Portrait de Yoshua Bengio

Yoshua Bengio

Membre académique principal

Chaire en IA Canada-CIFAR

Professeur titulaire, Université de Montréal, Département d'informatique et de recherche opérationnelle

Fondateur et Conseiller scientifique, Équipe de direction

Sujets de recherche

Apprentissage automatique médical

Apprentissage de représentations

Apprentissage par renforcement

Apprentissage profond

Causalité

Modèles génératifs

Modèles probabilistes

Modélisation moléculaire

Neurosciences computationnelles

Raisonnement

Réseaux de neurones en graphes

Réseaux de neurones récurrents

Théorie de l'apprentissage automatique

Traitement du langage naturel

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 :

Doctorat - UdeM

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

Aniket Didolkar

Doctorat - UdeM

Abdessamad EL KABID

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Loubna Benabbou

Desmond Elliott

Visiteur de recherche indépendant

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Co-superviseur⋅e :

Guillaume Lajoie

Doctorat - UdeM

Jean-Pierre Falet

Doctorat - UdeM

Doctorat

Doctorat - UdeM

Doctorat - UdeM

Thomas Jiralerspong

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

Younesse Kaddar

Collaborateur·rice alumni - UdeM

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 :

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

Visiteur de recherche indépendant - UdeM

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche - Ying Wu Coll of Computing

Collaborateur·rice de recherche - University of Waterloo

Superviseur⋅e principal⋅e :

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

Collaborateur·rice de recherche - UdeM

Co-superviseur⋅e :

Loubna Benabbou

Jarrid Rector-Brooks

Doctorat - UdeM

Postdoctorat - UdeM

Postdoctorat - UdeM

Camille Rochefort-Boulanger

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Dragos Secrieru

Collaborateur·rice alumni - UdeM

Postdoctorat

Co-superviseur⋅e :

Alex Hernández-García

Collaborateur·rice alumni - Polytechnique

Co-superviseur⋅e :

Pierre-Luc Bacon

Mélisande Astrid Crystal Teng

Doctorat - UdeM

Co-superviseur⋅e :

Hugo Larochelle

Collaborateur·rice de recherche

Superviseur⋅e principal⋅e :

Collaborateur·rice alumni - UdeM

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Siddarth Venkatraman

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche

Collaborateur·rice de recherche - UdeM

Doctorat - UdeM

Doctorat - McGill

Superviseur⋅e principal⋅e :

Mathieu Blanchette

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Aaron Courville

Collaborateur·rice alumni - McGill

Superviseur⋅e principal⋅e :

Billets de blogue

Generic thumbnail for Mila Blog articles.

22 février 2024

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

par

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Scaling in the service of reasoning & model-based ML

4 avril 2023

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

par

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

23 mars 2022

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

par

Jake P. Taylor-King

Generative Flow Networks

15 mars 2022

Les réseaux de flot génératifs

par

Publications

Adaptive Teachers for Amortized Samplers

Emmanuel Bengio

Jarrid Rector-Brooks

Sungsoo Ahn

Jinkyoo Park

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (voir plus)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \teacher) to guide the training of the primary amortized sampler (the \student). The \teacher, an auxiliary behavior model, is trained to sample high-loss regions of the \student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage. Source code is available at https://github.com/alstn12088/adaptive-teacher.

2025-01-21

ICLR.cc/2025/Conference (poster)

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… (voir plus)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.

2025-01-21

aistats.org/AISTATS/2025/Conference (poster)

proceedings.mlr.press

AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular Assembly

Hongyu Guo

2025-01-21

ICLR.cc/2025/Conference (poster)

BigDocs: An Open Dataset for Training Multi-modal Models on Document and Code Tasks

Xiangru Jian

Siba Smarak Panigrahi

Akshay Kalkunte

François Savard

Amirhossein Abaskohi

Pierre-Andre Noel

Mats Leon Richter

Saverio Vadacchino

Shubham Agarwal

Sanket Biswas … (voir 23 de plus)

