Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- One paper accepted by TPAMI (Impact Factor: 20.8) in March 2025.
- GPT4Video received a Best Paper Nomination at ACM MM 2024 (top 0.6%).
- GPT4Video was accepted as an oral presentation at ACM MM 2024 (3.97% acceptance rate).
- Two papers were early accepted by MICCAI 2024 in May 2024.
- Released GPT4Video, a unified MLLM for video understanding and generation, in November 2023.
- First quantitative evaluation of GPT-4V on various medical imaging tasks in November 2023.
- One paper accepted by Meta-Radiology in September 2023.
- One paper accepted by CVPR in March 2023.
- One paper accepted by IPMI (Oral) in February 2023.
- One paper accepted by TCSVT (IF=5.859) in December 2022.
- One paper accepted by MICCAI in August 2022.
- One paper accepted by TMI (IF=11.037) in April 2022.
- One paper accepted by CVPR in June 2021.
Research Experience
- Research Intern at Tencent AI Lab, July 2023 - present, mentored by Dr. Longyue Wang.
- Algorithm Researcher at QQ Multimedia AI Lab, December 2021 - March 2022, mentored by Dr. Dian Li.
- Algorithm Researcher at Kandian Content AI Lab, March 2021 - December 2021, mentored by Dr. Fengyun Rao.
- Visiting Student at Intelligent Computation Lab, Tsinghua University, July 2020 - March 2021, supervised by Prof. Xiu Li.
- Algorithm Researcher at SandStar, July 2019 - January 2020, mentored by Dr. Zexi Yang.
- Research Intern at SenseTime Intelligent Automative Group, September 2018 - March 2019, mentored by Dr. Zhe Wang.
Education
- Ph.D. student at the Medical Computer Vision Lab, University of Sydney, 2024, supervised by Prof. Luping Zhou, co-supervised by Prof. Wanli Ouyang, and mentored by Prof. Lei Wang and Prof. Lingqiao Liu.
- Master's degree from the Department of Automation, Tsinghua University, July 2019.
- Bachelor's degree from the Department of Automation, Tianjin University of Science and Technology, July 2015.
Background
- Currently an algorithm engineer at TikTok, focusing on multimodal pretraining and multimodal large language model research.
- Research interests include computer vision, multimodal learning, etc.