Zeva-Ego is introduced, a unified framework that learns physical priors from human experience and evolves through robot interaction and demonstrates a scalable path toward embodied intelligence that learns from human experience and continuously improves through its own interaction.
Bing-Jia Huang, Xin Ding, Fu Chen et al.· 0 citations
Embodied reinforcement learning (RL) improves model capabilities with a pipeline of environment simulation, action generation, and model updates. These stages show heterogeneous CPU and GPU demands, making efficient resource utilization difficult. Recent systems overlap rollout (simulation and generation) with training...
Liang Mi, Wei-Jun Wang, Bo-Wen Gao et al.· 0 citations
Zeva is presented, the first framework that enables in-context learning from a robot's own physical interaction experience while keeping the policy model frozen, and achieves the best performance among the compared frontier VLAs and WAMs and enables self-evolution during deployment without gradient updates.
Fu Chen, Xin Ding, Bing-Jia Huang et al.· 3 citations
Zetta is presented, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen, and shows that closed-loop harness self-evolution opens a scaling path for reliable physical intelligence.
