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

Jaehyeon Son1 Junhyun Kim1 Kyle Kam1 Jeremiah Coholich1 Seok Joon Kim1 Jinhoo Kim1 Chris Dongjoo Kim2 Jaemin Cho2, 3 Dieter Fox2, 4 Zsolt Kira1

1Georgia Institute of Technology 2Allen Institute for AI 3Johns Hopkins University 4University of Washington

Abstract

Vision-language-action models (VLAs) are promising general-purpose robot policies, but adapting them to new tasks typically requires costly task-specific teleoperation data. As an alternative, we study one-shot demo-conditioned VLAs, where a robot policy is conditioned on a single demonstration video of an unseen task. We find that existing end-to-end approaches often struggle when successful execution requires precisely localizing small target regions. To address this limitation, we propose SeeTraceAct, a demo-conditioned VLA framework that encourages precise spatial grounding through visibility-aware prediction of future end-effector traces. To enable reproducible evaluation with cross-embodiment demonstrations, we introduce and release RoboCasa-DC, a demo-conditioned extension of RoboCasa with episode-paired humanoid videos. Experiments on RoboCasa-DC and a real-world benchmark, where a Franka Panda arm is conditioned on human demonstrations, show that SeeTraceAct outperforms baselines, achieving the best success rate across all four RoboCasa-DC settings and improving real-world average success by 12.5 percentage points.

Citation

@article{son2026seetraceact,
  title   = {SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos},
  author  = {Son, Jaehyeon and Kim, Junhyun and Kam, Kyle and Coholich, Jeremiah and Kim, Seok Joon and Kim, Jinhoo and Kim, Chris Dongjoo and Cho, Jaemin and Fox, Dieter and Kira, Zsolt},
  journal = {arXiv preprint},
  year    = {2026}
}