V-JEPA 2 learns physical prediction from video
Meta released V-JEPA 2, a 1.2-billion-parameter world model pretrained on more than one million hours of video and one million images. After action-conditioned training on 62 hours of robot data, it supported zero-shot visual planning in unfamiliar laboratory settings.
Why it matters: Predictive video representations offer a path toward robots that plan from imagined outcomes rather than only mapping observations directly to actions.