Preprint
Aug 2026
XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?
XEWorld is introduced, a controlled cross-embodiment testbed for world models that isolates embodiments by evaluating held-out robots within physically identical scenes, highlighting that achieving true cross-embodiment generalization requires architectural innovations that decouple visual appearance from underlying physical dynamics.
Yixiang Chen, Jiabing Yang, Yuan Xu et al.
· 0 citations