Release date and specs of Meta's AI model
Video Joint Embedding Predictive Architecture model that learns visual representations by predicting in latent space.
- Released
- Feb 15, 2024
- Context window
- —
- Modality
- video
- Open source
- —
- API available
- —
- Releases
- 1
Releases
Feb 15, 2024V-JEPA releasedOpen weights
Meta released V-JEPA, a video model trained by predicting missing representations rather than pixels.
V-JEPA FAQ
When was V-JEPA released?
V-JEPA was released by Meta on Feb 15, 2024.
Which model family does V-JEPA belong to?
V-JEPA is part of the V-JEPA model family by Meta.

