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
This work introduces InternW0, the first instantiation of the InternW physical world model series from Shanghai AI Laboratory, built around omnimodal interfaces, asynchronous multi-frequency processing, and local physical modeling under partial observations and external influences.
Ji-Song Cai, Yao Mu, Gan-Lin Yang 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
EgoAfford is introduced, a benchmark designed to connect the semantic roles of participating objects with task-state-aligned visual observations and multi-step planning and EgoLens, a 3B multimodal large language model with role-specific mask decoders, as an in-domain reference model for this joint task.
Xinyuan Guan, Feifan Chen, Xinyu Zhan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