Sara Shanian

Noah Bolger

Kurt MacDonald

Simon Fauvel

Sathwik Tejaswi

Srinivas Sunkara

Joao Monteiro

Krishnamurthy Dj Dvijotham

Torsten Scholak

Nicolas Chapados

Sepideh Kharagani

Sean Hughes

M. Özsu

Marco Pedersoli

Christopher Pal

Perouz Taslakian

Sai Rajeswar

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows,… (voir plus) extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Despite this, their use in commercial applications is often limited due to limited access to training data and restrictive licensing, which hinders open access. To address these limitations, we introduce BigDocs-7.5M, a high-quality, open-access dataset comprising 7.5 million multimodal documents across 30 tasks. We use an efficient data curation process to ensure our data is high-quality and license-permissive. Our process emphasizes accountability, responsibility, and transparency through filtering rules, traceable metadata, and careful content analysis. Additionally, we introduce BigDocs-Bench, a benchmark suite with 10 novel tasks where we create datasets that reflect real-world use cases involving reasoning over Graphical User Interfaces (GUI) and code generation from images. Our experiments show that training with BigDocs-Bench improves average performance up to 25.8% over closed-source GPT-4o in document reasoning and structured output tasks such as Screenshot2HTML or Image2Latex generation. Finally, human evaluations showed a preference for outputs from models trained on BigDocs over GPT-4o. This suggests that BigDocs can help both academics and the open-source community utilize and improve AI tools to enhance multimodal capabilities and document reasoning. The project is hosted at https://bigdocs.github.io .

2025-01-21

International Conference on Learning Representations (poster)

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets

Tim Z. Xiao

Weiyang Liu

While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetun… (voir plus)e pretrained diffusion models with some reward functions that are either designed by experts or learned from small-scale datasets. Existing post-training methods for reward finetuning of diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. In response to this challenge, we take inspiration from recent successes in generative flow networks (GFlowNets) and propose a reinforcement learning method for diffusion model finetuning, dubbed Nabla-GFlowNet (abbreviated as

2025-01-21

ICLR.cc/2025/Conference (poster)

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Haebin Seong

Dong Bok Lee

Minki Kang

Dominik Wagner

Juho Lee

Sung Ju Hwang

Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsibl… (voir plus)e deployment of LLMs in real-world applications. However, deploying existing safety guard models with billions of parameters alongside LLMs on mobile devices is impractical due to substantial memory requirements and latency. To reduce this cost, we distill a large teacher safety guard model into a smaller one using a labeled dataset of instruction-response pairs with binary harmfulness labels. Due to the limited diversity of harmful instructions in the existing labeled dataset, naively distilled models tend to underperform compared to larger models. To bridge the gap between small and large models, we propose HarmAug, a simple yet effective data augmentation method that involves jailbreaking an LLM and prompting it to generate harmful instructions. Given a prompt such as, "Make a single harmful instruction prompt that would elicit offensive content", we add an affirmative prefix (e.g., "I have an idea for a prompt:") to the LLM's response. This encourages the LLM to continue generating the rest of the response, leading to sampling harmful instructions. Another LLM generates a response to the harmful instruction, and the teacher model labels the instruction-response pair. We empirically show that our HarmAug outperforms other relevant baselines. Moreover, a 435-million-parameter safety guard model trained with HarmAug achieves an F1 score comparable to larger models with over 7 billion parameters, and even outperforms them in AUPRC, while operating at less than 25% of their computational cost.

2025-01-21

ICLR.cc/2025/Conference (poster)

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

David Dobre

Juho Lee

Sung Ju Hwang

Kenji Kawaguchi

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of lar… (voir plus)ge language models (LLMs). Developing effective protection against many modes of attack prompts requires discovering diverse attacks. Automated red-teaming typically uses reinforcement learning to fine-tune an attacker language model to generate prompts that elicit undesirable responses from a target LLM, as measured, for example, by an auxiliary toxicity classifier. We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks. As a flexible and probabilistically principled alternative, we propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts. We find that the attacks generated by our method are effective against a wide range of target LLMs, both with and without safety tuning, and transfer well between target LLMs. Finally, we demonstrate that models safety-tuned using a dataset of red-teaming prompts generated by our method are robust to attacks from other RL-based red-teaming approaches.

