Vision-language-action (VLA) models have emerged as a powerful paradigm for robotic manipulation, enabling robots to generate actions from visual observations and language instructions. However, most existing VLA models still operate on image-level visual representations inherited from pretrained vision-language backbo...
Huai-Liang Ma, Yuxuan Li, Zi-Yi Zhao et al.· 2 citations
World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple framework for unified causal training that treats actions as both conditions for world prediction and targets for policy learning within a shared video-action architect...
Yue Su, Bo-Kai Lin, Xin-Kai Wang et al.· 1 citation· ⚡1
Robot demonstrations record what the robot saw and what it did. They do not specify how the 3D world changed in between. Scene-level 3D flow describes it by tracking 3D scene points, providing the world representation with 4D geometry. Prior work has used flow to improve robot policies. Flow served as an intermediate p...
Jia-Lin Tian, Zhuo-Fan Li, Xin-Kai Wang et al.· 0 citations
Track4Action is introduced, a framework that distills this realized transition from a frozen world-centric 3D tracker into a current-observation VLA policy, and gains across simulation and physical tasks support action-aligned 3D tracker features as privileged supervision for tracker-free VLA deployment.
Chenyi Wang, Xinkai Wang, Bokai Lin et al.· 4 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.