Pascal Vincent

Pascal Vincent

Université de Montréal

H-index: 57

North America-Canada

About Pascal Vincent

Pascal Vincent, With an exceptional h-index of 57 and a recent h-index of 49 (since 2020), a distinguished researcher at Université de Montréal, specializes in the field of Machine Learning, Deep Learning, Artificial Intelligence.

His recent articles reflect a diverse array of research interests and contributions to the field:

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

On the Identifiability of Quantized Factors

Pug: Photorealistic and semantically controllable synthetic data for representation learning

Towards democratizing joint-embedding self-supervised learning

Predicting masked tokens in stochastic locations improves masked image modeling

Self-supervised learning from images with a joint-embedding predictive architecture

Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection

Worldsense: A synthetic benchmark for grounded reasoning in large language models

Pascal Vincent Information

University

Position

Facebook AI Research; (Professor Computer Sc. & Op. Res.); MILA; CIFAR

Citations(all)

65975

Citations(since 2020)

40190

Cited By

43173

hIndex(all)

57

hIndex(since 2020)

49

i10Index(all)

92

i10Index(since 2020)

83

Email

University Profile Page

Université de Montréal

Google Scholar

View Google Scholar Profile

Pascal Vincent Skills & Research Interests

Machine Learning

Deep Learning

Artificial Intelligence

Top articles of Pascal Vincent

Title

Journal

Author(s)

Publication Date

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Advances in Neural Information Processing Systems

Casey Meehan

Florian Bordes

Pascal Vincent

Kamalika Chaudhuri

Chuan Guo

2024/2/13

On the Identifiability of Quantized Factors

Vitória Barin-Pacela

Kartik Ahuja

Simon Lacoste-Julien

Pascal Vincent

2024/4

Pug: Photorealistic and semantically controllable synthetic data for representation learning

Advances in Neural Information Processing Systems

Florian Bordes

Shashank Shekhar

Mark Ibrahim

Diane Bouchacourt

Pascal Vincent

...

2024/2/13

Towards democratizing joint-embedding self-supervised learning

arXiv preprint arXiv:2303.01986

Florian Bordes

Randall Balestriero

Pascal Vincent

2023/3/3

Predicting masked tokens in stochastic locations improves masked image modeling

arXiv preprint arXiv:2308.00566

Amir Bar

Florian Bordes

Assaf Shocher

Mahmoud Assran

Pascal Vincent

...

2023/7/31

Self-supervised learning from images with a joint-embedding predictive architecture

Mahmoud Assran

Quentin Duval

Ishan Misra

Piotr Bojanowski

Pascal Vincent

...

2023

Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection

arXiv preprint arXiv:2306.16334

Vitória Barin-Pacela

Kartik Ahuja

Simon Lacoste-Julien

Pascal Vincent

2023/6/28

Worldsense: A synthetic benchmark for grounded reasoning in large language models

arXiv preprint arXiv:2311.15930

Youssef Benchekroun

Megi Dervishi

Mark Ibrahim

Jean-Baptiste Gaya

Xavier Martinet

...

2023/11/27

Objectives matter: Understanding the impact of self-supervised objectives on vision transformer representations

arXiv preprint arXiv:2304.13089

Shashank Shekhar

Florian Bordes

Pascal Vincent

Ari Morcos

2023/4/25

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations

arXiv preprint arXiv:2311.08815

Cian Eastwood

Julius von Kügelgen

Linus Ericsson

Diane Bouchacourt

Pascal Vincent

...

2023/11/15

A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation

arXiv preprint arXiv:2304.05369

Florian Bordes

Samuel Lavoie

Randall Balestriero

Nicolas Ballas

Pascal Vincent

2023/4/11

Motif: Intrinsic motivation from artificial intelligence feedback

ICLR 2024

Martin Klissarov*

Pierluca D'Oro*

Shagun Sodhani

Roberta Raileanu

Pierre-Luc Bacon

...

2023/10/3

Instance-Conditioned GAN Data Augmentation for Representation Learning

arXiv preprint arXiv:2303.09677

Pietro Astolfi

Arantxa Casanova

Jakob Verbeek

Pascal Vincent

Adriana Romero-Soriano

...

2023/3/16

Discovering environments with XRM

arXiv preprint arXiv:2309.16748

Mohammad Pezeshki

Diane Bouchacourt

Mark Ibrahim

Nicolas Ballas

Pascal Vincent

...

2023/9/28

Disentanglement of correlated factors via hausdorff factorized support

arXiv preprint arXiv:2210.07347

Karsten Roth

Mark Ibrahim

Zeynep Akata

Pascal Vincent

Diane Bouchacourt

2022/10/13

The hidden uniform cluster prior in self-supervised learning

ICLR - International Conference on Learning Representations

Mahmoud Assran

Randall Balestriero

Quentin Duval

Florian Bordes

Ishan Misra

...

2022/10/13

The Emergence of Argument Structure in Artificial Languages

Transactions of the Association for Computational Linguistics

Tom Bosc

Pascal Vincent

2022/12/23

Guillotine regularization: Why removing layers is needed to improve generalization in self-supervised learning

Transactions of Machine Learning Research (TMLR)

Florian Bordes

Randall Balestriero

Quentin Garrido

Adrien Bardes

Pascal Vincent

2022/6/27

Imagenet-x: Understanding model mistakes with factor of variation annotations

arXiv preprint arXiv:2211.01866

Badr Youbi Idrissi

Diane Bouchacourt

Randall Balestriero

Ivan Evtimov

Caner Hazirbas

...

2022/11/3

Masked siamese networks for label-efficient learning

Mahmoud Assran

Mathilde Caron

Ishan Misra

Piotr Bojanowski

Florian Bordes

...

2022/10/23

See List of Professors in Pascal Vincent University(Université de Montréal)

Co-Authors

H-index: 227
Yoshua Bengio

Yoshua Bengio

Université de Montréal

H-index: 145
Yann LeCun

Yann LeCun

New York University

H-index: 98
Aaron Courville

Aaron Courville

Université de Montréal

H-index: 22
Samira Ebrahimi Kahou

Samira Ebrahimi Kahou

École de Technologie Supérieure

H-index: 15
Vincent Michalski

Vincent Michalski

Université de Montréal

H-index: 13
Salah Rifai

Salah Rifai

Université de Montréal

academic-engine