Yann LeCun
Graph View
Backlinks
- A Cookbook of Self-Supervised Learning
- Back to the Features - DINO as a Foundation for Video World Models
- Intuitive physics understanding emerges from self-supervised pretraining on natural videos
- Layer by Layer - Uncovering Hidden Representations in Language Models
- Learning Latent Action World Models In The Wild
- On the duality between contrastive and non-contrastive self-supervised learning
- Optimal Brain Damage
- RankMe - Assessing the downstream performance of pretrained self-supervised representations by their rank
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Scaling Language-Free Visual Representation Learning
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- Self-supervised learning of Split Invariant Equivariant representations
- Stochastic positional embeddings improve masked image modeling
- To Compress or Not to Compress- Self-Supervised Learning and Information Theory - A Review
- V-JEPA 2 - Self-Supervised Video Models Enable Understanding, Prediction and Planning
- V-JEPA 2.1 - Unlocking Dense Features in Video Self-Supervised Learning
- VICRegL - Self-Supervised Learning of Local Visual Features
- Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
- What Drives Success in Physical Planning with Joint-Embedding Predictive World Models