Yuanming Hu 胡渊鸣
I graduated with honor from Tsinghua University (Yao class) in July 2017. I worked on deep learning and computer vision, during my internship with Stephen Lin at Microsoft Research Asia. My undergrad thesis is on automatic (differentiable) photo post-processing using reinforcement & adversarial learning (TOG & SIGGRAPH 2018). I completed my master thesis (The ChainQueen Differentiable Physical Simulator) with Wojciech Matusik in November 2018. My research has been partly supported by an Edwin Webster fellowship, a Snap Research fellowship, and an Adobe Research fellowship.
I designed and implemented the Taichi programming language.
Contact: yuanming _at_ mit.edu Github
My current research interests include ...
- High-performance systems for computer graphics:
- The Taichi programming language for high-performance sparse visual computing (main project since January 2019);
- DiffTaichi: Differentiable programming for physical simulation.
- Giga-Voxel Narrowband TopOpt: topology optimization of 1,040,875,347 voxels on a single computer with an MGPCG FEM solver and SPGrid;
- SIMD MLS-MPM: hand-optimized CPU MLS-MPM 14x faster than the previous state of the art.
- Physical simulation for VFX, machine learning, and robotics:
- Computational photography and deep learning:
- (11/2019) Andy's NeurIPS paper on learning-in-the-loop optimization with the differentiable MPM simulator (ChainQueen) made MIT front page!
- (09/2019) The differentiable programming extension (DiffTaichi) for the Taichi programming language is released. [paper] [code]
- (08/2019)The Taichi programming language for spatially sparse computation (SIGGRAPH Asia 2019) is released. [paper][code]
- (07/2019) Welcome to our SIGGRAPH 2019 course On Hybrid Lagrangian-Eulerian Simulation Methods: Practical Notes and High-Performance Aspects (Thursday 3:45pm-5:15pm Room 408AB)! [Course Website]
- (07/2019) MLS-MPM is featured on Two Minute Papers.
- (06/2019) ChainQueen is on the MIT CSAIL news.
- (05/2019) The code for our 1,040,875,347 voxel topology optimization is released.
Learning-In-The-Loop Optimization: End-To-End Control and Co-Design of Soft Robots Through Learned Deep Latent Representations
NeurIPS 2019 [Video]
Andrew Spielberg, Allan Zhao, Tao Du, Yuanming Hu, Daniela Rus, Wojciech Matusik
DiffTaichi: Differentiable Programming for Physical Simulation
Yuanming Hu, Luke Anderson, Tzu-Mao Li, Qi Sun, Nathan Carr, Jonathan Ragan-Kelley, Fredo Durand
Yuanming Hu, Tzu-Mao Li, Luke Anderson, Jonathan Ragan-Kelley, Fredo Durand
On Hybrid Lagrangian-Eulerian Simulation Methods: Practical Notes and High-Performance Aspects
SIGGRAPH 2019 Courses
Yuanming Hu, Xinxin Zhang, Ming Gao, Chenfanfu Jiang
Ph.D. Student@Massachusetts Institute of Technology 2017.9-
I am a Ph.D. student at MIT CSAIL, working on computational photography, physical simulation, and high-performance graphics systems.
Visiting Student@The University of Pennsylvania 2017.7-2017.8
I visited Prof. Chenfanfu Jiang during summer 2017. We developed a new material point method that is faster and supports cutting and rigid-body coupling (SIGGRAPH 2018).
Research Intern@Microsoft Research Asia 2016.9-2017.6
Computer vision research with Dr. Stephen Lin and Dr. Baoyuan Wang. We developed a novel color constancy algorithm that outperforms the previous state of the art with a 100-fold speed increase (CVPR 2017, oral), and a practical generative adversarial network (combined with reinforcement learning) that is capable of processing images with no resolution limits (ACM TOG, presented at SIGGRAPH 2018).
Asia-Pacific Informatics Olympiad 2012, China District
China National Olympiad in Informatics 2012
ACM-ICPC Asia Changsha Regional Contest 2013, with my team
ACM-ICPC Asia Shanghai Regional Contest 2014, with my team
China National Olympiad in Informatics 2014
Gold Medal, 1st / 450
Gold Medal, 13th / 350
Gold Medal, 3rd / 200
Gold Medal, 5th / 250