Yoshua Bengio

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

Berkes Anaïs

Collaborateur·rice de recherche - Cambridge University

Superviseur⋅e principal⋅e :

Rim Assouel

Doctorat - UdeM

Stefan Bauer

Visiteur de recherche indépendant

Co-superviseur⋅e :

Guillaume Lajoie

Shahana Chatterjee

Collaborateur·rice de recherche - N/A

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Collaborateur·rice de recherche - KAIST

Doctorat - UdeM

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Loubna Benabbou

Desmond Elliott

Visiteur de recherche indépendant

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Co-superviseur⋅e :

Doctorat - UdeM

Doctorat - UdeM

Doctorat

Doctorat - UdeM

Moksh Jain

Doctorat - UdeM

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice alumni - UdeM

Hyeonah Kim

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Alex Hernández-García

Tabitha Edith Lee

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice alumni

Collaborateur·rice alumni - UdeM

Cristian Dragos Manta

Doctorat - UdeM

Co-superviseur⋅e :

Dhanya Sridhar

Sarthak Mittal

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Visiteur de recherche indépendant - UdeM

Padideh Nouri

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Ali Parviz

Collaborateur·rice de recherche - Ying Wu Coll of Computing

Lena Podina

Collaborateur·rice de recherche - University of Waterloo

Superviseur⋅e principal⋅e :

David Rolnick

Camille Rochefort-Boulanger

Nassim Rahaman

Collaborateur·rice alumni - Max-Planck-Institute for Intelligent Systems

Amine RAZIG

Collaborateur·rice de recherche - UdeM

Co-superviseur⋅e :

Doctorat - UdeM

Postdoctorat - UdeM

Postdoctorat - UdeM

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Julie Hussin

Dragos Secrieru

Collaborateur·rice alumni - UdeM

Divya Sharma

Postdoctorat

Co-superviseur⋅e :

Alex Hernández-García

Mélisande Astrid Crystal Teng

Vincent Taboga

Collaborateur·rice alumni - Polytechnique

Co-superviseur⋅e :

Doctorat - UdeM

Co-superviseur⋅e :

Hugo Larochelle

Ivan Titov

Collaborateur·rice de recherche

Superviseur⋅e principal⋅e :

Siva Reddy

Alex Tong

Collaborateur·rice alumni - UdeM

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche

Collaborateur·rice de recherche - UdeM

Doctorat - UdeM

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Aaron Courville

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

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

Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning

Jaesik Yoon

Hyeonseo Cho

Sungjin Ahn

Diffusion models have recently emerged as a powerful approach for trajectory planning. However, their inherently non-sequential nature limit… (voir plus)s their effectiveness in long-horizon reasoning tasks at test time. The recently proposed Monte Carlo Tree Diffusion (MCTD) offers a promising solution by combining diffusion with tree-based search, achieving state-of-the-art performance on complex planning problems. Despite its strengths, our analysis shows that MCTD incurs substantial computational overhead due to the sequential nature of tree search and the cost of iterative denoising. To address this, we propose Fast-MCTD, a more efficient variant that preserves the strengths of MCTD while significantly improving its speed and scalability. Fast-MCTD integrates two techniques: Parallel MCTD, which enables parallel rollouts via delayed tree updates and redundancy-aware selection; and Sparse MCTD, which reduces rollout length through trajectory coarsening. Experiments show that Fast-MCTD achieves up to 100× speedup over standard MCTD while maintaining or improving planning performance. Remarkably, it even outperforms Diffuser in inference speed on some tasks, despite Diffuser requiring no search and yielding weaker solutions. These results position Fast-MCTD as a practical and scalable solution for diffusion-based inference-time reasoning.

2025-09-17

NeurIPS.cc/2025/Conference (spotlight)

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

Brian Bartoldson

James Diffenderfer

Tal Ben-Nun

Johan Obando-Ceron

Bhavya Kailkhura

Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post… (voir plus)-training are not naturally robust to a diversified content of experience replay buffers, which asynchronous off-policy actors can efficiently populate in parallel to training. We propose efficiently learning on such off-policy data via Trajectory Balance with Asynchrony (TBA), an approach to asynchronous RL for LLMs that leverages the principled off-policy TB objective. On math, preference-tuning, and automated red-teaming tasks, we post-train models ranging from Pythia 410M to Qwen 2.5 7B, finding TBA offers speed and performance boosts over strong baselines like Online DPO and Dr. GRPO. Beyond TBA's performance benefits (high accuracy even as asynchrony grows) and speedups (

