Yann LeCun

Revisiting Feature Prediction for Learning Visual Representations from Video

Adrien Bardes, Quentin Garrido, Jean Ponce, Xinlei Chen, Michael Rabbat, Yann LeCun, Mahmoud Assran, Nicolas Ballas

A hierarchical loss and its problems when classifying non-hierarchically

Cinna Wu, Mark Tygert, Yann LeCun

Comments 19 pages, 4 figures, 7 tables

Journal ref PLOS ONE, 14 (12): 1-17, 2019

Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation

Remi Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

Xiaoxin He, Xavier Bresson, Thomas Laurent, Adam Perold, Yann LeCun, Bryan Hooi

Comments In Proceedings of ICLR 2024

Learning and Leveraging World Models in Visual Representation Learning

Quentin Garrido, Mahmoud Assran, Nicolas Ballas, Adrien Bardes, Laurent Najman, Yann LeCun

Comments 23 pages, 16 figures

Stochastic positional embeddings improve masked image modeling

Amir Bar, Florian Bordes, Assaf Shocher, Mahmoud Assran, Pascal Vincent, Nicolas Ballas, Trevor Darrell, Amir Globerson, Yann LeCun

Comments Code and models available in https://github.com/amirbar/StoP

Variance-Covariance Regularization Improves Representation Learning

Jiachen Zhu, Katrina Evtimova, Yubei Chen, Ravid Shwartz-Ziv, Yann LeCun

Comments 165 pages, 5 figures

Learning by Reconstruction Produces Uninformative Features For Perception

Randall Balestriero, Yann LeCun

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

Grégoire Mialon, Quentin Garrido, Hannah Lawrence, Danyal Rehman, Yann LeCun, Bobak T. Kiani

Comments NeurIPS 2023

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations

Grégoire Mialon, Randall Balestriero, Yann LeCun

Fast and Exact Enumeration of Deep Networks Partitions Regions

Randall Balestriero, Yann LeCun

Gradient-based Planning with World Models

Jyothir S, Siddhartha Jalagam, Yann LeCun, Vlad Sobal

GAIA: a benchmark for General AI Assistants

Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann LeCun, Thomas Scialom

To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review

Ravid Shwartz-Ziv, Yann LeCun

VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment

Shraman Pramanick, Li Jing, Sayan Nag, Jiachen Zhu, Hardik Shah, Yann LeCun, Rama Chellappa

Comments Published in TMLR 2023

Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need

Vivien Cabannes, Leon Bottou, Yann Lecun, Randall Balestriero

Comments 8 main pages, 20 totals, 10 figures

MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features

Adrien Bardes, Jean Ponce, Yann LeCun

A Cookbook of Self-Supervised Learning

Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Gregoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum

RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank

Quentin Garrido, Randall Balestriero, Laurent Najman, Yann Lecun

Journal ref The Fortieth International Conference on Machine Learning, 2023, Honolulu, United States

On the duality between contrastive and non-contrastive self-supervised learning

Quentin Garrido, Yubei Chen, Adrien Bardes, Laurent Najman, Yann Lecun

Comments The Eleventh International Conference on Learning Representations, 2023, Kigali, Rwanda

Self-supervised learning of Split Invariant Equivariant representations

Quentin Garrido, Laurent Najman, Yann Lecun

Journal ref The Fortieth International Conference on Machine Learning, 2023, Honolulu, United States

Decoupled Contrastive Learning

Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu, Yubei Chen, Yann LeCun

Comments Accepted by ECCV2022

Bag of Image Patch Embedding Behind the Success of Self-Supervised Learning

Yubei Chen, Adrien Bardes, Zengyi Li, Yann LeCun

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

Vivien Cabannes, Bobak T. Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti

Journal ref Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023

Reverse Engineering Self-Supervised Learning

Ido Ben-Shaul, Ravid Shwartz-Ziv, Tomer Galanti, Shai Dekel, Yann LeCun

A Generalization of ViT/MLP-Mixer to Graphs

Xiaoxin He, Bryan Hooi, Thomas Laurent, Adam Perold, Yann LeCun, Xavier Bresson

Comments In Proceedings of ICML 2023

Minimalistic Unsupervised Learning with the Sparse Manifold Transform

Yubei Chen, Zeyu Yun, Yi Ma, Bruno Olshausen, Yann LeCun

Comments This paper is published at ICLR 2023

Journal ref The Eleventh International Conference on Learning Representations (2023)

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Yann LeCun, Nicolas Ballas

Comments 2023 IEEE/CVF International Conference on Computer Vision

EMP-SSL: Towards Self-Supervised Learning in One Training Epoch

Shengbang Tong, Yubei Chen, Yi Ma, Yann Lecun

Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors

Zeyu Yun, Yubei Chen, Bruno A Olshausen, Yann LeCun

Comments This paper is published at DeeLIO Workshop@NAACL 2021