• I am currently working as TopMinds at Huawei (base in HK) where I lead a research group of 30+ excellent researchers focusing on Multi-modal (Includes both vision understanding and generation) and AI Agent.
• Before that, I was a senior researcher at SenseTime Group where I investigated on-device multi-modal models including vision language models (VLMs) and diffusion models (DMs).
• I hold a PhD from MMLab, CUHK, supervised by Prof. Xiaogang Wang and Prof. Hongsheng Li.

News

• [July, 2025] Released a novel reinforcement learning algorithm GHPO for LLM post-training.
• [Apr., 2025] Released a SOTA level Image-to-Video model Pusa.
• [Sep., 2024] Joined Huawei Hong Kong Research Center.
• [July, 2022] Joined Sensetime as senior researcher.
• [June, 2022] Graduated from MMLab, CUHK.