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
Site web
Google Scholar

Biographie

*Pour toute demande média, veuillez écrire à medias@mila.quebec.

Pour plus d’information, contactez Marie-Josée Beauchamp, adjointe administrative à marie-josee.beauchamp@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
Github
Google Scholar
Mohammed Abukalam
Collaborateur·rice alumni - UdeM
Github
Berkes Anaïs
Collaborateur·rice de recherche - Cambridge University
Superviseur⋅e principal⋅e :
David Rolnick
Site web
Github
Google Scholar
Rim Assouel
Doctorat - UdeM
Stefan Bauer
Visiteur de recherche indépendant
Co-superviseur⋅e :
Guillaume Lajoie
Google Scholar
Paul Bertin
Doctorat - UdeM
Joyce Chai
Visiteur de recherche indépendant
Superviseur⋅e principal⋅e :
Siva Reddy
Shahana Chatterjee
Collaborateur·rice de recherche - N/A
Superviseur⋅e principal⋅e :
David Rolnick
Google Scholar
Xiaoyin Chen
Doctorat - UdeM
Sanghyeok Choi
Collaborateur·rice de recherche - KAIST
Site web
Github
Google Scholar
Tristan Deleu
Collaborateur·rice alumni - UdeM
Site web
Github
Google Scholar
Aniket Didolkar
Doctorat - UdeM
Site web
Github
Google Scholar
Abdessamad EL KABID
Collaborateur·rice alumni - UdeM
Co-superviseur⋅e :
Loubna Benabbou
Desmond Elliott
Visiteur de recherche indépendant
Superviseur⋅e principal⋅e :
Siva Reddy
Site web
Google Scholar
Eric Elmoznino
Doctorat - UdeM
Co-superviseur⋅e :
Guillaume Lajoie
Site web
Github
Google Scholar
Léna Ezzine
Doctorat - UdeM
Jean-Pierre Falet
Doctorat - UdeM
Site web
Github
Google Scholar
Leo Feng
Doctorat - UdeM
Site web
Google Scholar
Pietro Greiner
Doctorat
Google Scholar
Mohsin Hasan
Doctorat - UdeM
Site web
Github
Google Scholar
Edward Hu
Doctorat - UdeM
Moksh Jain
Doctorat - UdeM
Site web
Github
Google Scholar
Thomas Jiralerspong
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Guillaume Lajoie
Site web
Github
Google Scholar
Younesse Kaddar
Collaborateur·rice alumni - UdeM
Site web
Github
Hyeonah Kim
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Alex Hernandez-Garcia
Salem Lahlou
Collaborateur·rice alumni - UdeM
Tabitha Edith Lee
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Glen Berseth
Site web
Github
Google Scholar
Zhen Liu
Collaborateur·rice alumni - UdeM
Superviseur⋅e principal⋅e :
Liam Paull
Chenghao Liu
Collaborateur·rice alumni
Site web
Github
Google Scholar
Kanika Madan
Doctorat - UdeM
Nikolay Malkin
Collaborateur·rice alumni - UdeM
Site web
Github
Google Scholar
Cristian Dragos Manta
Doctorat - UdeM
Co-superviseur⋅e :
Dhanya Sridhar
Github
Sarthak Mittal
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Guillaume Lajoie
Site web
Github
Google Scholar
Jama Mohamud
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Mirco Ravanelli
Site web
Github
Google Scholar
Cyrus Neary
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Glen Berseth
Site web
Github
Google Scholar
Phong Nguyen
Visiteur de recherche indépendant - UdeM
Padideh Nouri
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Doina Precup
Site web
Github
Google Scholar
Ali Parviz
Collaborateur·rice de recherche - Ying Wu Coll of Computing
Google Scholar
Lena Podina
Collaborateur·rice de recherche - University of Waterloo
Superviseur⋅e principal⋅e :
David Rolnick
Google Scholar
Nassim Rahaman
Collaborateur·rice alumni - Max-Planck-Institute for Intelligent Systems
Amine RAZIG
Collaborateur·rice de recherche - UdeM
Co-superviseur⋅e :
Loubna Benabbou
Site web
Jarrid Rector-Brooks
Doctorat - UdeM
Danyal REHMAN
Postdoctorat - UdeM
Github
James Requeima
Visiteur de recherche indépendant - UdeM
Oli RICHARDSON
Postdoctorat - UdeM
Site web
Google Scholar
Camille Rochefort-Boulanger
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Julie Hussin
Github
Abhik Roychoudhury Roychoudhury
Visiteur de recherche indépendant
Superviseur⋅e principal⋅e :
Siva Reddy
Github
Luca Scimeca
Postdoctorat - UdeM
Site web
Github
Google Scholar
Dragos Secrieru
Collaborateur·rice alumni - UdeM
Marcin Sendera
Collaborateur·rice alumni - UdeM
Github
Google Scholar
Divya Sharma
Postdoctorat
Co-superviseur⋅e :
Alex Hernandez-Garcia
Site web
Github
Marco Stock
Visiteur de recherche indépendant - Technical University of Munich
Github
Mélisande Astrid Crystal Teng
Doctorat - UdeM
Co-superviseur⋅e :
Hugo Larochelle
Site web
Github
Ivan Titov
Visiteur de recherche indépendant
Superviseur⋅e principal⋅e :
Siva Reddy
Site web
Google Scholar
Alex Tong
Collaborateur·rice alumni - UdeM
Site web
Github
Google Scholar
Donna Vakalis
Postdoctorat - UdeM
Co-superviseur⋅e :
David Rolnick
Site web
Github
Google Scholar
Siddarth Venkatraman
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Glen Berseth
Site web
Github
Google Scholar
Omar G. Younis
Collaborateur·rice de recherche
Site web
Github
Google Scholar
Taeyoung YUN
Collaborateur·rice de recherche - UdeM
Github
Tianyu Zhang
Doctorat - UdeM
Site web
Github
Google Scholar
Nicole Zhang
Doctorat - McGill
Superviseur⋅e principal⋅e :
Mathieu Blanchette
Site web
Github
Google Scholar
Dinghuai Zhang
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Aaron Courville
Site web
Harry Zhao
Collaborateur·rice alumni - McGill
Superviseur⋅e principal⋅e :
Doina Precup
Site web
Github
Google Scholar

