I am a Ph.D. student in a joint program between Shanghai Jiao Tong University and Shanghai Innovation
Institute starting in 2026, advised by Assistant Professor Xue Yang
at Shanghai Jiao Tong University. I received my M.S. in Information and Communication Engineering from
Beijing Institute of Technology, and my B.Eng. in Automation from Central South University. My previous
research interests include foundation vision models and their applications in remote sensing,
cross-modal representation and alignment, and
audio-video understanding and evaluation.
My current research focuses on AI Agents, spanning data pipelines, framework design,
evaluation methods, and model optimization.
M.S. · Beijing Institute of Technology, Information and Communication Engineering 2023.09 – 2026.06
Information and Communication Engineering
B.Eng. · Central South University, Automation 2019.09 – 2023.06
Automation
Internship
Tencent Youtu Lab · Research Intern, ShenNong Research Center 2025.12 – 2026.09
Worked on omni-modal model development: designed and built an automated evaluation system, contributed to dataset evaluation and cleaning, and wrote and submitted one paper (under review).
DeepGlint · Research Intern, Foundation Model Group 2025.06 – 2025.10
Conducted research on multimodal retrieval foundation models; one first-authored paper was accepted to NeurIPS 2026 as a Spotlight.
Honors & Awards
2026.06 Xu Teli Scholarship Candidate (6 graduate students selected university-wide)