Select language
< Return to main menu
du-468.jpg

Tao Du

PI(September 2022 to present)
Assistant Professor

Biography

Tao Du is an Assistant Professor at the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University. His research aims at developing computational methods to help people understand physical systems. Before joining Tsinghua University, he completed his Ph.D. at MIT in 2021 under the supervision of Wojciech Matusik and continued as a Postdoctoral Associate from 2021 to 2022. At MIT, he developed differentiable deformable-solid and fluid simulators and explored their downstream applications in machine learning and robotics. His research work has been featured by technical media outlets including WIRED, IEEE Spectrum, TechCrunch, Engadget, and so on. In addition, he was recognized by NeurIPS (2021 and 2022) and ICML (2022) as an outstanding reviewer.

Personal honor

NeurIPS top reviewer (2022)

ICML outstanding reviewer (2022)

NeurIPS outstanding reviewer (2021)


Research Direction

•Computer Graphics


Research topic

•Physics Simulation 

•Computational Design and Fabrication

Members

1687943318052.jpg

Open positions

Research Direction:

Computer Graphics: Physics Simulation/High-Performance Computing

Responsibilities:

Developing high-performance multi-physics simulators for learning/robotics applications.

Required Qualification:

CS/Math/Physics major with strong mathematical backgrounds;

Prior experience with computer graphics research and proficient in C++/CUDA programming.

Please send your CV:

leqq@sqz.ac.cn


News

Deep Learning for Physics Simulation accepted to SIGGRAPH Course (2023.5)

PI Tao Du will present this course at ACM SIGGRAPH 2023, the premier academic conference in computer graphics. The course reviews the recent trends in applying learning methods to physics simulation problem and introduces several representative works in this field, including the latest ICML work from our group. More details about the course will be released at https://people.iiis.tsinghua.edu.cn/~taodu/dl4sim/.


Paper/Publication

Deep Learning for Physics Simulation, Tao Du, SIGGRAPH 2023 Course.

Learning Preconditioner for Conjugate Gradient PDE Solvers, Yichen Li, Peter Yichen Chen, Tao Du, Wojciech Matusik, ICML 2023.

Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics, Pingchuan Ma, Peter Yichen Chen, Bolei Deng, Joshua B. Tenenbaum, Tao Du, Chuang Gan, Wojciech Matusik, ICML 2023.

DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics, Sizhe Li, Zhiao Huang, Tao Chen, Tao Du, Hao Su, Joshua B. Tenenbaum, Chuang Gan, ICLR 2023.