Yoshua Bengio

jamal.abouhaibeh@mila.quebec

Biographie

*Pour toute demande média, veuillez écrire à medias@mila.quebec.

Pour plus d’information, contactez Cassidy MacNeil, adjointe principale et responsable des opérations cassidy.macneil@mila.quebec.

Reconnu comme une sommité mondiale en intelligence artificielle, Yoshua Bengio s’est surtout distingué par son rôle de pionnier en apprentissage profond, ce qui lui a valu le prix A. M. Turing 2018, le « prix Nobel de l’informatique », avec Geoffrey Hinton et Yann LeCun. Il est professeur titulaire à l’Université de Montréal, fondateur et conseiller scientifique de Mila – Institut québécois d’intelligence artificielle, et codirige en tant que senior fellow le programme Apprentissage automatique, apprentissage biologique de l'Institut canadien de recherches avancées (CIFAR). Il occupe également la fonction de conseiller spécial et directeur scientifique fondateur d’IVADO.

En 2018, il a été l’informaticien qui a recueilli le plus grand nombre de nouvelles citations au monde. En 2019, il s’est vu décerner le prestigieux prix Killam. Depuis 2022, il détient le plus grand facteur d’impact (h-index) en informatique à l’échelle mondiale. Il est fellow de la Royal Society de Londres et de la Société royale du Canada, et officier de l’Ordre du Canada.

Soucieux des répercussions sociales de l’IA et de l’objectif que l’IA bénéficie à tous, il a contribué activement à la Déclaration de Montréal pour un développement responsable de l’intelligence artificielle.

Étudiants actuels

Jamal Abou Haibeh

Collaborateur·rice alumni - McGill

Collaborateur·rice de recherche - Cambridge University

Superviseur⋅e principal⋅e :

David Rolnick

berkes.anais@mila.quebec

sanghyeok.choi@mila.quebec

Rim Assouel

Doctorat - UdeM

assouelr@mila.quebec

Xiaoyin Chen

Doctorat - UdeM

xiaoyin.chen@mila.quebec

Sanghyeok Choi

Collaborateur·rice de recherche - KAIST

Doctorat - UdeM

aniket.didolkar@mila.quebec

Doctorat - UdeM

Co-superviseur⋅e :

Guillaume Lajoie

eric.elmoznino@mila.quebec

Doctorat - UdeM

lena-nehale.ezzine@mila.quebec

Jean-Pierre Falet

Doctorat - UdeM

jean-pierre.falet@mila.quebec

Doctorat

pietro.greiner@mila.quebec

Mohsin Hasan

Doctorat - UdeM

mohsin.hasan@mila.quebec

thomas.jiralerspong@mila.quebec

Moksh Jain

Doctorat - UdeM

moksh.jain@mila.quebec

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

Collaborateur·rice alumni - UdeM

younesse.kaddar@mila.quebec

Minsu Kim

Collaborateur·rice de recherche - UdeM

minsu.kim@mila.quebec

Hyeonah Kim

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Alex Hernández-García

hyeonah.kim@mila.quebec

Jeongjae Lee

Collaborateur·rice de recherche - KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

jeongjae.lee@mila.quebec

Collaborateur·rice de recherche

Song LIU

Collaborateur·rice de recherche - s.o.

liusong299@gmail.com

cristian-dragos.manta@mila.quebec

Cristian Dragos Manta

Doctorat - UdeM

Co-superviseur⋅e :

Dhanya Sridhar

Sarthak Mittal

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Visiteur de recherche indépendant - UdeM

nguyenph@mila.quebec

Ali Parviz

Collaborateur·rice de recherche - Ying Wu Coll of Computing

ali.parviz@mila.quebec

Lena Podina

Collaborateur·rice de recherche - University of Waterloo

Superviseur⋅e principal⋅e :

David Rolnick

elena.podina@mila.quebec

jarrid.rector-brooks@mila.quebec

Jarrid Rector-Brooks

Doctorat - UdeM

Danyal REHMAN

Postdoctorat - UdeM

danyal.rehman@mila.quebec

oliver.richardson@mila.quebec

Oli RICHARDSON

Postdoctorat - UdeM

Camille Rochefort-Boulanger

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Postdoctorat - UdeM

Co-superviseur⋅e :

Alex Hernández-García

divya.sharma@mila.quebec

Mélisande Astrid Crystal Teng

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Alex Tong

Collaborateur·rice alumni - UdeM

alexander.tong@mila.quebec

Collaborateur·rice de recherche - University of Cambridge

oszkar.urban@mila.quebec

donna.vakalis@mila.quebec

Donna Vakalis

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

David Rolnick

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Glen Berseth

siddarth.venkatraman@mila.quebec

Collaborateur·rice de recherche

joseph.viviano2@mila.quebec

Collaborateur·rice de recherche - UdeM

esmeralda.whitammer@mila.quebec

Collaborateur·rice alumni

omar.younis@mila.quebec

Collaborateur·rice de recherche - UdeM

taeyoung.yun@mila.quebec

Skipper : combiner l’abstraction spatiale et temporelle afin d’améliorer la généralisation

Tianyu Zhang

Doctorat - UdeM

tianyu.zhang@mila.quebec

Doctorat - McGill

Superviseur⋅e principal⋅e :

Harry Zhao

Collaborateur·rice alumni - McGill

Superviseur⋅e principal⋅e :

Billets de blogue

Generic thumbnail for Mila Blog articles.

