facebookresearch/vjepa2
PyTorch code and models for VJEPA2 self-supervised learning from video.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #469 of 2,845 repositories GStars tracks this week (top 16%).
The project lists 14 contributors on GitHub.
Peaked at #49 in the weekly ranking the week of Mar 22, its best in the past year.
Use Cases & Benefits
- Implements self-supervised learning models for video understanding, prediction, and planning using PyTorch.
- Achieves state-of-the-art performance on motion understanding and human action anticipation without task-specific training.
- Use for training video encoders on large-scale unlabeled video datasets to learn dense, temporally consistent features.
- Use for deploying action-conditioned world models to solve robot manipulation tasks from monocular RGB inputs.
- Use for evaluating and fine-tuning video classification and action anticipation tasks with attentive probe training.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
- No commits in the last six months (last push Mar 2026).
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
🆕 [2026-03-16]: :fire: V-JEPA 2.1 is released :fire: A new familly of models trained with a novel recipe that learns high quality and temporolly consistent dense features !!!
[2025-06-25]: V-JEPA 2 is released. [
Blog]Mahmoud Assran∗, Adrien Bardes∗, David Fan∗, Quentin Garrido∗, Russell Howes∗, Mojtaba Komeili∗, Matthew Muckley∗, Ammar Rizvi∗, Claire Roberts∗, Koustuv Sinha∗, Artem Zholus*, Sergio Arnaud*, Abha Gejji*, Ada Martin*, Francois Robert Hogan*, Daniel Dugas*, Piotr Bojanowski, Vasil Khalidov, Patrick Labatut, Francisco Massa, Marc Szafraniec, Kapil Krishnakumar, Yong Li, Xiaodong Ma, Sarath Chandar, Franziska Meier*, Yann LeCun*, Michael Rabbat*, Nicolas Ballas*
Official Pytorch codebase for V-JEPA 2, V-JEPA 2-AC, V-JEPA 2.1.
V-JEPA 2 is a self-supervised approach to training video encoders, using internet-scale video data, that attains state-of-the-art performance on motion understanding and human action anticipation tasks. V-JEPA 2-AC is a latent action-conditioned world model post-trained from V-JEPA 2 (using a small amount of robot trajectory interaction data) that solves robot manipulation tasks without environment-specific data collection or task-specific training or calibration.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
590+44
Open issues
94+12
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| NationalSecurityAgency/ghidra | 93.2K | +7.5K | 75 | today |
| DuarteSantos8/openGym | 14.9K | +4.4K | 59 | 12 days ago |
| K-Dense-AI/scientific-agent-skills | 53.9K | +3.2K | 75 | 21 days ago |
| 666ghj/MiroFish | 80.7K | +2.4K | 23 | 226 days ago |
| anthropics/claude-plugins-official | 43.9K | +2.3K | 35 | — |
| facebookresearch/vjepa2 | 4.8K | +0 | 23 | — |
| Category median | 53.9K | +3.2K | 59 | — |
Also by facebookresearch
Other repositories from this maintainer that GStars tracks
- Python34.9K stars
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
- Python14.5K stars
vggt
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
- Python12.1K stars
sam3
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
- Jupyter Notebook11.6K stars
dinov3
Reference PyTorch implementation and models for DINOv3
- Python10.6K stars
xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.
Discover Repositories
Search across tracked repositories by name or description