2025-01-21

International Conference on Learning Representations (poster)

MAP: Low-Compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

Zhiqi Bu

Huan He

Yonghui Wu

Jiang Bian

Yong Chen

Model merging has emerged as an effective approach to combine multiple single-task models into a multitask model. This process typically inv… (voir plus)olves computing a weighted average of the model parameters without any additional training. Existing model-merging methods focus on enhancing average task accuracy. However, interference and conflicts between the objectives of different tasks can lead to trade-offs during the merging process. In real-world applications, a set of solutions with various trade-offs can be more informative, helping practitioners make decisions based on diverse preferences. In this paper, we introduce a novel and low-compute algorithm, Model Merging with Amortized Pareto Front (MAP). MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved. It amortizes the substantial computational cost of evaluations needed to estimate the Pareto front by using quadratic approximation surrogate models derived from a pre-selected set of scaling coefficients. Experimental results on vision and natural language processing tasks demonstrate that MAP can accurately identify the Pareto front, providing practitioners with flexible solutions to balance competing task objectives. We also introduce Bayesian MAP for scenarios with a relatively low number of tasks and Nested MAP for situations with a high number of tasks, further reducing the computational cost of evaluation.

2025-01-21

ICLR.cc/2025/Conference (poster)

Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold

Lazar Atanackovic

Xi Zhang

Brandon Amos

Mathieu Blanchette

Leo J. Lee

Kirill Neklyudov

Numerous biological and physical processes can be modeled as systems of interacting entities evolving continuously over time, e.g. the dynam… (voir plus)ics of communicating cells or physical particles. Learning the dynamics of such systems is essential for predicting the temporal evolution of populations across novel samples and unseen environments. Flow-based models allow for learning these dynamics at the population level - they model the evolution of the entire distribution of samples. However, current flow-based models are limited to a single initial population and a set of predefined conditions which describe different dynamics. We argue that multiple processes in natural sciences have to be represented as vector fields on the Wasserstein manifold of probability densities. That is, the change of the population at any moment in time depends on the population itself due to the interactions between samples. In particular, this is crucial for personalized medicine where the development of diseases and their respective treatment response depend on the microenvironment of cells specific to each patient. We propose Meta Flow Matching (MFM), a practical approach to integrate along these vector fields on the Wasserstein manifold by amortizing the flow model over the initial populations. Namely, we embed the population of samples using a Graph Neural Network (GNN) and use these embeddings to train a Flow Matching model. This gives MFM the ability to generalize over the initial distributions, unlike previously proposed methods. We demonstrate the ability of MFM to improve the prediction of individual treatment responses on a large-scale multi-patient single-cell drug screen dataset.

2025-01-21

International Conference on Learning Representations (poster)

Structure Language Models for Protein Conformation Generation

Stephen Z. Lu

Hongyu Guo

Proteins adopt multiple structural conformations to perform their diverse biological functions, and understanding these conformations is cru… (voir plus)cial for advancing drug discovery. Traditional physics-based simulation methods often struggle with sampling equilibrium conformations and are computationally expensive. Recently, deep generative models have shown promise in generating protein conformations as a more efficient alternative. However, these methods predominantly rely on the diffusion process within a 3D geometric space, which typically centers around the vicinity of metastable states and is often inefficient in terms of runtime. In this paper, we introduce Structure Language Modeling (SLM) as a novel framework for efficient protein conformation generation. Specifically, the protein structures are first encoded into a compact latent space using a discrete variational auto-encoder, followed by conditional language modeling that effectively captures sequence-specific conformation distributions. This enables a more efficient and interpretable exploration of diverse ensemble modes compared to existing methods. Based on this general framework, we instantiate SLM with various popular LM architectures as well as proposing the ESMDiff, a novel BERT-like structure language model fine-tuned from ESM3 with masked diffusion. We verify our approach in various scenarios, including the equilibrium dynamics of BPTI, conformational change pairs, and intrinsically disordered proteins. SLM provides a highly efficient solution, offering a 20-100x speedup than existing methods in generating diverse conformations, shedding light on promising avenues for future research.

2025-01-21

ICLR.cc/2025/Conference (poster)

On the Transfer of Object-Centric Representation Learning.

Aniket Rajiv Didolkar

Andrii Zadaianchuk

Michael Curtis Mozer

Georg Martius

Maximilian Seitzer

2025-01-21

ICLR.cc/2025/Conference (poster)

Towards Improving Exploration Through Sibling Augmented GFlowNets

Emmanuel Bengio

2025-01-21

ICLR.cc/2025/Conference (poster)