22 février 2024

par

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Mise à l’échelle au service du raisonnement et de l’apprentissage automatique basé sur un modèle

Scaling in the service of reasoning & model-based ML

4 avril 2023

par

Yoshua Bengio

Edward J. Hu

Une collaboration entre Mila et Relation Therapeutics pour découvrir in vitro de nouvelles associations médicamenteuses synergiques

A collaboration between Mila and Relation Therapeutics to discover novel synergistic combinations of drugs in vitro

23 mars 2022

par

Paul Bertin

Jake P. Taylor-King

Yoshua Bengio

Les réseaux de flot génératifs

15 mars 2022

par

Yoshua Bengio

Publications

Scaling Latent Reasoning via Looped Language Models

Ruiming Zhu

Zixuan Wang

Kai Hua

Tianyu Zhang

Ziniu Li

Haoran Que

Boyi Wei

Zixin Wen

Fan Yin

He Xing

Li Li

Jiajun Shi

Kaijing Ma

Shanda Li

Taylor Kergan

Andrew C. Smith

Xin Qu

Mude Hui

Bohong Wu

Qiyang Min … (voir 13 de plus)

Hongzhi Huang

Xun Zhou

Wei Ye

Jiaheng Liu

Jian Yang 0030

Yunfeng Shi

Chenghua Lin

Enduo Zhao

Tianle Cai

Ge Zhang

Wenhao Huang

Jason K. Eshraghian

Modern LLMs are trained to"think"primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-trai… (voir plus)ning and under-leverages pre-training data. We present and open-source Ouro, named after the recursive Ouroboros, a family of pre-trained Looped Language Models (LoopLM) that instead build reasoning into the pre-training phase through (i) iterative computation in latent space, (ii) an entropy-regularized objective for learned depth allocation, and (iii) scaling to 7.7T tokens. Ouro 1.4B and 2.6B models enjoy superior performance that match the results of up to 12B SOTA LLMs across a wide range of benchmarks. Through controlled experiments, we show this advantage stems not from increased knowledge capacity, but from superior knowledge manipulation capabilities. We also show that LoopLM yields reasoning traces more aligned with final outputs than explicit CoT. We hope our results show the potential of LoopLM as a novel scaling direction in the reasoning era. Our model is available here: http://ouro-llm.github.io.

2025-10-28

ArXiv (prépublication)

Deep-learning-based virtual screening of antibacterial compounds

Gabriele Scalia

Steven T. Rutherford

Ziqing Lu

Kerry R. Buchholz

Nicholas Skelton

Kangway Chuang

Nathaniel Diamant

Jan-Christian Hütter

Jerome-Maxim Luescher

Anh Miu

Jeff Blaney

Leo Gendelev

Elizabeth Skippington

Greg Zynda

Nia Dickson

Michał Koziarski

Aviv Regev

Man-Wah Tan

Tommaso Biancalani

2025-10-23

Nature Biotechnology (inconnu)

Surrogate-based quantification of policy uncertainty in generative flow networks

Ram'on Nartallo-Kaluarachchi

Robert Manson-Sawko

Shashanka Ubaru

Dongsung Huh

Malgorzata J. Zimo'n

Lior Horesh

2025-10-23

ArXiv (prépublication)

International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications

Stephen Clare

Carina Prunkl

Maksym Andriushchenko

BEN BUCKNALL

Philip Fox

Tiancheng Hu

Cameron Jones

Sam Manning

Nestor Maslej

Vasilios Mavroudis

Conor McGlynn

Malcolm Murray

Shalaleh Rismani

Charlotte Stix

Lucia Velasco

Nicole Wheeler

Daniel Privitera

Sören Mindermann

Daron Acemoglu … (voir 36 de plus)

Thomas G. Dietterich

Fredrik Heintz

Geoffrey Hinton

Nick Jennings

Susan Leavy

Teresa Ludermir

Vidushi Marda

Helen Margetts

John McDermid

Jane Munga

Arvind Narayanan

Alondra Nelson

Clara Neppel

Sarvapali D. (Gopal) Ramchurn

Stuart Russell

Marietje Schaake

Bernhard Schölkopf

Alvaro Soto

Lee Tiedrich

Gael Varoquaux

Andrew Yao

Ya-Qin Zhang

Lambrini Das

Claire Dennis

Arianna Dini

Freya Hempleman

Samuel Kenny

Patrick King

Hannah Merchant

Jamie-Day Rawal

Rose Woolhouse

Jonathan Barry

Marc-Antoine Guérard

Claire Latendresse

Cassidy MacNeil

Benjamin Prud’homme

Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New trainin… (voir plus)g techniques that teach AI systems to reason step-by-step and inference-time enhancements have primarily driven these advances, rather than simply training larger models. As a result, general-purpose AI systems can solve more complex problems in a range of domains, from scientific research to software development. Their performance on benchmarks that measure performance in coding, mathematics, and answering expert-level science questions has continued to improve, though reliability challenges persist, with systems excelling on some tasks while failing completely on others. These capability improvements also have implications for multiple risks, including risks from biological weapons and cyber attacks. Finally, they pose new challenges for monitoring and controllability. This update examines how AI capabilities have improved since the first Report, then focuses on key risk areas where substantial new evidence warrants updated assessments.