2025-09-17

NeurIPS.cc/2025/Conference (poster)

Illusions of AI consciousness

Eric Elmoznino

The belief that AI is conscious is not without risk

2025-09-10

Science (publié)

Relative Trajectory Balance is equivalent to Trust-PCL

2025-08-31

ArXiv (prépublication)

arxiv.org

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

Michael Cohen

Joumana Ghosn

Adam Oberman

Jesse Richardson

Oliver Richardson

Marc-Antoine Rondeau

Pierre-Luc St-Charles

David Williams-King

The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue go… (voir plus)als across almost all tasks that humans can perform. Despite how useful these systems might be, unchecked AI agency poses significant risks to public safety and security, ranging from misuse by malicious actors to a potentially irreversible loss of human control. We discuss how these risks arise from current AI training methods. Indeed, various scenarios and experiments have demonstrated the possibility of AI agents engaging in deception or pursuing goals that were not specified by human operators and that conflict with human interests, such as self-preservation. Following the precautionary principle, we see a strong need for safer, yet still useful, alternatives to the current agency-driven trajectory. Accordingly, we propose as a core building block for further advances the development of a non-agentic AI system that is trustworthy and safe by design, which we call Scientist AI. This system is designed to explain the world from observations, as opposed to taking actions in it to imitate or please humans. It comprises a world model that generates theories to explain data and a question-answering inference machine. Both components operate with an explicit notion of uncertainty to mitigate the risks of overconfident predictions. In light of these considerations, a Scientist AI could be used to assist human researchers in accelerating scientific progress, including in AI safety. In particular, our system can be employed as a guardrail against AI agents that might be created despite the risks involved. Ultimately, focusing on non-agentic AI may enable the benefits of AI innovation while avoiding the risks associated with the current trajectory. We hope these arguments will motivate researchers, developers, and policymakers to favor this safer path.

2025-08-14

SuperIntelligence - Robotics - Safety & Alignment (publié)

arxiv.org

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

BEN BUCKNALL

Saad Siddiqui

Robert Trager

LARA THURNHERR

CONOR MCGURK

BEN HARACK

International cooperation is common in AI research, including between geopolitical rivals. While many experts advocate for greater internati… (voir plus)onal cooperation on AI safety to address shared global risks, some view cooperation on AI with suspicion, arguing that it can pose unacceptable risks to national security. However, the extent to which cooperation on AI safety poses such risks, as well as provides benefits, depends on the specific area of cooperation. In this paper, we consider technical factors that impact the risks of international cooperation on AI safety research, focusing on the degree to which such cooperation can advance dangerous capabilities, result in the sharing of sensitive information, or provide opportunities for harm. We begin by why nations historically cooperate on strategic technologies and analyse current US-China cooperation in AI as a case study. We further argue that existing frameworks for managing associated risks can be supplemented with consideration of key risks specific to cooperation on technical AI safety research. Through our analysis, we find that research into AI verification mechanisms and shared protocols may be suitable areas for such cooperation. Through this analysis we aim to help researchers and governments identify and mitigate the risks of international cooperation on AI safety research, so that the benefits of cooperation can be fully realised.

2025-08-10

SuperIntelligence - Robotics - Safety & Alignment (publié)

RL, but don't do anything I wouldn't do

Michael K. Cohen

Marcus Hutter

Stuart Russell

In reinforcement learning (RL), if the agent's reward differs from the designers' true utility, even only rarely, the state distribution res… (voir plus)ulting from the agent's policy can be very bad, in theory and in practice. When RL policies would devolve into undesired behavior, a common countermeasure is KL regularization to a trusted policy ("Don't do anything I wouldn't do"). All current cutting-edge language models are RL agents that are KL-regularized to a "base policy" that is purely predictive. Unfortunately, we demonstrate that when this base policy is a Bayesian predictive model of a trusted policy, the KL constraint is no longer reliable for controlling the behavior of an advanced RL agent. We demonstrate this theoretically using algorithmic information theory, and while systems today are too weak to exhibit this theorized failure precisely, we RL-finetune a language model and find evidence that our formal results are plausibly relevant in practice. We also propose a theoretical alternative that avoids this problem by replacing the "Don't do anything I wouldn't do" principle with "Don't do anything I mightn't do".

