Yoshua Bengio

Biography

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

For more information please contact Marie-Josée Beauchamp, Administrative Assistant at marie-josee.beauchamp@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

Mohammed Abukalam

Collaborating Alumni - Université de Montréal

Berkes Anaïs

Collaborating researcher - Cambridge University

Principal supervisor :

Rim Assouel

PhD - Université de Montréal

Stefan Bauer

Independent visiting researcher

Co-supervisor :

Paul Bertin

PhD - Université de Montréal

Joyce Chai

Independent visiting researcher

Principal supervisor :

Siva Reddy

Shahana Chatterjee

Collaborating researcher - N/A

Principal supervisor :

Xiaoyin Chen

PhD - Université de Montréal

Sanghyeok Choi

Collaborating researcher - KAIST

Collaborating Alumni - Université de Montréal

PhD - Université de Montréal

Collaborating Alumni - Université de Montréal

Co-supervisor :

Loubna Benabbou

Desmond Elliott

Independent visiting researcher

Principal supervisor :

PhD - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Jean-Pierre Falet

PhD - Université de Montréal

Leo Feng

PhD - Université de Montréal

PhD

PhD - Université de Montréal

Edward Hu

PhD - Université de Montréal

Moksh Jain

PhD - Université de Montréal

PhD - Université de Montréal

Principal supervisor :

Collaborating Alumni - Université de Montréal

Hyeonah Kim

Postdoctorate - Université de Montréal

Principal supervisor :

Alex Hernandez-Garcia

Salem Lahlou

Collaborating Alumni - Université de Montréal

Tabitha Edith Lee

Postdoctorate - Université de Montréal

Principal supervisor :

Collaborating Alumni

Zhen Liu

Collaborating Alumni - Université de Montréal

Principal supervisor :

Liam Paull

Kanika Madan

PhD - Université de Montréal

Collaborating Alumni - Université de Montréal

Cristian Dragos Manta

PhD - Université de Montréal

Co-supervisor :

Dhanya Sridhar

Sarthak Mittal

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Postdoctorate - Université de Montréal

Principal supervisor :

Independent visiting researcher - Université de Montréal

Padideh Nouri

PhD - Université de Montréal

Principal supervisor :

Ali Parviz

Collaborating researcher - Ying Wu Coll of Computing

Lena Podina

Collaborating researcher - University of Waterloo

Principal supervisor :

Nassim Rahaman

Collaborating Alumni - Max-Planck-Institute for Intelligent Systems

Amine RAZIG

Collaborating researcher - Université de Montréal

Co-supervisor :

Loubna Benabbou

Jarrid Rector-Brooks

PhD - Université de Montréal

Danyal REHMAN

Postdoctorate - Université de Montréal

James Requeima

Independent visiting researcher - Université de Montréal

Oli RICHARDSON

Postdoctorate - Université de Montréal

Camille Rochefort-Boulanger

PhD - Université de Montréal

Principal supervisor :

Julie Hussin

Abhik Roychoudhury Roychoudhury

Independent visiting researcher

Principal supervisor :

Siva Reddy

Luca Scimeca

Postdoctorate - Université de Montréal

Collaborating Alumni - Université de Montréal

Marcin Sendera

Collaborating Alumni - Université de Montréal

Divya Sharma

Postdoctorate

Co-supervisor :

Alex Hernandez-Garcia

Marco Stock

Independent visiting researcher - Technical University of Munich

Mélisande Astrid Crystal Teng

PhD - Université de Montréal

Co-supervisor :

Hugo Larochelle

Ivan Titov

Independent visiting researcher

Principal supervisor :

Siva Reddy

Alex Tong

Collaborating Alumni - Université de Montréal

Postdoctorate - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Principal supervisor :

Collaborating researcher

Collaborating researcher - Université de Montréal

Nicole Zhang

PhD - McGill University

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Aaron Courville

Tianyu Zhang

PhD - Université de Montréal

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Harry Zhao

Collaborating Alumni - McGill University

Principal supervisor :

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

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise

Luca Scimeca

Thomas Jiralerspong

Berton Earnshaw

Jason Hartford

Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In th… (see more)is work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. We introduce an anisotropic noise operator that shapes these biases by replacing the isotropic forward covariance with a structured, frequency-diagonal covariance. This operator unifies band-pass masks and power-law weightings, allowing us to emphasize or suppress designated frequency bands, while keeping the forward process Gaussian. We refer to this as spectrally anisotropic Gaussian diffusion (SAGD). In this work, we derive the score relation for anisotropic covariances and show that, under full support, the learned score converges to the true data score as

2025-10-07

ArXiv (preprint)

