Selected Publications: Vgent (NeurIPS 2025), LongVU (ICML 2025), StoryGPT-V (CVPR 2025), MiniGPT-4 (ICLR 2024), MoStGAN-V (CVPR 2023), etc. The MiniGPT-4 project has over 25,000 stars and 4,000 citations on GitHub.
Research Experience
Research Intern, Nvidia, Taiwan, June 2025 - September 2025; Research Scientist Intern, XR Core AI, Meta, May 2024 - November 2024; Visiting Research Student at Mohamed Elhoseiny's Group, KAUST, December 2021 - March 2022; Research Assistant at Yongfeng Huang's Group, Tsinghua University, December 2020 - March 2021.
Education
PhD: King Abdullah University of Science and Technology, Computer Science, Advisor: Mohamed Elhoseiny; BSc: Jilin University, China, Computer Science.
Background
Research Interests: Generative Models (Image Generation, Video Generation), Vision-Language (Multi-Modal Comprehension). Currently a PhD student in Computer Science at King Abdullah University of Science and Technology, supervised by Mohamed Elhoseiny. Developed research and industry experience through internships at Meta and Nvidia.
Miscellany
Services include serving as a reviewer for multiple conferences (e.g., CVPR, ECCV, AAAI, ICLR, ICCV, SIGGRAPH Asia, NeurIPSW) and journals (e.g., IJCV, CVIU), and as a teaching assistant for the course KAUST CS 283 Deep Generative Modeling.