In October 2025, Video-MMLU received the Outstanding Paper Award at ICCV 2025 Workshop @ Knowledge-Intensive Multimodal Reasoning with a Travel Grant. In September 2025, one paper was accepted by NeurIPS 2025, and two papers were accepted by the NeurIPS 2025 Datasets and Benchmarks Track, with one Oral. In August 2025, UniHPR received the Best Paper Award at IEEE MIPR 2025. In June 2025, one paper was accepted by ICCV 2025. In May 2025, one paper was accepted by ACL 2025. In April 2025, hosted the CVPR 2025 Video Understanding Challenge @ LOVEU, sponsored by Lambda. In February 2025, three papers were accepted by CVPR 2025. In January 2025, two papers were accepted by ICLR 2025. In December 2024, two papers were accepted by AAAI 2025. In July 2024, two papers were accepted by ECCV 2024. In February 2024, two papers were accepted by CVPR 2024, with one Highlight (2.81%). In April 2024, gave an invited talk at the AgentX seminar about the STEVE series works. In February 2024, gave an invited talk at the AAAI 2024 workshop @ IMAGEOMICS.
Research Experience
Interned at Pika Labs and Microsoft Research Asia. Leads the development of MovieChat, the first large multimodal model and benchmark for hour-long video understanding. Core member of the LiveCodeBench Pro Team.
Education
Started his Ph.D. in Computer Science at Princeton University in Fall 2025, working with Prof. Zhuang Liu; graduated from the University of Washington in March 2025 with a Master's thesis on Large Multimodal Models for Video Captioning, nominated for the Distinguished Thesis Award by the ECE Department; received his bachelor's degree from Zhejiang University.
Background
Research interests span a wide range of topics in machine learning and computer vision. Previously studied at Stanford University, working with Prof. Christopher D. Manning, and at the University of Illinois Urbana-Champaign as a visiting scholar.
Miscellany
Personal interests include chatting with master/undergraduate students about life, career plans, or research ideas related to AI/ML. Dedicates at least 30 minutes every week for such meetings. Encourages students from underrepresented groups to reach out. Looking for interns at Princeton University. Hosting a Discord server among professors and students for daily sharing and research discussion.