Vision-Language-Action

SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos

A demo-conditioned VLA that grounds one-shot demonstrations via visibility-aware future-trace prediction

Jaehyeon Son, Junhyun Kim, Kyle Kam, Jeremiah Coholich, Seok Joon Kim, Jinhoo Kim, Chris Dongjoo Kim, Jaemin Cho, Dieter Fox, Zsolt Kira