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

Tianyu Zhang

Andrew Robert Williams

Phillip Wozny

Kai-Hendrik Cohrs

Koen Ponse

Marco Jiralerspong

Soham Rajesh Phade

Sunil Srinivasa

Li Li

Yang Zhang

Prateek Gupta

Erman Acar

Irina Rish

Stephan Zheng

Global cooperation on climate change mitigation is essential to limit temperature increases while supporting long-term, equitable economic g… (see more)rowth and sustainable development. Achieving such cooperation among diverse regions, each with different incentives, in a dynamic environment shaped by complex geopolitical and economic factors, without a central authority, is a profoundly challenging game-theoretic problem. This article introduces RICE-N, a multi-region integrated assessment model that simulates the global climate, economy, and climate negotiations and agreements. RICE-N uses multi-agent reinforcement learning (MARL) to encourage agents to develop strategic behaviors based on the environmental dynamics and the actions of the others. We present two negotiation protocols: (1) Bilateral Negotiation, an exemplary protocol and (2) Basic Club, inspired from Climate Clubs and the carbon border adjustment mechanism (Nordhaus, 2015; Comissions, 2022). We compare their impact against a no-negotiation baseline with various mitigation strategies, showing that both protocols significantly reduce temperature growth at the cost of a minor drop in production while ensuring a more equitable distribution of the emission reduction costs.

2025-10-06

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

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 n… (see more)aturally 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.

2025-10-06

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

Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models

Any well-behaved generative model over a variable …

2025-10-06

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

Rejecting Hallucinated State Targets during Planning

Romain Laroche

In planning processes of computational decision-making agents, generative or predictive models are often used as "generators" to propose "ta… (see more)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.

2025-10-06

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

Towards a Formal Theory of Representational Compositionality

Compositionality is believed to be fundamental to intelligence. In humans, it underlies the structure of thought and language. In AI, it ena… (see more)bles a powerful form of out-of-distribution generalization, in which a model systematically adapts to novel combinations of known concepts. However, while we have strong intuitions about what compositionality is, we lack satisfying formal definitions for it. Here, we propose such a definition called representational compositionality that is conceptually simple, quantitative, and grounded in algorithmic information theory. Intuitively, representational compositionality states that a compositional representation is both expressive and describable as a simple function of parts. We validate our definition on both real and synthetic data, and show how it unifies disparate intuitions from across the literature in both AI and cognitive science. We hope that our definition can inspire the design of novel, theoretically-driven models that better capture the mechanisms of compositional thought. We make our code available at https://github.com/EricElmoznino/complexity_compositionality.

2025-10-06

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

Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study

Alexandre AGM Duval

Alex Hernandez-Garcia

Félix Therrien

Efficient and inexpensive energy storage is essential for accelerating the adoption of renewable energy and ensuring a stable supply, despit… (see more)e fluctuations in sources such as wind and solar. Electrocatalysts play a key role in hydrogen energy storage (HES), allowing the energy to be stored as hydrogen. However, the development of affordable and high-performance catalysts for this process remains a significant challenge. We introduce Catalyst GFlowNet, a generative model that leverages machine learning-based predictors of formation and adsorption energy to design crystal surfaces that act as efficient catalysts. We demonstrate the performance of the model through a proof-of-concept application to the hydrogen evolution reaction, a key reaction in HES, for which we successfully identified platinum as the most efficient known catalyst. In future work, we aim to extend this approach to the oxygen evolution reaction, where current optimal catalysts are expensive metal oxides, and open the search space to discover new materials. This generative modeling framework offers a promising pathway for accelerating the search for novel and efficient catalysts.

2025-10-02

ArXiv (preprint)

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Brian R. Bartoldson

Bhavya Kailkhura

Glen Berseth

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (see more) 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.

2025-09-30

ArXiv (preprint)

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Brian R. Bartoldson

Bhavya Kailkhura

Glen Berseth

Moksh J. Jain

2025-09-30

ArXiv (preprint)

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Brian R. Bartoldson

Bhavya Kailkhura

Glen Berseth

Moksh J. Jain

2025-09-30

ArXiv (preprint)

Active Attacks: Red-teaming LLMs via Adaptive Environments

Taeyoung YUN

Pierre-Luc St-Charles

Jinkyoo Park

Minsu Kim

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults,… (see more) sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt engineering, attacker LLMs can be trained with reinforcement learning (RL) to automatically generate such prompts using only a toxicity classifier as a reward. However, capturing a wide range of harmful behaviors is a significant challenge that requires explicit diversity objectives. Existing diversity-seeking RL methods often collapse to limited modes: once high-reward prompts are found, exploration of new regions is discouraged. Inspired by the active learning paradigm that encourages adaptive exploration, we introduce \textit{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its attacks as the victim evolves. By periodically safety fine-tuning the victim LLM with collected attack prompts, rewards in exploited regions diminish, which forces the attacker to seek unexplored vulnerabilities. This process naturally induces an easy-to-hard exploration curriculum, where the attacker progresses beyond easy modes toward increasingly difficult ones. As a result, Active Attacks uncovers a wide range of local attack modes step by step, and their combination achieves wide coverage of the multi-mode distribution. Active Attacks, a simple plug-and-play module that seamlessly integrates into existing RL objectives, unexpectedly outperformed prior RL-based methods -- including GFlowNets, PPO, and REINFORCE -- by improving cross-attack success rates against GFlowNets, the previous state-of-the-art, from 0.07% to 31.28% (a relative gain greater than

2025-09-26

ArXiv (preprint)

Graph Dreamer: Temporal Graph World Models for Sample-Efficient and Generalisable Reinforcement Learning

Anaïs Berkes

Donna Vakalis