AI for Science · Multimodal Models · Scientific Reasoning
I am a researcher at Shanghai AI Laboratory, working on AI for Science.
My research focuses on multimodal models and scientific reasoning, with particular interests in equation discovery and structural inference of dynamical systems.
If you are interested in collaboration opportunities, please contact me at
VIPER-R1, our work on visual-to-symbolic physics formula discovery, has been accepted to NeurIPS 2026.
May 20, 2025
Joined Shanghai AI Laboratory as a researcher.
Nov 23, 2024
Successfully defended my doctoral thesis!
Sep 26, 2024
Two papers accepted by NeurIPS2024!
“Structural Inference of Dynamical Systems with Conjoined State Space Models” is accepted by NeurIPS 2024 Main Track.
“Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data” is accepted by NeurIPS 2024 Datasets and Benchmarks Track.
Jun 12, 2024
Our benchmark on LLMs’ ability to reason with educational knowledge graphs is now live!
selected publications
NeurIPS
Mimicking the Physicist’s Eye: A VLM-centric Approach for Physics Formula Discovery
Jiaqi Liu, Songning Lai, Pengze Li, Di Yu, …, and Aoran WangJiaqi Liu, Songning Lai, Pengze Li, Di Yu, Wenjie Zhou, Yiyang Zhou, Peng Xia, Zijun Wang, Xi Chen, Shixiang Tang, Lei Bai, Wanli Ouyang, Mingyu Ding, Huaxiu Yao, and Aoran Wang
In Advances in Neural Information Processing Systems 2026 · Accepted
