Xuhong Huang
Xuhong Huang is an incoming PhD student at XLANG Lab, University of Hong Kong, advised by Professor Tao Yu, and an undergraduate student at Nanjing University. He is a research intern at the Qwen Team, Alibaba Group, where he is a core contributor to Qwen-VLA and works on Vision-Language-Action models. His research focuses on spatial intelligence, embodied agents, and multimodal learning. He is a co-first author on FineVLA, contributing to data pipeline, benchmark construction, policy training, and real-world evaluation.
“Xintong Hu & Xuhong Huang: Equal-contribution first authors; XLANG Lab, University of Hong Kong. Led the technical execution of the full FineVLA framework”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.