HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos

HumanX is a unified framework that transforms human videos into generalizable, real‑world interaction skills for humanoid robots without task‑specific design. It combines XGen, a data‑generation pipeline that creates physically plausible robot interaction data from monocular video, with XMimic, a learning framework that extracts interaction priors from only seconds of demonstration. Across five domains—basketball, football, badminton, cargo pickup, and reactive fighting—HumanX learns nine distinct skills and transfers them zero‑shot to a physical Unitree G1 humanoid, achieving complex maneuvers and sustained passing sequences from a single video.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• robotics