Zhejiang University
Visual Analytics and Intelligence Group (📮 ZJUVAI)
<aside> <img src="/icons/mail_gray.svg" alt="/icons/mail_gray.svg" width="40px" /> Email
</aside>
<aside> <img src="/icons/graduate_gray.svg" alt="/icons/graduate_gray.svg" width="40px" /> Google Scholar
</aside>
<aside> <img src="attachment:d560817c-b8a4-4c76-bac8-80d9755a896f:25231.png" alt="attachment:d560817c-b8a4-4c76-bac8-80d9755a896f:25231.png" width="40px" /> GitHub
</aside>
$\color{black}\rule{415px}{2px}$
I am a tenure-track Assistant Professor in the School of Software at Zhejiang University. I received Ph.D. Degree in Computer Science from the State Key Laboratory of CAD&CG, Zhejiang University under the supervision of Prof. Wei Chen. My research interests include Math and Visualization. Here is the homepage of Visual Analytics and Intelligence Group of ZJU.
I am actively recruiting Master’s students to join VAI. Research in this area involves high coding, a math background, and hard work. Visiting scholars and interns are also very welcome! If you are interested, please submit your Application.
[2025-06-25] 🛞 Don't Reinvent the Wheel is selected for an oral presentation at ACL 2025.
[2025-06-19] 🕸️ Graphon-Based Network Visualization is accept by TVCG
[2025-02-12] 🔥 We have presented a multimodal reasoning model, R1-Onevision.
[ 🔍 Visualization] See the Black Box
This research designs visualization tools to illuminate the inner workings of complex AI models. By translating opaque decision-making processes into clear, interactive visualizations, this work builds essential bridges of trust between humans and intelligent systems, fostering safer and more collaborative tools.
[🤖LLM] Understand the Universe
My research focuses on developing large-scale language models capable of sophisticated multimodal reasoning, enabling more natural and context-aware interactions. The goal is to create a model with a deeper, more contextual, and commonsense understanding of our world.
[ 🧭AI4Research] Accelerate Scientific Discovery
This research centers on designing large-scale models that integrate formal methods with machine learning to autonomously prove mathematical theorems and push the boundaries of machine reasoning. The strategic roadmap unfolds in three stages: first, proving capability on benchmarks like the IMO; second, empowering scientists as synergistic partners; and ultimately, pioneering entirely new scientific theories.