I’m a second-year master’s student at Zhejiang University. I have published several papers as the first author at top AI conferences such as ICLR and ACM MM. My research focuses on Multimodal Large Language Models, especially the applications of Vision-Language Models and effective fine-tuning strategies. Recently, I’ve been particularly interested in streaming video understanding, aiming to enable models to continuously interpret live video streams with strong temporal reasoning and timely responses. My long-term goal is to build a truly user-friendly AI assistant—reliable, practical, and proactive—that can understand visual content, communicate naturally, and help users accomplish real-world tasks with a consistently solid experience.

📖 Educations

2024.09 - 2027.06 (now), Software School, Software Engineer, Zhejiang University.
2020.09 - 2024.06, Undergraduate, Software College, Software Engineering (International (English)), Northeastern University.