Yoshua Bengio

jamal.abouhaibeh@mila.quebec

Biography

*For media requests, please write to medias@mila.quebec.

For more information please contact Cassidy MacNeil, Senior Assistant and Operation Lead at cassidy.macneil@mila.quebec.

Yoshua Bengio is recognized worldwide as a leading expert in AI. He is most known for his pioneering work in deep learning, which earned him the 2018 A.M. Turing Award, “the Nobel Prize of computing,” with Geoffrey Hinton and Yann LeCun.

Bengio is a full professor at Université de Montréal, and the founder and scientific advisor of Mila – Quebec Artificial Intelligence Institute. He is also a senior fellow at CIFAR and co-directs its Learning in Machines & Brains program, serves as special advisor and founding scientific director of IVADO, and holds a Canada CIFAR AI Chair.

In 2019, Bengio was awarded the prestigious Killam Prize and in 2022, he was the most cited computer scientist in the world by h-index. He is a Fellow of the Royal Society of London, Fellow of the Royal Society of Canada, Knight of the Legion of Honor of France and Officer of the Order of Canada. In 2023, he was appointed to the UN’s Scientific Advisory Board for Independent Advice on Breakthroughs in Science and Technology.

Concerned about the social impact of AI, Bengio helped draft the Montréal Declaration for the Responsible Development of Artificial Intelligence and continues to raise awareness about the importance of mitigating the potentially catastrophic risks associated with future AI systems.

Current Students

Jamal Abou Haibeh

Collaborating Alumni - McGill University

Berkes Anaïs

Collaborating researcher - Cambridge University

berkes.anais@mila.quebec

shahana.chatterjee@mila.quebec

Rim Assouel

PhD - Université de Montréal

assouelr@mila.quebec

Shahana Chatterjee

Collaborating researcher - N/A

sanghyeok.choi@mila.quebec

Xiaoyin Chen

PhD - Université de Montréal

xiaoyin.chen@mila.quebec

Sanghyeok Choi

Collaborating researcher - KAIST

PhD - Université de Montréal

aniket.didolkar@mila.quebec

PhD - Université de Montréal

eric.elmoznino@mila.quebec

PhD - Université de Montréal

lena-nehale.ezzine@mila.quebec

Jean-Pierre Falet

PhD - Université de Montréal

jean-pierre.falet@mila.quebec

PhD

pietro.greiner@mila.quebec

Mohsin Hasan

PhD - Université de Montréal

mohsin.hasan@mila.quebec

thomas.jiralerspong@mila.quebec

Moksh Jain

PhD - Université de Montréal

moksh.jain@mila.quebec

PhD - Université de Montréal

Collaborating Alumni - Université de Montréal

younesse.kaddar@mila.quebec

Hyeonah Kim

Postdoctorate - Université de Montréal

hyeonah.kim@mila.quebec

Minsu Kim

Collaborating researcher - Université de Montréal

minsu.kim@mila.quebec

Research Intern - KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

jeongjae.lee@mila.quebec

cristian-dragos.manta@mila.quebec

Song LIU

Collaborating researcher - s.o.

