arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Yann LeCun"" — arXiv2 Search
Showing 1–4 of 4 results
/ Date
/ Name
Dec 11, 2025
VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
Jul 25, 2025
Back to the Features: DINO as a Foundation for Video World Models
Jun 11, 2025
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Feb 15, 2024
Revisiting Feature Prediction for Learning Visual Representations from Video