Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Yann LeCun

MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding


Apr 26, 2021
Aishwarya Kamath, Mannat Singh, Yann LeCun, Ishan Misra, Gabriel Synnaeve, Nicolas Carion


  Access Paper or Ask Questions

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


Mar 29, 2021
Zeyu Yun, Yubei Chen, Bruno A Olshausen, Yann LeCun


  Access Paper or Ask Questions

Barlow Twins: Self-Supervised Learning via Redundancy Reduction


Mar 04, 2021
Jure Zbontar, Li Jing, Ishan Misra, Yann LeCun, Stéphane Deny

* 13 pages, 5 figures 

  Access Paper or Ask Questions

Implicit Rank-Minimizing Autoencoder


Oct 14, 2020
Li Jing, Jure Zbontar, Yann LeCun


  Access Paper or Ask Questions

Inspirational Adversarial Image Generation


Jun 17, 2019
Morgane Riviere, Olivier Teytaud, Jérémy Rapin, Yann LeCun, Camille Couprie


  Access Paper or Ask Questions

Unsupervised Image Matching and Object Discovery as Optimization


Apr 05, 2019
Huy V. Vo, Francis Bach, Minsu Cho, Kai Han, Yann LeCun, Patrick Perez, Jean Ponce

* Accepted to CVPR 2019 

  Access Paper or Ask Questions

Learning about an exponential amount of conditional distributions


Feb 22, 2019
Mohamed Ishmael Belghazi, Maxime Oquab, Yann LeCun, David Lopez-Paz

* 8 pages, 7 figures 

  Access Paper or Ask Questions

Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic


Jan 08, 2019
Mikael Henaff, Alfredo Canziani, Yann LeCun


  Access Paper or Ask Questions

A Spectral Regularizer for Unsupervised Disentanglement


Dec 04, 2018
Aditya Ramesh, Youngduck Choi, Yann LeCun


  Access Paper or Ask Questions

Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation


Nov 10, 2018
Xiang Zhang, Yann LeCun


  Access Paper or Ask Questions

Predicting Future Instance Segmentation by Forecasting Convolutional Features


Oct 03, 2018
Pauline Luc, Camille Couprie, Yann LeCun, Jakob Verbeek


  Access Paper or Ask Questions

DeSIGN: Design Inspiration from Generative Networks


Sep 14, 2018
Othman Sbai, Mohamed Elhoseiny, Antoine Bordes, Yann LeCun, Camille Couprie


  Access Paper or Ask Questions

GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations


Jul 02, 2018
Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William W. Cohen, Ruslan Salakhutdinov, Yann LeCun


  Access Paper or Ask Questions

Adversarially Regularized Autoencoders


Jun 29, 2018
Jake Zhao, Yoon Kim, Kelly Zhang, Alexander M. Rush, Yann LeCun

* ICML 2018 

  Access Paper or Ask Questions

Backpropagation for Implicit Spectral Densities


Jun 01, 2018
Aditya Ramesh, Yann LeCun


  Access Paper or Ask Questions

Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks


May 30, 2018
Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro

* 19 pages, 8 figures 

  Access Paper or Ask Questions

A Closer Look at Spatiotemporal Convolutions for Action Recognition


Apr 12, 2018
Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, Manohar Paluri


  Access Paper or Ask Questions

Model-Based Planning with Discrete and Continuous Actions


Apr 04, 2018
Mikael Henaff, William F. Whitney, Yann LeCun


  Access Paper or Ask Questions

Byte-Level Recursive Convolutional Auto-Encoder for Text


Feb 06, 2018
Xiang Zhang, Yann LeCun

* Rejected from ICLR 2018 

  Access Paper or Ask Questions

Prediction Under Uncertainty with Error-Encoding Networks


Nov 30, 2017
Mikael Henaff, Junbo Zhao, Yann LeCun


  Access Paper or Ask Questions

Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond


Oct 05, 2017
Levent Sagun, Leon Bottou, Yann LeCun

* ICLR submission, 2016 - updated to match the openreview.net version 

  Access Paper or Ask Questions

Which Encoding is the Best for Text Classification in Chinese, English, Japanese and Korean?


Aug 17, 2017
Xiang Zhang, Yann LeCun


  Access Paper or Ask Questions

Predicting Deeper into the Future of Semantic Segmentation


Aug 08, 2017
Pauline Luc, Natalia Neverova, Camille Couprie, Jakob Verbeek, Yann LeCun

* Accepted to ICCV 2017. Supplementary material available on the authors' webpages 

  Access Paper or Ask Questions

Tracking the World State with Recurrent Entity Networks


May 10, 2017
Mikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes, Yann LeCun

* ICLR 2017 

  Access Paper or Ask Questions

Geometric deep learning: going beyond Euclidean data


May 03, 2017
Michael M. Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, Pierre Vandergheynst


  Access Paper or Ask Questions

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys


Apr 21, 2017
Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer Chayes, Levent Sagun, Riccardo Zecchina

* ICLR '17 

  Access Paper or Ask Questions

Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs


Apr 03, 2017
Li Jing, Yichen Shen, Tena Dubček, John Peurifoy, Scott Skirlo, Yann LeCun, Max Tegmark, Marin Soljačić

* 9 pages, 4 figures 

  Access Paper or Ask Questions

Recurrent Orthogonal Networks and Long-Memory Tasks


Mar 15, 2017
Mikael Henaff, Arthur Szlam, Yann LeCun


  Access Paper or Ask Questions

Energy-based Generative Adversarial Network


Mar 06, 2017
Junbo Zhao, Michael Mathieu, Yann LeCun

* Submitted to ICLR 2017 

  Access Paper or Ask Questions