Nicolas Ballas
Graph View
Backlinks
- DINOv2 - Learning Robust Visual Features without Supervision
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- Learning Latent Action World Models In The Wild
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Scaling Language-Free Visual Representation Learning
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- Stochastic positional embeddings improve masked image modeling
- The Hidden Uniform Cluster Prior in Self-Supervised Learning
- V-JEPA 2 - Self-Supervised Video Models Enable Understanding, Prediction and Planning
- V-JEPA 2.1 - Unlocking Dense Features in Video Self-Supervised Learning