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
- Currently at
- Meta FAIR (Fundamental AI Research)
- twitter.com/ylecun
- GitHub
- github.com/ylecun
- Scholar
- scholar.google.com/citations
- Papers
- 33
Cite
Notes
Only stored in your browser.
Authored papers
33stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation
arXiv 2026
Causal-JEPA: Learning World Models through Object-Level Latent Masking
arXiv 2026
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
arXiv 2026
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
arXiv 2026
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
arXiv 2025
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
arXiv 2025
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
arXiv 2025
Layer by Layer: Uncovering Hidden Representations in Language Models
arXiv 2025
Closing the Train-Test Gap in World Models for Gradient-Based Planning
arXiv 2025
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
arXiv 2025
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
arXiv 2025
Revisiting Feature Prediction for Learning Visual Representations from Video
arXiv preprint 2024 2
Navigation World Models
CVPR 2025 1
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
arXiv 2024
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
arXiv 2024
Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization
arXiv 2024
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
arXiv 2024
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
arXiv 2024
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
arXiv 2024
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
CVPR 2024 1
GAIA: A Benchmark for General AI Assistants
ICLR
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
CVPR 2023 1
Stochastic positional embeddings improve masked image modeling
arXiv 2023
Self-supervised learning of Split Invariant Equivariant representations
arXiv 2023
Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
self-supervised-learning-with-lie-symmetries
Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
arXiv 2023
A Generalization of ViT/MLP-Mixer to Graphs
arXiv 2022
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
coarse-to-fine-vision-language-pre-training-1
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
arXiv 2021
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
arXiv 2021
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
vicreg-variance-invariance-covariance-1
A Closer Look at Spatiotemporal Convolutions for Action Recognition
a-closer-look-at-spatiotemporal-convolutions-1
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
arXiv 2016
Eval contributions
2Affiliations
Frequent co-authors
10from 33 papers