Portrait of Yoshua Bengio

Yoshua Bengio

Core Academic Member
Canada CIFAR AI Chair
Full Professor, Université de Montréal, Department of Computer Science and Operations Research Department
Scientific Director, Leadership Team
Research Topics
Causality
Computational Neuroscience
Deep Learning
Generative Models
Graph Neural Networks
Machine Learning Theory
Medical Machine Learning
Molecular Modeling
Natural Language Processing
Probabilistic Models
Reasoning
Recurrent Neural Networks
Reinforcement Learning
Representation Learning

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 director 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 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

Collaborating Alumni - McGill University
Collaborating Alumni - Université de Montréal
Research Intern - Université de Montréal
PhD - Université de Montréal
Collaborating Alumni - Université du Québec à Rimouski
Independent visiting researcher
Co-supervisor :
PhD - Université de Montréal
Collaborating Alumni - UQAR
PhD - Université de Montréal
Collaborating researcher - N/A
Principal supervisor :
PhD - Université de Montréal
Collaborating researcher - KAIST
PhD - Université de Montréal
PhD - Université de Montréal
Collaborating Alumni - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
PhD - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Research Intern - Barcelona University
Research Intern - Université de Montréal
Research Intern - Université de Montréal
Research Intern
Postdoctorate - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Master's Research - Université de Montréal
Co-supervisor :
Collaborating Alumni - Université de Montréal
Collaborating researcher - Université de Montréal
Collaborating Alumni - Université de Montréal
Collaborating Alumni - Université de Montréal
Collaborating Alumni
PhD - Université de Montréal
Principal supervisor :
Collaborating Alumni - Imperial College London
PhD - Université de Montréal
Collaborating Alumni - Université de Montréal
Collaborating Alumni - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
Collaborating researcher - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
Postdoctorate - Université de Montréal
Principal supervisor :
Independent visiting researcher - Université de Montréal
Collaborating researcher - Ying Wu Coll of Computing
PhD - University of Waterloo
Principal supervisor :
Collaborating Alumni - Max-Planck-Institute for Intelligent Systems
PhD - Université de Montréal
Postdoctorate - Université de Montréal
Independent visiting researcher - Université de Montréal
Postdoctorate - Université de Montréal
PhD - Université de Montréal
Principal supervisor :
Collaborating Alumni - Université de Montréal
Postdoctorate - Université de Montréal
Master's Research - Université de Montréal
Collaborating Alumni - Université de Montréal
Research Intern - Université de Montréal
Master's Research - Université de Montréal
Collaborating Alumni
Independent visiting researcher - Technical University of Munich
Postdoctorate - Polytechnique Montréal
Co-supervisor :
PhD - Université de Montréal
Co-supervisor :
Collaborating researcher - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)
Principal supervisor :
Postdoctorate - Université de Montréal
Postdoctorate - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Collaborating Alumni - Université de Montréal
Collaborating researcher
Collaborating researcher - KAIST
PhD - McGill University
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
PhD - McGill University
Principal supervisor :

