Publication types
Publications in this category
Hierarchical AI Agent architecture for general robot manipulation, compiling sparse demonstrations into reusable Skill Blocks with frozen foundation backbones and physical self-healing.
Read paper story
A 4D multi-view generative world model for robot demonstration augmentation, editing spatiotemporal appearances while strictly preserving recorded physical actions for downstream VLA policies.
Read paper story
Proposes a geometry-conditioned diffusion paradigm for sample consensus, iteratively refining candidate minimal sets to achieve robust estimation under extreme outlier ratios.
Read paper story