Linking pages
Linked pages
- Sora https://openai.com/sora 3439 comments
- [2404.02258] Mixture-of-Depths: Dynamically allocating compute in transformer-based language models https://arxiv.org/abs/2404.02258 103 comments
- [2301.08243] Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture https://arxiv.org/abs/2301.08243 10 comments
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Models https://arxiv.org/abs/2201.11903 1 comment
- [2307.12698] MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features https://arxiv.org/abs/2307.12698 1 comment
- https://openreview.net/pdf?id=BZ5a1r-kVsf 0 comments
- [1705.06950] The Kinetics Human Action Video Dataset https://arxiv.org/abs/1705.06950 0 comments
- Revisiting Feature Prediction for Learning Visual Representations from Video | Research - AI at Meta https://ai.meta.com/research/publications/revisiting-feature-prediction-for-learning-visual-representations-from-video/ 0 comments
Related searches:
Search whole site: site:rohitbandaru.github.io
Search title: Deep Dive into Yann LeCun’s JEPA | Rohit Bandaru
See how to search.