5 papers
DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
Huaijin Pi, Zehong Shen, Yong Wang +8
We study how to generate diverse, physically executable robot demonstrations for dexterous vision-language-action (VLA) learning. Existing demonstration-generation methods typicall…
LHNav: Long-Horizon Humanoid Navigation via Multirate Coordination and Physics-Grounded Action Data
Xueyang Wang, Zehong Shen, Dingkun Wei +6
We study humanoid navigation across multiple destinations under long-horizon language instructions. This task is challenging because robots must maintain progress across successive…
DKWBC: Decoupling Motion Tracking and Balancing for Humanoid Whole-Body Control
Dingkun Wei, Zehong Shen, Huaijin Pi +5
Humanoid whole-body control requires a robot to track diverse reference motions while maintaining balance under gravity, torque limits, contact switching, and external disturbances…
GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images
Jiahao Sun, Dingkun Wei, Zehong Shen +3
Converting multi-view RGB observations into simulation-ready 3D environments remains challenging because current reconstruction pipelines produce monolithic scene representations w…
Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos
Dingkun Wei, Zehong Shen, Yan Xia +3
Human motion recovered from monocular videos often appears overly smooth or dynamically inconsistent, even when joint positions are numerically accurate. We observe that this limit…