2025-10-14

arXiv (prépublication)

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise

Luca Scimeca

Thomas Jiralerspong

Berton Earnshaw

Jason Hartford

2025-10-06

ArXiv (prépublication)

Monte Carlo Tree Diffusion for System 2 Planning

Jaesik Yoon

Hyeonseo Cho

Doojin Baek

Sungjin Ahn

Diffusion models have recently emerged as a powerful tool for planning. However, unlike Monte Carlo Tree Search (MCTS)-whose performance nat… (voir plus)urally improves with inference-time computation scaling-standard diffusion-based planners offer only limited avenues for the scalability. In this paper, we introduce Monte Carlo Tree Diffusion (MCTD), a novel framework that integrates the generative strength of diffusion models with the adaptive search capabilities of MCTS. Our method reconceptualizes denoising as a tree-structured process, allowing partially denoised plans to be iteratively evaluated, pruned, and refined. By selectively expanding promising trajectories while retaining the flexibility to revisit and improve suboptimal branches, MCTD achieves the benefits of MCTS such as controlling exploration-exploitation trade-offs within the diffusion framework. Empirical results on challenging long-horizon tasks show that MCTD outperforms diffusion baselines, yielding higher-quality solutions as inference-time computation increases.

2025-10-05

Proceedings of the 42nd International Conference on Machine Learning (publié)

proceedings.mlr.press

Rejecting Hallucinated State Targets during Planning

Mingde Zhao

Tristan Sylvain

Romain Laroche

Doina Precup

In planning processes of computational decision-making agents, generative or predictive models are often used as "generators" to propose "ta… (voir plus)rgets" representing sets of expected or desirable states. Unfortunately, learned models inevitably hallucinate infeasible targets that can cause delusional behaviors and safety concerns. We first investigate the kinds of infeasible targets that generators can hallucinate. Then, we devise a strategy to identify and reject infeasible targets by learning a target feasibility evaluator. To ensure that the evaluator is robust and non-delusional, we adopted a design choice combining off-policy compatible learning rule, distributional architecture, and data augmentation based on hindsight relabeling. Attaching to a planning agent, the designed evaluator learns by observing the agent's interactions with the environment and the targets produced by its generator, without the need to change the agent or its generator. Our controlled experiments show significant reductions in delusional behaviors and performance improvements for various kinds of existing agents.

2025-10-05

Proceedings of the 42nd International Conference on Machine Learning (publié)

proceedings.mlr.press

Towards a Formal Theory of Representational Compositionality

2025-10-05

Proceedings of the 42nd International Conference on Machine Learning (publié)

proceedings.mlr.press

HVAC-SPICE: Value-Uncertainty In-Context RL with Thompson Sampling for Zero-Shot HVAC Control

Anaïs Berkes

Urban buildings consume 40\% of global energy, yet most rely on inefficient rule-based HVAC systems due to the impracticality of deploying a… (voir plus)dvanced controllers across diverse building stock. In-context reinforcement learning (ICRL) offers promise for rapid deployment without per-building training, but standard supervised learning objectives that maximise likelihood of training actions inherit behaviour-policy bias and provide weak exploration under the distribution shifts common when transferring across buildings and climates. We present SPICE (Sampling Policies In-Context with Ensemble uncertainty), a novel ICRL method specifically designed for zero-shot building control that addresses these fundamental limitations. SPICE introduces two key methodological innovations: (i) a propensity-corrected, return-aware training objective that prioritises high-advantage, high-uncertainty actions to enable improvement beyond suboptimal training demonstrations, and (ii) lightweight value ensembles with randomised priors that provide explicit uncertainty estimates for principled episode-level Thompson sampling. At deployment, SPICE samples one value head per episode and acts greedily, resulting in temporally coherent exploration without test-time gradients or building-specific models. We establish a comprehensive experimental protocol using the HOT dataset to evaluate SPICE across diverse building types and climate zones, focusing on the energy efficiency, occupant comfort, and zero-shot transfer capabilities that are critical for urban-scale deployment.

2025-09-29

NeurIPS.cc/2025/Workshop/UrbanAI (poster)

openreview.net

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Nikolay Malkin

Moksh Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (voir plus) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-29

ArXiv (prépublication)

Active Attacks: Red-teaming LLMs via Adaptive Environments

Taeyoung YUN

Pierre-Luc St-Charles

Jinkyoo Park