0

Yann LeCun

VP & Chief AI Scientist at Meta; 2018 Turing Award co-recipient; NYU professor; advocate for world-model / JEPA architectures over LLMs.

Role
VP & Chief AI Scientist
Papers
33

Cite

Notes

Only stored in your browser.

33papers·2eval contribs

Authored papers

33

stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

arXiv 2026

2026

Causal-JEPA: Learning World Models through Object-Level Latent Masking

arXiv 2026

2026

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

arXiv 2026

2026

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

arXiv 2026

2026

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

arXiv 2025

2025

What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?

arXiv 2025

2025

Intuitive physics understanding emerges from self-supervised pretraining on natural videos

arXiv 2025

2025

Layer by Layer: Uncovering Hidden Representations in Language Models

arXiv 2025

2025

Closing the Train-Test Gap in World Models for Gradient-Based Planning

arXiv 2025

2025

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

arXiv 2025

2025

Forgotten Polygons: Multimodal Large Language Models are Shape-Blind

arXiv 2025

2025

Revisiting Feature Prediction for Learning Visual Representations from Video

arXiv preprint 2024 2

2024

Navigation World Models

CVPR 2025 1

2024

LiveBench: A Challenging, Contamination-Limited LLM Benchmark

arXiv 2024

2024

DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

arXiv 2024

2024

Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization

arXiv 2024

2024

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

arXiv 2024

2024

G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

arXiv 2024

2024

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

arXiv 2024

2024

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

CVPR 2024 1

2024

GAIA: A Benchmark for General AI Assistants

ICLR

2023

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

CVPR 2023 1

2023

Stochastic positional embeddings improve masked image modeling

arXiv 2023

2023

Self-supervised learning of Split Invariant Equivariant representations

arXiv 2023

2023

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

self-supervised-learning-with-lie-symmetries

2023

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

arXiv 2023

2023

A Generalization of ViT/MLP-Mixer to Graphs

arXiv 2022

2022

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

coarse-to-fine-vision-language-pre-training-1

2022

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

arXiv 2021

2021

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

arXiv 2021

2021

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

vicreg-variance-invariance-covariance-1

2021

A Closer Look at Spatiotemporal Convolutions for Action Recognition

a-closer-look-at-spatiotemporal-convolutions-1

2017

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

arXiv 2016

2016

Eval contributions

2

Affiliations

Frequent co-authors

10

from 33 papers