mirror of
https://github.com/zenlm/vjepa2.git
synced 2026-10-30 19:33:29 +00:00
main
This fork does not ship upstream's releases, and its hosted-runner jobs never start here. Claude-Session: https://claude.ai/code/session_01HuMDfgFssPUptYUzgZ6Cp8
VJEPA2
Self-supervised visual representation learning from video. Part of the Zen LM ecosystem.
Overview
VJEPA2 implements Video Joint-Embedding Predictive Architecture for learning visual representations from unlabeled video data without relying on hand-crafted augmentations.
Features
- Self-supervised learning from video
- No hand-crafted augmentations required
- Pre-trained visual encoder for downstream tasks
- Efficient training with masking strategies
Related
License
See LICENSE file.
Languages
Python
96.3%
Jupyter Notebook
3.7%