Publications

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
Tianyu Zhang
Suyuchen Wang
Li Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured … (voir plus)texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
2024-06-10
ArXiv (prépublication)
arxiv.org
arxiv.org
VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
Tianyu Zhang
Suyuchen Wang
Li Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured … (voir plus)texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
2024-06-10
ArXiv (prépublication)
arxiv.org
arxiv.org
VCR: Visual Caption Restoration
Tianyu Zhang
Suyuchen Wang
Lu Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured … (voir plus)texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
2024-06-10
ArXiv (prépublication)
doi.org
arxiv.org
VCR: Visual Caption Restoration
Tianyu Zhang
Suyuchen Wang
Lu Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured … (voir plus)texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
2024-06-10
ArXiv (prépublication)
doi.org
arxiv.org
VCR: Visual Caption Restoration
Tianyu Zhang
Suyuchen Wang
Lu Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured … (voir plus)texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.
2024-06-10
ArXiv (prépublication)
doi.org
arxiv.org
Baking Symmetry into GFlowNets
George Ma
Emmanuel Bengio
Yoshua Bengio
Dinghuai Zhang
GFlowNets have exhibited promising performance in generating diverse candidates with high rewards. These networks generate objects increment… (voir plus)ally and aim to learn a policy that assigns probability of sampling objects in proportion to rewards. However, the current training pipelines of GFlowNets do not consider the presence of isomorphic actions, which are actions resulting in symmetric or isomorphic states. This lack of symmetry increases the amount of samples required for training GFlowNets and can result in inefficient and potentially incorrect flow functions. As a consequence, the reward and diversity of the generated objects decrease. In this study, our objective is to integrate symmetries into GFlowNets by identifying equivalent actions during the generation process. Experimental results using synthetic data demonstrate the promising performance of our proposed approaches.
2024-06-08
ArXiv (prépublication)
doi.org
arxiv.org
RGFN: Synthesizable Molecular Generation Using GFlowNets
Michał Koziarski
Andrei Rekesh
Dmytro Shevchuk
Almer M. van der Sloot
Piotr Gainski
Yoshua Bengio
Cheng-Hao Liu
Mike Tyers
Robert A. Batey
Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional… (voir plus) in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking.
2024-06-01
ArXiv (prépublication)
doi.org
arxiv.org
RGFN: Synthesizable Molecular Generation Using GFlowNets
Michał Koziarski
Andrei Rekesh
Dmytro Shevchuk
Almer M. van der Sloot
Piotr Gainski
Yoshua Bengio
Cheng-Hao Liu
Mike Tyers
Robert A. Batey
Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional… (voir plus) in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking.
2024-06-01
ArXiv (prépublication)
doi.org
arxiv.org
RGFN: Synthesizable Molecular Generation Using GFlowNets
Michał Koziarski
Andrei Rekesh
Dmytro Shevchuk
Almer M. van der Sloot
Piotr Gainski
Yoshua Bengio
Cheng-Hao Liu
Mike Tyers
Robert A. Batey
Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional… (voir plus) in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking.
2024-06-01
ArXiv (prépublication)
doi.org
arxiv.org
Amortizing intractable inference in diffusion models for vision, language, and control
Siddarth Venkatraman
Moksh J. Jain
Luca Scimeca
Minsu Kim
Marcin Sendera
Mohsin Hasan
Luke Rowe
Sarthak Mittal
Pablo Lemos
Emmanuel Bengio
Alexandre Adam
Jarrid Rector-Brooks
Yoshua Bengio
Glen Berseth
Nikolay Malkin
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
2024-05-31
ArXiv (prépublication)
doi.org
arxiv.org
Amortizing intractable inference in diffusion models for vision, language, and control
Siddarth Venkatraman
Moksh J. Jain
Luca Scimeca
Minsu Kim
Marcin Sendera
Mohsin Hasan
Luke Rowe
Sarthak Mittal
Pablo Lemos
Emmanuel Bengio
Alexandre Adam
Jarrid Rector-Brooks
Yoshua Bengio
Glen Berseth
Nikolay Malkin
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
2024-05-31
ArXiv (prépublication)
doi.org
arxiv.org
Amortizing intractable inference in diffusion models for vision, language, and control
Siddarth Venkatraman
Moksh J. Jain
Luca Scimeca
Minsu Kim
Marcin Sendera
Mohsin Hasan
Luke Rowe
Sarthak Mittal
Pablo Lemos
Emmanuel Bengio
Alexandre Adam
Jarrid Rector-Brooks
Yoshua Bengio
Glen Berseth
Nikolay Malkin
Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (voir plus)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,
2024-05-31
ArXiv (prépublication)
doi.org
arxiv.org