2025-07-10

Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence (publié)

proceedings.mlr.press

Discrete Feynman-Kac Correctors

Mohsin Hasan

Viktor Ohanesian

Artem Gazizov

Alán Aspuru-Guzik

Roberto Bondesan

Marta Skreta

Kirill Neklyudov

Discrete diffusion models have recently emerged as a promising alternative to the autoregressive approach for generating discrete sequences.… (voir plus) Sample generation via gradual denoising or demasking processes allows them to capture hierarchical non-sequential interdependencies in the data. These custom processes, however, do not assume a flexible control over the distribution of generated samples. We propose Discrete Feynman-Kac Correctors, a framework that allows for controlling the generated distribution of discrete masked diffusion models at inference time. We derive Sequential Monte Carlo (SMC) algorithms that, given a trained discrete diffusion model, control the temperature of the sampled distribution (i.e. perform annealing), sample from the product of marginals of several diffusion processes (e.g. differently conditioned processes), and sample from the product of the marginal with an external reward function, producing likely samples from the target distribution that also have high reward. Notably, our framework does not require any training of additional models or fine-tuning of the original model. We illustrate the utility of our framework in several applications including: efficient sampling from the annealed Boltzmann distribution of the Ising model, improving the performance of language models for code generation and amortized learning, as well as reward-tilted protein sequence generation.

2025-07-08

ICML.cc/2025/Workshop/AI4MATH (poster)

HVAC-GRACE: Transferable Building Control via Heterogeneous Graph Neural Network Policies

Anaïs Berkes

Donna Vakalis

David Rolnick

Buildings consume 40% of global energy, with HVAC systems responsible for up to half of that demand. As energy use grows, optimizing HVAC ef… (voir plus)ficiency is critical to meeting climate goals. While reinforcement learning (RL) offers a promising alternative to rule-based control, real-world adoption is limited by poor sample efficiency and generalisation. We introduce HVAC-GRACE, a graph-based RL framework that models buildings as heterogeneous graphs and integrates spatial message passing directly into temporal GRU gates. This enables each zone to learn control actions informed by both its own history and its structural context. Our architecture supports zero-shot transfer by learning topology-agnostic functions—but initial experiments reveal that this benefit depends on sufficient conditioned zone connectivity to maintain gradient flow. These findings highlight both the promise and the architectural requirements of scalable, transferable RL for building control

2025-06-30

ICML.cc/2025/Workshop/CO-BUILD (poster)

Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators

Oscar Davis

Michael Bronstein

Avishek Joey Bose

Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large… (voir plus)-scale diffusion and flow matching models. However, such modern generative models suffer from expensive inference, inhibiting their use in numerous scientific applications like Boltzmann Generators (BGs) for molecular conformations that require fast likelihood evaluation. In this paper, we revisit classical normalizing flows in the context of BGs that offer efficient sampling and likelihoods, but whose training via maximum likelihood is often unstable and computationally challenging. We propose Regression Training of Normalizing Flows (RegFlow), a novel and scalable regression-based training objective that bypasses the numerical instability and computational challenge of conventional maximum likelihood training in favour of a simple

2025-06-10

ICML.cc/2025/Workshop/GenBio (spotlight)

Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning

Jaesik Yoon

Hyeonseo Cho

Sungjin Ahn

Diffusion models have recently emerged as a powerful approach for trajectory planning. However, their inherently non-sequential nature limit… (voir plus)s their effectiveness in long-horizon reasoning tasks at test time. The recently proposed Monte Carlo Tree Diffusion (MCTD) offers a promising solution by combining diffusion with tree-based search, achieving state-of-the-art performance on complex planning problems. Despite its strengths, our analysis shows that MCTD incurs substantial computational overhead due to the sequential nature of tree search and the cost of iterative denoising. To address this, we propose Fast-MCTD, a more efficient variant that preserves the strengths of MCTD while significantly improving its speed and scalability. Fast-MCTD integrates two techniques: Parallel MCTD, which enables parallel rollouts via delayed tree updates and redundancy-aware selection; and Sparse MCTD, which reduces rollout length through trajectory coarsening. Experiments show that Fast-MCTD achieves up to 100x speedup over standard MCTD while maintaining or improving planning performance. Remarkably, it even outperforms Diffuser in inference speed on some tasks, despite Diffuser requiring no search and yielding weaker solutions. These results position Fast-MCTD as a practical and scalable solution for diffusion-based inference-time reasoning.

2025-06-10

ArXiv (prépublication)