# Three cross-embodiment papers examined: body, motion, and environment data still need manual translation

- Source: 人形大讲堂 · 微信公众号
- Published: 2026-10-28T10:00:00.000Z
- RoboHot: https://robohot.news/en/items/sqw1tj07k4np97ffva3i9qnw8
- Original: https://mp.weixin.qq.com/s?__biz=MzkzMjY2Mzc5MA==&mid=2247496346&idx=1&sn=35a4417db657102ba10df2f5f20d3593&chksm=c3e531c9d7fc2d3d51f03a947df46929390c9cd5bca22cef7453036a3e798980c6313383fe24&scene=126&sessionid=1793192415#rd

## Summary

The article examines three cross-embodiment research papers published between October 24 and 26, arguing that cross-embodiment is more like translation than a spontaneous model capability. MimicAll uses a structured body-condition table covering 16 series and 4,096 body variants.