About Me

Mingrui Zhang

I am a fourth year Ph.D. student at Imperial College London, advised by Prof. Matthew Piggott. I obtained my Master degree from Imperial College London and Bachelor's degree from Zhejiang University. I've did research at Taichi Graphics, where I explored differentiable physical simulation and automatic differentiation compilers, under the supervision of Dr. Tiantian Liu.

My research focuses on differentiable physical simulation and applying machine learning techniques to enhance simulation. I am also interested in incorporating scientific knowledge to improve the performance of machine learning algorithms.

[Github] | [Google Scholar]


Publications

image

End-to-end wind turbine wake modelling with deep graph representation learning

Siyi Li, Mingrui Zhang, Matthew Piggott
Applied Energy, 2023
[Paper]

image

Complex locomotion skill learning via differentiable physics

Yu Fang*, Jiancheng Liu*, Mingrui Zhang*, Jiasheng Zhang, Yidong Ma, Minchen Li, Yuanming Hu, Chenfanfu Jiang, Tiantian Liu (*Equal contribution)
arXiv preprint, 2022
[Paper]

image

Learning to Estimate and Refine Fluid Motion with Physical Dynamics

Mingrui Zhang, Jianhong Wang, James Tlhomole, Matthew D Piggott
International Conference on Machine Learning (ICML), 2022
[Paper]

image

M2N: Mesh movement networks for PDE solvers

Wenbin Song*, Mingrui Zhang*, Joseph G Wallwork, Junpeng Gao, Zheng Tian, Fanglei Sun, Matthew D Piggott, Junqing Chen, Zuoqiang Shi, Xiang Chen, Jun Wang (*Equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), 2022
[Paper]

image

E2N: error estimation networks for goal-oriented mesh adaptation

Joseph G Wallwork, Jingyi Lu, Mingrui Zhang, Matthew D Piggott
arXiv preprint, 2022
[Paper]

image

Unsupervised learning of particle image velocimetry

Mingrui Zhang, Matthew Piggott
International Conference on High Performance Computing (ISC), 2020
[Paper]