HGDiffuser (IROS 2025)
Efficient task-oriented grasp generation via human-guided grasp diffusion models.
Projects
Efficient Object Rearrangement via Multi-view Fusion (ICRA 2024)
A multi-view fusion perception module for efficient tabletop object rearrangement from a goal image.
GraspGPT (IEEE RA-L 2023)
Leveraging semantic knowledge from a large language model for task-oriented grasping.
FoundationGrasp (IEEE T-ASE 2025)
Generalizable task-oriented grasping with foundation models.
CloudEdgeSLAM (IEEE TVT 2023)
Cloud-learning meets edge model-based: a cloud-edge collaborative visual SLAM system.
OmniScientist (arXiv 2025)
Toward a co-evolving ecosystem of human and AI scientists.
Open Source Contributions
- RLinf — Contributed to the development of RLinf, a VLA RL infrastructure framework for training and evaluating Vision-Language-Action models with reinforcement learning.
- AlohaMini — Contributed to the development of AlohaMini, an open-source low-cost mobile manipulation platform for robotics research and education.