Introducing V-JEPA 2knowledge-baseJan 30, 2026By Team M37Labshttps://ai.meta.com/vjepa/AI at MetaIntroducing V-JEPA 2Video Joint Embedding Predictive Architecture 2 (V-JEPA 2) is the first world model trained on video that achieves state-of-the-art visual understanding and prediction, enabling zero-shot robot control in new environments.ai.meta.com
