Yann LeCun

OpenReview

Affiliations

FacebookNYU

papers

4,151

total citations

papers (28)

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

ICCV 2021arXiv

1,068

citations

Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture

CVPR 2023arXiv

632

citations

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods

NEURIPS 2022arXiv

158

citations

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

NEURIPS 2022arXiv

153

citations

Navigation World Models

CVPR 2025arXiv

151

citations

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

ICCV 2025arXiv

150

citations

Layer by Layer: Uncovering Hidden Representations in Language Models

ICML 2025arXiv

145

citations

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

ICLR 2024arXiv

133

citations

The Effects of Regularization and Data Augmentation are Class Dependent

NEURIPS 2022arXiv

112

citations

Transformers without Normalization

CVPR 2025arXiv

103

citations

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

ICLR 2025arXiv

citations

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

NEURIPS 2022arXiv

citations

Reverse Engineering Self-Supervised Learning

NEURIPS 2023arXiv

citations

Scaling Language-Free Visual Representation Learning

ICCV 2025arXiv

citations

projUNN: efficient method for training deep networks with unitary matrices

NEURIPS 2022arXiv

citations

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

NEURIPS 2023arXiv

citations

The Entropy Enigma: Success and Failure of Entropy Minimization

ICML 2024arXiv

citations

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

ICLR 2025arXiv

citations

RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training

CVPR 2025arXiv

citations

Stochastic positional embeddings improve masked image modeling

ICML 2024arXiv

citations

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

ICLR 2025arXiv

citations

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

CVPR 2025arXiv

citations

A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training

NEURIPS 2022

citations

How Learning by Reconstruction Produces Uninformative Features For Perception

ICML 2024

citations

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

NEURIPS 2023

citations

Yann LeCun

Affiliations

papers (28)

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

Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Decoupled Contrastive Learning

VICRegL: Self-Supervised Learning of Local Visual Features

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

Navigation World Models

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Layer by Layer: Uncovering Hidden Representations in Language Models

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

The Effects of Regularization and Data Augmentation are Class Dependent

Transformers without Normalization

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Reverse Engineering Self-Supervised Learning

Scaling Language-Free Visual Representation Learning

projUNN: efficient method for training deep networks with unitary matrices

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

The Entropy Enigma: Success and Failure of Entropy Minimization

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training

Stochastic positional embeddings improve masked image modeling

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training

How Learning by Reconstruction Produces Uninformative Features For Perception

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

papers (28)

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

Self-Supervised Learning From Images With a Joint-Embedding Predictive Architecture

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Decoupled Contrastive Learning

VICRegL: Self-Supervised Learning of Local Visual Features

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

Navigation World Models

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Layer by Layer: Uncovering Hidden Representations in Language Models

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

The Effects of Regularization and Data Augmentation are Class Dependent

Transformers without Normalization

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Reverse Engineering Self-Supervised Learning

Scaling Language-Free Visual Representation Learning

projUNN: efficient method for training deep networks with unitary matrices

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

The Entropy Enigma: Success and Failure of Entropy Minimization

Hierarchical World Models as Visual Whole-Body Humanoid Controllers

RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training

Stochastic positional embeddings improve masked image modeling

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation

A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training

How Learning by Reconstruction Produces Uninformative Features For Perception

An Information Theory Perspective on Variance-Invariance-Covariance Regularization