Yuelin Zhang

Prior to that, I obtained CS bachelor degree at Shenyuan Honors College, Beihang University.

Email  /  Google Scholar  /  Github  

My current research focuses on multimodal large language models, with a particular emphasis on improving their perceptual and spatial reasoning capabilities.

I am also interested in developing efficient online video models and enhancing the applicability of vision-language models in real-world scenarios.

Previously, my research centered on geometric graph neural networks, especially for simulating complex physical systems.

Representative papers are highlighted.

Last updated: August 15, 2026

Template from Jon Barron. Big thanks!