Yaohua Zang is a Postdoctoral Researcher at the School of Engineering and Design, Technical University of Munich, working with Prof. Faidon-Stelios Koutsourelakis. His research lies at the intersection of artificial intelligence and scientific computing (AI4Science). In particular, he focus on inverse materials design with deep generative models, physics-informed machine learning for PDEs, and deep learning-based approaches for inverse problems.

Brief CV

• Postdoctoral Scholar, School of Engineering and Design, TUM, Germany, 2023-present
• Researcher, Huawei Hangzhou Research Center, China, 2021-2013
• Visiting Ph.D., School of Mathematics, Georgia Tech, USA, 2018-2019
  • Supervisor: Prof. Haomin Zhou
• Ph.D., Department of Mathematics, Zhejiang University, China, 2015-2021
  • Supervisor: Prof. Gang Bao
• B.Sc., Department of Mathematics, Jilin University, China, 2011-2015

Research Interests

AI4Science, Inverse Problems, Numerical PDEs, Inverse Material Design, Machine Learning Enhanced Optimal Control

Publications

Preprints

• Yaohua, Zang, Phaedon-Stelios Koutsourelakis. (2025). Design-GenNO: A Physics-Informed Generative Model with Neural Operators for Inverse Microstructure Design. arXiv preprint arXiv:2502.06250.
• Gang, Bao, Yaohua, Zang. (2025). ParticleWNN: a Novel Neural Networks Framework for Solving Partial Differential Equations. arXiv preprint arXiv:2509.08749.

Papers

• Yaohua Zang, Phaedon-Stelios Koutsourelakis. (2025). DGenNO: a novel physics-aware neural operator for solving forward and inverse PDE problems based on deep, generative probabilistic modeling. Journal of Computational Physics, 538, 114137.
• Wei Hu, Jihao Long, Yaohua Zang, Weinan E, Jiequn Han. (2025). Solving optimal control problems of rigid-body dynamics with collisions using the hybrid minimum principle. Communications in Nonlinear Science and Numerical Simulation, 143, 108603.
• Yaohua Zang, Phaedon-Stelios Koutsourelakis. (2025). PSP-GEN: Stochastic inversion of the Process-Structure-Property chain in materials design through deep, generative probabilistic modeling. Acta Materialia, 284, 120600.
• Vincent C Scholz, Yaohua Zang, Phaedon-Stelios Koutsourelakis. (2025). Weak neural variational inference for solving Bayesian inverse problems without forward models: applications in elastography. Computer Methods in Applied Mechanics and Engineering, 433, 117493.
• Hanwen Kang, Yaohua Zang, Xing Wang, Yaohui Chen. (2022). Uncertainty-driven Spiral Trajectory for Robotic Peg-in-Hole Assembly. IEEE Robotics and Automation Letters 7(3), 6661-6668.
• Yaohua Zang, Jihao Long, Xuanxi Zhang, Wei Hu, Weinan E, Jiequn Han. (2022). A Machine Learning Enhanced Algorithm for the Optimal Landing Problem. Mathematical and Scientific Machine Learning (pp. 319-334). PMLR.
• Gang Bao, Xiaojing Ye, Yaohua, Zang, Haomin Zhou. (2020). Numerical solution of inverse problems by weak adversarial networks. Inverse Problems, 36(11), 115003.
• Yaohua Zang, Gang Bao, Xiaojing Ye, Haomin Zhou. (2020). Weak adversarial networks for high-dimensional partial differential equations. Journal of Computational Physics, 411, 109409.
• Yaohua Zang, Gang Bao, Xiaojing Ye, Hongyuan Zha, Haomin Zhou. (2020). A jump stochastic differential equation approach for influence prediction on heterogeneous networks. Communications in Mathematical Sciences, 18(8), 2341-2359.

Contact Information

School of Engineering and Design
Technische Universität München
Boltzmannstraße 15
D-85748 Garching b. München
Office: Room 5504.EG.438
E-mail: yaohua.zang[at]tum[dot]de