About me

Hi, I am a second-year Ph.D. student at LMU Munich (world ranking 58, 2nd in 🇩🇪), supervised by Prof. Thomas Seidl (MCML Diector, latest service: ACM KDD 2026 SAC). I also collaborate with Prof. Hinrich Schütze, Prof. Jiancheng Lv, and Prof. Barbara Plank. I maintain close ties with several leading research and industry groups: Qwen 👤 A, 👤 B, CIS NLP, and MaiNLP. My research focus is around large vision-langugae models, where I am particularly interested in how VLMs perceive and understand the physical world to develop advanced reasoning and planning capabilities. I believe vision and language are the two fundamental pillars through which humans perceives and interacts with the physical world. My mission is to bridge VLMs into physical reality, empowering them to perceive and act with human-like understanding.

Before diving into my PhD, I was lucky to have a wealth of exchange experiences. Exploring the world and seeing it through different lenses has been an invaluable part of my personal growth: Arizona State University 🇺🇸 (advised by Prof. Huan Liu, Kai Shu, and Guoliang Xue); University of Oxford 🇬🇧.

🚀 News

• [2026.01] ✨ Our work “Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering” has been accepted by ICLR 26 - See you in Rio!