Rui Zhang

Post-Doc

Zhang Rui received a Bachelor of Science degree from East China Normal University in 2019 and a Doctor of Science degree from the Academy of Mathematics and Systems Science, Chinese Academy of Sciences, in 2024. After completing his doctorate, he joined Renmin University of China as a postdoctoral researcher. His main research interests include physics-driven deep learning methods and interpretable neural networks. During his doctoral studies, he received several honors, including the Special Prize of the Dean’s Scholarship of the Academy of Mathematics and Systems Science, Chinese Academy of Sciences, and the Hua Loo-Keng Scholarship. He has participated in multiple projects under the National Key R&D Program of China, and has served as principal investigator for a National Natural Science Foundation of China Young Scientists Fund project and a China Postdoctoral Science Foundation General Program project, with total research funding under his responsibility amounting to RMB 3.94 million. As first or corresponding author, he has published papers in leading international journals and conferences, including National Science Review, IEEE TPAMI, Physics of Fluids, AAAI, and IJCAI.

Enter Personal Website

Education

2019-2024，Academy of Mathematics and Systems Science, Chinese Academy of Sciences，Ph.D., Supervisor: Zhi-Ming Ma

2015-2019，East China Normal University，School of Mathematical Sciences，B.S.

Work Experience

2024-Now，Renmin University of China, Gaoling School of Artificial Intelligence, Post-Doc，Supervisor：Hao Sun

RESEARCH INTERESTS

AI for scientific computing

Interpretable machine learning

Publications

Note: * equal contribution, # corresponding author

Preprint

[13] Mao, R.*, Zhang, R.*, Bai, X., Wu, T., Zhang, T., Chen, Z., Lin, M., Zeng, B., Xu, Y., Xiang, Y., Zhang, H., Goswami, S., Dawe, P. A., Xu, Y., An, Z., Yan, M., Lu, X., Wang, Y., Bai, R., Gao, H., Fang, X., Li, H., Sun, H.#, Chen, Z. X.# (2026). Benchmarking Neural Surrogates on Realistic Spatiotemporal Multiphysics Flows. arXiv preprint arXiv:2512.18595.
[12] Zhang, R., Wan, H., Liu, Y., Sun, H.# (2026). Stable Spectral Neural Operator for Learning Stiff PDE Systems from Limited Data. arXiv preprint arXiv:2512.11686.
[11] Zhang, R., Meng, Q., Wan, H., Liu, Y., Ma, Z-M., & Sun, H. (2026). OmniFluids: Unified Physics Pre-trained Modeling of Fluid Dynamics. arXiv preprint arXiv:2506.10862.
[10] Wan, H., Zhang, R.#, & Sun, H.# (2026). Spectral-inspired Operator Learning with Limited Data and Unknown Physics. arXiv preprint arXiv:2505.21573.

2026

[9] Wan, H., Wang, Q., Mi, Y., Zhang, R.#, & Sun, H.# (2026). PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Burst-sampled Spatiotemporal Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence.
[8] Du, X.*#, Dou, Q.*, Fan, L., & Zhang, R.# (2026). Flexible Concept Bottleneck Model. Proceedings of the AAAI Conference on Artificial Intelligence.

2025

[7] Wan, H.*, Zhang, R.*, Wang, Q., Liu, Y., & Sun, H. (2025). PeSANet: Physics-encoded Spectral Attention Network for Simulating PDE-Governed Complex Systems. International Joint Conference on Artificial Intelligence.
[6] Zhang, R., Meng, Q., Zhu, R., Wang, Y., Shi, W., Zhang, S., Ma, Z.M., & Liu, T.Y. (2025). Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence.
[5] Zhang, R.*, Du, X.*, Yan, J., & Zhang, S. (2025). The Decoupling Concept Bottleneck Model. IEEE Transactions on Pattern Analysis and Machine Intelligence.

2024

[4] Zhang, R., Meng, Q., & Ma, Z.M. (2024). Deciphering and Integrating Invariants for Neural Operator Learning with Various Physical Mechanisms. National Science Review.

2022

[3] Zhang, R., Hu, P., Meng, Q., Wang, Y., Zhu, R., Chen, B., Ma, Z.M., & Liu, T.Y. (2022). DRVN (Deep Random Vortex Network): A New Physics-informed Machine Learning Method for Simulating and Inferring Incompressible Fluid Flows. Physics of Fluids.
[2] Zhang, R., & Zhang, S. (2022). Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime. In Proceedings of the AAAI Conference on Artificial Intelligence (Oral).
[1] Du, X., Yan, J., Zhang, R., & Zha, H. (2022). Cross-network Skip-gram Embedding for Joint Network Alignment and Link Prediction. IEEE Transactions on Knowledge and Data Engineering.

Honors and Awards

AMSS Special Prize of President Scholarship

Hua Loo-Keng Scholarship

Outstanding Undergraduate in Shanghai

Services

Reviewers：TPAMI, TKDE, TMLR, TSC, ICML, ICLR, NeurIPS, KDD, AAAI…

Contact

Email：rayzhang@ruc.edu.cn

Website：https://optray.github.io/