Collaborating researcher

Cristian Dragos Manta

PhD - Université de Montréal

Sarthak Mittal

PhD - Université de Montréal

Independent visiting researcher - Université de Montréal

nguyenph@mila.quebec

Ali Parviz

Collaborating researcher - Ying Wu Coll of Computing

ali.parviz@mila.quebec

Lena Podina

Collaborating researcher - University of Waterloo

elena.podina@mila.quebec

jarrid.rector-brooks@mila.quebec

Jarrid Rector-Brooks

PhD - Université de Montréal

Danyal REHMAN

Postdoctorate - Université de Montréal

danyal.rehman@mila.quebec

oliver.richardson@mila.quebec

Oli RICHARDSON

Postdoctorate - Université de Montréal

Camille Rochefort-Boulanger

PhD - Université de Montréal

rochefoc@mila.quebec

Divya Sharma

Postdoctorate - Université de Montréal

divya.sharma@mila.quebec

Mélisande Astrid Crystal Teng

Collaborating Alumni - Université de Montréal

tengmeli@mila.quebec

alexander.tong@mila.quebec

Alex Tong

Collaborating Alumni - Université de Montréal

Collaborating researcher - University of Cambridge

oszkar.urban@mila.quebec

donna.vakalis@mila.quebec

Donna Vakalis

Collaborating Alumni - Université de Montréal

PhD - Université de Montréal

siddarth.venkatraman@mila.quebec

Collaborating researcher - Université de Montréal

esmeralda.whitammer@mila.quebec

Collaborating Alumni

omar.younis@mila.quebec

Collaborating researcher - Université de Montréal

taeyoung.yun@mila.quebec

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Tianyu Zhang

PhD - Université de Montréal

tianyu.zhang@mila.quebec

PhD - McGill University

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Scaling in the Service of Reasoning & Model-Based ML

April 4, 2023

Yoshua Bengio

Edward J. Hu

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

March 23, 2022

Paul Bertin

Jake P. Taylor-King

Yoshua Bengio

March 15, 2022

Generative Flow Networks

Yoshua Bengio

Publications

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… (see more)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 (published)

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-Raphael Segerie

OSCAR DELANEY

Alessandro Abate

Fazl Barez

Michael K. Cohen

Philip Torr

FERENC HUSZÁR

ANISOARA CALINESCU

GABRIEL DAVIS JONES … (see 2 more)

Robert Trager

2025-08-10

SuperIntelligence - Robotics - Safety & Alignment (published)

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… (see more)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 (published)

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.… (see more) 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

AI4MATH @ International Conference on Machine Learning (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… (see more)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… (see more)-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… (see more)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 (preprint)

Torsional-GFN: a conditional conformation generator for small molecules

Lena Nehale Ezzine

Alex Hernández-García

2025-06-10

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

Structure-Aligned Protein Language Model

Can Chen

David Heurtel-Depeiges

Robert M. Vernon

Christopher J. Langmead

Quentin Fournier

2025-05-21

ArXiv (preprint)

Self-Evolving Curriculum for LLM Reasoning

Nicolas Gontier

Ehsan Kamalloo

2025-05-19

ArXiv (preprint)

Can a Bayesian Oracle Prevent Harm from an Agent?

Michael K. Cohen

Nikolay Malkin

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the … (see more)long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. Such a risk evaluation would need to be performed at run-time to provide a guardrail against dangerous actions of an AI. Noting that different plausible hypotheses about the world could produce very different outcomes, and because we do not know which one is right, we derive bounds on the safety violation probability predicted under the true but unknown hypothesis. Such bounds could be used to reject potentially dangerous actions. Our main results involve searching for cautious but plausible hypotheses, obtained by a maximization that involves Bayesian posteriors over hypotheses. We consider two forms of this result, in the iid case and in the non-iid case, and conclude with open problems towards turning such theoretical results into practical AI guardrails.

2025-05-06

Conference on Uncertainty in Artificial Intelligence (poster)

proceedings.mlr.press

Ant Colony Sampling with GFlowNets for Combinatorial Optimization

Jiwoo Son

Jinkyoo Park

We present the Generative Flow Ant Colony Sampler (GFACS), a novel meta-heuristic method that hierarchically combines amortized inference an… (see more)d parallel stochastic search. Our method first leverages Generative Flow Networks (GFlowNets) to amortize a \emph{multi-modal} prior distribution over combinatorial solution space that encompasses both high-reward and diversified solutions. This prior is iteratively updated via parallel stochastic search in the spirit of Ant Colony Optimization (ACO), leading to the posterior distribution that generates near-optimal solutions. Extensive experiments across seven combinatorial optimization problems demonstrate GFACS's promising performances.

2025-05-02

International Conference on Artificial Intelligence and Statistics (Accept (Poster))