5 papers
STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition
Yuhang Wen, Mengyuan Liu, Zixuan Tang +3
Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision. While most existing methods rely on skeleton sequences--effective…
Search Self-play: Pushing the Frontier of Agent Capability without Supervision
Hongliang Lu, Yuhang Wen, Pengyu Cheng +7
Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on well-crafted task queries and cor…
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
Yuhang Wen, Mengyuan Liu, Songtao Wu +1
Skeleton-based multi-entity action recognition is a challenging task aiming to identify interactive actions or group activities involving multiple diverse entities. Existing models…
A Survey on Backbones for Deep Video Action Recognition
Zixuan Tang, Youjun Zhao, Yuhang Wen +1
Action recognition is a key technology in building interactive metaverses. With the rapid development of deep learning, methods in action recognition have also achieved great advan…
Surfer: Progressive Reasoning with World Models for Robotic Manipulation
Pengzhen Ren, Kaidong Zhang, Hetao Zheng +5
Considering how to make the model accurately understand and follow natural language instructions and perform actions consistent with world knowledge is a key challenge in robot man…