5 papers
ACROSSVAM3.0: Resource-Bounded 4D Scene Construction and Adaptive Surface Association
Nan Wu, Hong Yee Hung
Combining video generation, dynamic reconstruction and monocular SLAM requires consistent coordinates, explicit handling of missing outputs and predictable memory use. We present A…
AcrossDEX 1.0: From Human Motion Pretraining to Bimanual Dexterous Manipulation across Hand Embodiments
Xiaoyu Yang, Nan Wu
Bimanual dexterous manipulation requires continuous coordination of wrist motion, finger contact, and object motion. Human videos provide rich manipulation experience. Using this e…
AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation
Nan Wu, Yee Hung Hong
Explicit point correspondence is attractive for adapting video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large pretrai…
PhasePlan: Ordered Future-Phase Planning for Robot Brain Models
Xiaoyu Yang, Yafei Zhang, Wensheng Li +2
Robot brain models integrate vision, language, and robot state to generate actions for complex manipulation tasks. Most predict fixed-length action chunks that may span multiple ta…
Geometry-Preserving Human-to-Robot Upper-Body Motion Retargeting from Monocular Video
Xiaoyu Yang, Sen Han, Da Li +1
Monocular RGB video provides an accessible source of human demonstrations for upper-body robot motion, yet video-driven human-to-robot transfer remains challenging because body and…