Robotics

SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos
A demo-conditioned VLA framework for visibility-aware latent planning from cross-embodiment demonstration videos.
Jaehyeon Son, Junhyun Kim, Kyle Kam, Jeremiah Coholich, Seok Joon Kim, Jinhoo Kim, Chris Dongjoo Kim, Jaemin Cho, Dieter Fox, Zsolt Kira
PDF Cite arXiv
SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos