Zeva-Ego: Egocentric Mid-Training with In-Context Causal Learning for Robot Manipulation

2026-09-21

AI Summary

本文提出Zeva-Ego框架，通过自我中心视角视频学习物理先验并结合情境因果学习方法，解决机器人操作中的知识转化和持续适应问题。

Abstract

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 Action-Centric Encoder (ACE) converts egocentric visual transitions into action-centered supervision for VLA mid-training, while In-Context Causal Learning (ICCL) enables parameter-free adaptation from action-effect feedback at deployment. Scaling Ego data to 10K hours improves RoboTwin success from 63.8% to 75.3%, matching 2K hours of robot demonstrations (74.7%), corresponding to an empirical data ratio of roughly 4-5:1. With accumulated interaction experience, ICCL further improves success from 58% to 89% within four attempts without parameter updates. These results demonstrate a scalable path toward embodied intelligence that learns from human experience and continuously improves through its own interaction.

Problem

• Egocentric Video
• Robot Manipulation
• Physical Interaction Experience
• Continual Adaptation

Innovation

• Egocentric Mid-Training
• In-Context Causal Learning
• Action-Centric Encoder