نسخة أولية وصول مفتوح
Zeva-Ego: Egocentric Mid-Training with In-Context Causal Learning for Robot Manipulation
Egocentric video offers a scalable source of physical interaction experience, yet translating it into robot-executable knowledge and enabling continual adaptation remain challenging. We introduce Zeva-Ego, a unified framework that learns physical priors from human experience and evolves through robot interaction. An Ac …