Publications

Sources of richness and ineffability for phenomenally conscious states
Xu Ji
Eric Elmoznino
George Deane
Axel Constant
Jonathan Simon
Distributional GFlowNets with Quantile Flows
Dinghuai Zhang
Ling Pan
Ricky T. Q. Chen
Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating com… (see more)plex combinatorial structure through a series of decision-making steps. Despite being inspired from reinforcement learning, the current GFlowNet framework is relatively limited in its applicability and cannot handle stochasticity in the reward function. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. By parameterizing each edge flow through their quantile functions, our proposed \textit{quantile matching} GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty. Moreover, we find that the distributional approach can achieve substantial improvement on existing benchmarks compared to prior methods due to our enhanced training algorithm, even in settings with deterministic rewards.
Computing Power and the Governance of Artificial Intelligence
Girish Sastry
Lennart Heim
Haydn Belfield
Markus Anderljung
Miles Brundage
Julian Hazell
Cullen C. O'keefe
Gillian K. Hadfield
Richard Ngo
Konstantin Pilz
George Gor
Emma Bluemke
Sarah Shoker
Janet Egan
Robert F. Trager
Shahar Avin
Adrian Weller
Diane Coyle
Computing power, or"compute,"is crucial for the development and deployment of artificial intelligence (AI) capabilities. As a result, govern… (see more)ments and companies have started to leverage compute as a means to govern AI. For example, governments are investing in domestic compute capacity, controlling the flow of compute to competing countries, and subsidizing compute access to certain sectors. However, these efforts only scratch the surface of how compute can be used to govern AI development and deployment. Relative to other key inputs to AI (data and algorithms), AI-relevant compute is a particularly effective point of intervention: it is detectable, excludable, and quantifiable, and is produced via an extremely concentrated supply chain. These characteristics, alongside the singular importance of compute for cutting-edge AI models, suggest that governing compute can contribute to achieving common policy objectives, such as ensuring the safety and beneficial use of AI. More precisely, policymakers could use compute to facilitate regulatory visibility of AI, allocate resources to promote beneficial outcomes, and enforce restrictions against irresponsible or malicious AI development and usage. However, while compute-based policies and technologies have the potential to assist in these areas, there is significant variation in their readiness for implementation. Some ideas are currently being piloted, while others are hindered by the need for fundamental research. Furthermore, naive or poorly scoped approaches to compute governance carry significant risks in areas like privacy, economic impacts, and centralization of power. We end by suggesting guardrails to minimize these risks from compute governance.
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Tara Akhound-Sadegh
Jarrid Rector-Brooks
Joey Bose
Sarthak Mittal
Pablo Lemos
Cheng-Hao Liu
Marcin Sendera
Nikolay Malkin
Alexander Tong
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-… (see more)body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant
On diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling
Marcin Sendera
Minsu Kim
Sarthak Mittal
Pablo Lemos
Luca Scimeca
Jarrid Rector-Brooks
Alexandre Adam
Nikolay Malkin
We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We ben… (see more)chmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks). Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work. We also propose a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer, and show that it improves the quality of samples on a variety of target distributions. Our code for the sampling methods and benchmarks studied is made public at https://github.com/GFNOrg/gfn-diffusion as a base for future work on diffusion models for amortized inference.
Amortizing intractable inference in large language models
Edward J Hu
Moksh J. Jain
Eric Elmoznino
Younesse Kaddar
Nikolay Malkin
Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This l… (see more)imits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many tasks of interest -- including sequence continuation, infilling, and other forms of constrained generation -- involve sampling from intractable posterior distributions. We address this limitation by using amortized Bayesian inference to sample from these intractable posteriors. Such amortization is algorithmically achieved by fine-tuning LLMs via diversity-seeking reinforcement learning algorithms: generative flow networks (GFlowNets). We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem and demonstrate that our approach enables data-efficient adaptation of LLMs to tasks that require multi-step rationalization and tool use.
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Harry Zhao
Harry Zhao 0001
Mingde Zhao
Safa Alver
Harm van Seijen
Romain Laroche
Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstracti… (see more)ons to generalize better in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and thus enables sparse decision-making and focused computation on the relevant parts of the environment. The decomposition relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guarantees under appropriate assumptions and establish where our approach is expected to be helpful. Generalization-focused experiments validate Skipper’s significant advantage in zero-shot generalization, compared to some existing state-of-the-art hierarchical planning methods.
Cycle Consistency Driven Object Discovery
Aniket Rajiv Didolkar
Anirudh Goyal
Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. … (see more)Existing approaches facilitate object discovery by representing objects as fixed-size vectors, called ``slots'' or ``object files''. While these approaches have shown promise in certain scenarios, they still exhibit certain limitations. First, they rely on architectural priors which can be unreliable and usually require meticulous engineering to identify the correct objects. Second, there has been a notable gap in investigating the practical utility of these representations in downstream tasks. To address the first limitation, we introduce a method that explicitly optimizes the constraint that each object in a scene should be associated with a distinct slot. We formalize this constraint by introducing consistency objectives which are cyclic in nature. By integrating these consistency objectives into various existing slot-based object-centric methods, we showcase substantial improvements in object-discovery performance. These enhancements consistently hold true across both synthetic and real-world scenes, underscoring the effectiveness and adaptability of the proposed approach. To tackle the second limitation, we apply the learned object-centric representations from the proposed method to two downstream reinforcement learning tasks, demonstrating considerable performance enhancements compared to conventional slot-based and monolithic representation learning methods. Our results suggest that the proposed approach not only improves object discovery, but also provides richer features for downstream tasks.
Delta-AI: Local objectives for amortized inference in sparse graphical models
Jean-Pierre R. Falet
Hae Beom Lee
Nikolay Malkin
Chen Sun
Dragos Secrieru
Dinghuai Zhang
We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call …
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Dinghuai Zhang
Ricky T. Q. Chen
Cheng-Hao Liu
Expected flow networks in stochastic environments and two-player zero-sum games
Marco Jiralerspong
Bilun Sun
Danilo Vucetic
Tianyu Zhang
Nikolay Malkin
Local Search GFlowNets
Minsu Kim
Taeyoung Yun
Emmanuel Bengio
Dinghuai Zhang
Sungsoo Ahn
Jinkyoo Park
Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their re… (see more)wards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue. Our main idea is to explore the local neighborhood via backtracking and reconstruction guided by backward and forward policies, respectively. This allows biasing the samples toward high-reward solutions, which is not possible for a typical GFlowNet solution generation scheme, which uses the forward policy to generate the solution from scratch. Extensive experiments demonstrate a remarkable performance improvement in several biochemical tasks. Source code is available: https://github.com/dbsxodud-11/ls_gfn.