World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera viewpoint change remains one of their hardest perturbation axes. We study a question specific to this model class: when training with same-state cross-view image pairs, o...
Bingqi Huang, Bingchuan Wei, Ying-Kai Cai et al.· 2 citations
The results show that the Atomic Action Contract can serve as a common registration and dispatch interface across heterogeneous control modalities and defines the path toward runtime gap-triggered self-evolution, mission-grade admission, and lunar-environment validation in subsequent system-level studies.
Bingqi Huang, Bingchuan Wei, Ying-Kai Cai et al.· Astronautics· 0 citations
Vision-language-action (VLA) policies fine-tuned from a fixed scene camera can fail when the camera is moved, even when the task, objects, language, and robot state are unchanged. We study scene-camera viewpoint robustness using only a scene RGB image, language, and proprioception, without camera labels, extrinsics, de...
Bingqi Huang, Bingchuan Wei, Xuan Wang et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.