Shang-Ching Liu

Latest

• AffordGraspVLM: Enhancing Task-oriented Grasping via 3d Affordance Estimation from Vision-Language Models
• PAVLM: Advancing Point Cloud based Affordance Understanding via Vision-Language Model
• EHoI: A Benchmark for Task-oriented Hand-Object Action Recognition Via Event Vision
• Learning Multimodal Multifingered Dexterous Manipulation Skills from Human Demonstration