General-purpose multimodal foundation models are increasingly capable of directly controlling robots, yet improving their manipulation capabilities through autonomous interaction remains challenging. A key challenge to such self-improvement is learning from failures in complex manipulation tasks involving cross-stage d...
Experiments demonstrate that MoWAM achieves strong in-distribution performance, improved out-of-distribution robustness, and higher average real-world success than representative WAM baselines, demonstrating that explicit future motion provides an effective and efficient basis for inference-time scaling.
It is found that current models often generate visually coherent videos, but struggle with constraint reasoning, counterfactual grounding, physical interaction, and unsafe-instruction suppression, and results show that visual quality and surface-level instruction following are insufficient for trustworthy robotic video...
Huiqiong Li, Jia-Yu Wang, Zhiting Mei et al.· arXiv.org· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
