{"ID":3006016,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-04T17:52:58.968687531Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02745","arxiv_id":"2606.02745","title":"SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos","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.","short_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....","url_abs":"https://arxiv.org/abs/2606.02745","url_pdf":"https://arxiv.org/pdf/2606.02745v1","authors":"[\"Jaehyeon Son\",\"Junhyun Kim\",\"Kyle Kam\",\"Jeremiah Coholich\",\"Seok Joon Kim\",\"Jinhoo Kim\",\"Chris Dongjoo Kim\",\"Jaemin Cho\",\"Dieter Fox\",\"Zsolt Kira\"]","published":"2026-06-01T18:09:31Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.LG\"]","methods":"[]","has_code":false}