Yann LeCun

Yann LeCun on Hugging Face Daily Papers: 16 papers, 5 in the top 3 of their day, 751 upvotes.

  1. V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning 22 upvotes, #10 of 2026-03-19
  2. Causal-JEPA: Learning World Models through Object-Level Latent Interventions 5 upvotes, #16 of 2026-02-18
  3. V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning 26 upvotes, #8 of 2025-06-18
  4. Scaling Language-Free Visual Representation Learning 24 upvotes, #10 of 2025-04-02
  5. Transformers without Normalization 128 upvotes, #1 of 2025-03-14
  6. Intuitive physics understanding emerges from self-supervised pretraining on natural videos 13 upvotes, #13 of 2025-02-18
  7. DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning 11 upvotes, #7 of 2025-02-03
  8. LiveBench: A Challenging, Contamination-Free LLM Benchmark 12 upvotes, #9 of 2024-06-28
  9. Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs 48 upvotes, #2 of 2024-06-25
  10. Just How Flexible are Neural Networks in Practice? 6 upvotes, #22 of 2024-06-18
  11. Learning and Leveraging World Models in Visual Representation Learning 32 upvotes, #2 of 2024-03-04
  12. GAIA: a benchmark for General AI Assistants 253 upvotes, #1 of 2023-11-23
  13. Predicting masked tokens in stochastic locations improves masked image modeling 17 upvotes, #4 of 2023-08-02
  14. MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features 7 upvotes, #10 of 2023-07-25
  15. Self-Supervised Learning with Lie Symmetries for Partial Differential Equations 18 upvotes, #5 of 2023-07-12
  16. To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review 7 upvotes, #2 of 2023-05-10

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.