I am a Master of Philosophy student at the Hong Kong University of Science and Technology (Guangzhou). My research is supervised by Professor Hui Xiong (Fellow of AAAS, IEEE, CAAI, and AAAI) and Assistant Professor Xuming Hu. I am affiliated with the AI+ Lab/HKUST-GZ NLP Group, specializing in multimodal large language models and reinforcement learning.

My current research focuses on long video understanding, addressing the critical challenge of key frame selection in extended videos. By integrating key frame search algorithms with multimodal fusion techniques, I aim to enhance both efficiency and accuracy in long-video comprehension systems.

I welcome collaborations with scholars working on related topics and enjoy exploring interdisciplinary applications of AI technologies.