VLA-JEPA World Model Launches in LeRobot for Efficient Robot Training

Blog: https://ginwind.github.io/VLA-JEPA/ Docs: https://huggingface.co/docs/lerobot/main/en/vla_jep Models: https://huggingface.co/collections/lerobot/vla-jepa

@LeRobotHF @_lilkm_ neat

jepa makes sense: skip pixel reconstruction, learn latent dynamics directly. but i keep wondering how much of the gain is better feature alignment vs actual world model reasoning. libero is controlled lighting, objects, camera. the interesting failure mode is whether the latent world model helps in messy ood scenarios where standard vlAs hallucinate

@LeRobotHF So I record nearly 800 duck episodes only to find there is a model that could have done it with 13 examples? 😭

@LeRobotHF The 13 example fine tune is the most interesting part.

V-JEPA2 helps the robot learn how actions affect the world before training on the real task. Then during use the world model is removed so the system stays simple and fast.

That is a smart setup for real time robotics.

@LeRobotHF The smart bit is using the world model during learning, then dropping it at inference. Robotics needs that kind of practical asymmetry.