin note: substantial text overlap with arXiv:2405.20971

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control

Thomas Jiralerspong, Berton Earnshaw, Jason Hartford, Yoshua Bengio, Luca Scimeca

Comments Published as workshop paper at DeLTa and FPI workshops, ICLR 2025

Structure Language Models for Protein Conformation Generation

Jiarui Lu, Xiaoyin Chen, Stephen Zhewen Lu, Chence Shi, Hongyu Guo, Yoshua Bengio, Jian Tang

Comments Published as a conference paper at ICLR 2025, see https://openreview.net/forum?id=OzUNDnpQyd

Learning Decision Trees as Amortized Structure Inference

Mohammed Mahfoud, Ghait Boukachab, Michał Koziarski, Alex Hernandez-Garcia, Stefan Bauer, Yoshua Bengio, Nikolay Malkin

Comments Code: $\href{https://github.com/GFNOrg/dt-gfn}{https://github.com/GFNOrg/dt-gfn}$

Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold

Lazar Atanackovic, Xi Zhang, Brandon Amos, Mathieu Blanchette, Leo J. Lee, Yoshua Bengio, Alexander Tong, Kirill Neklyudov

Comments Accepted to ICLR 2025

Learning diverse attacks on large language models for robust red-teaming and safety tuning

Seanie Lee, Minsu Kim, Lynn Cherif, David Dobre, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Moksh Jain

Comments ICLR 2025

Ant Colony Sampling with GFlowNets for Combinatorial Optimization

Minsu Kim, Sanghyeok Choi, Hyeonah Kim, Jiwoo Son, Jinkyoo Park, Yoshua Bengio

Comments AISTATS 2025, 21 pages, 6 figures

Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?

Yoshua Bengio, Michael Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King

Comments v2 with fixed formatting for URLs and hyperlinks

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Seanie Lee, Haebin Seong, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner, Yoshua Bengio, Juho Lee, Sung Ju Hwang

Comments ICLR 2025

In-Context Parametric Inference: Point or Distribution Estimators?

Sarthak Mittal, Yoshua Bengio, Nikolay Malkin, Guillaume Lajoie