Tingwu Wang
Research scientist at Nvidia. Phone: +1 (416) 830 - 1487. Email = A+B;
A: wode406, tingwuw; wilsonwanguoft, tingwuwang
B: @hotmail.com, @nvidia.com, @gmail.com, @cs.toronto.edu

CV / Resume | Semantic Scholar | Google Scholar | Github | Twitter

I am currently a research scientist in Nvidia's animation group. Previously I obtained my PhD in University of Toronto, proudly advised by Prof. Sanja Fidler and Prof. Jimmy Ba. My name is pronounced as Ting-Wu, and it means "midday" in Chinese.

I have been exploring scalable, generalized and efficient methods to learn physics-based motion skills for robotics and animation tasks. Reinforcement learning and graph neural networks have been the two most important mathematical tools for my research.
I am especially interested in character animation. I believe in the near future, characters animated by neural networks will be used in real-life applications in movies and video games.
  • PhD in Computer Science @ University of Toronto Jan. 2018 - June. 2022
    Toronto, Ontario, Canada Advisor: Prof. Sanja Fidler and Prof. Jimmy Ba

  • MSc in Computer Science @ University of Toronto Aug. 2016 - Jan. 2018
    Toronto, Ontario, Canada, GPA: 4.0/4.0 Advisor: Prof. Sanja Fidler

  •  BSc in Electronic Engineering @ Tsinghua University Sep. 2012 - Jun. 2016
    Beijing, P. R. China Advisor: Prof. Xing Li

  •  Visitor in Electronic Information @ Technischen Universität München Sep. 2014 - Feb. 2015
    Munich, Bavaria, Germany
Publications and Patents

Physics-based Human Motion Estimation and Synthesis from Videos
Kevin Xie, Tingwu Wang, Umar Iqbal, Yunrong Guo, Sanja Fidler & Florian Shkurti
International Conference on Computer Vision, ICCV, 2021
Two Minute Papers | Arxiv | Project Webpage

UniCon: Universal Neural Controller For Physics-based Character Motion
Tingwu Wang, Yunrong Guo, Maria Shugrina & Sanja Fidler
Arxiv, 2020
Project Webpage | Arxiv | Teaser Demo | Video | PDF

Learning to Generate Diverse Dance Motions with Transformer
Jiaman Li, Yihang Yin, Hang Chu, Yi Zhou, Tingwu Wang, Sanja Fidler & Hao Li
Arxiv, 2020
Arxiv | Video | Code

Benchmarking Model-Based Reinforcement Learning
Tingwu Wang, Xuchan Bao, Ignasi Clavera, Jerrick Hoang, Yeming Wen, Eric Langlois, Shunshi Zhang, Guodong Zhang, Pieter Abbeel & Jimmy Ba
Arxiv, 2019
Code | Project Page | Arxiv | PDF

Exploring Model-based Planning with Policy Networks
Tingwu Wang & Jimmy Ba
8th International Conference on Learning Representations (ICLR), 2020
Code | Arxiv

Neural Graph Evolution: Towards Efficient Automatic Robot Design
Tingwu Wang*, Henry Zhou*, Sanja Fidler & Jimmy Ba
7th International Conference on Learning Representations (ICLR), 2019
Project Webpage | Slides | OpenReview | Code | Video | Arxiv

NerveNet: Learning Structured Policy with Graph Neural Networks
Tingwu Wang*, Renjie Liao*, Jimmy Ba & Sanja Fidler
6th International Conference on Learning Representations (ICLR), 2018
Project Webpage | Video | OpenReview | Slides

VirtualHome: Simulating Household Activities via Programs
Xavier Puig, Kevin Ra, Marko Boben, Jiaman Li, Tingwu Wang, Sanja Fidler & Antonio Torralba
Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (Oral)
Project Webpage | Slides | Talk | Arxiv | BBC News | MIT News

Access Points Selection in Super WiFi Network Powered by Solar Energy Harvesting
Tingwu Wang, Chunxiao Jiang & Yong Ren
IEEE Wireless Communications and Networking Conference (WCNC), 2016
PDF | IEEE Webpage

Access Strategy in Energy Harvesting Super WiFi Network: A POMDP Method
Tingwu Wang, Jian Wang, Chunxiao Jiang, Jingjing Wang & Yong Ren
IEEE 83rd Vehicular Technology Conference (VTC), 2016
PDF | Arxiv | IEEE Webpage | Code

Costume Detection and Attribute Value Identification Method and System
Qiu Shi, Po Man Cheng, Tingwu Wang, Yan Xia & Wei Zhang. Patent: CN105447529 A, 2016.
Work done as an intern in SenseTime. Contributions used in DeepFashion.

*Two authors contribute equally.


About Myself ( or Ting-Wu Wang)

I was born in Changsha. I was named by my grandfather, where "Ting-wu" means "the exact midday". The name comes from the Commentary on the Water Classic written by an ancient Chinese geographer called Li Daoyuan:
"To witness the Sun and the Moon, one shall wait until the exact midday or midnight."

Last Update: Jan, 2021; special thanks to Mr. Zhicong Lu, Mr. Ziyu Zhang, Mr. Bin Yang, Ms. Rachel Ye,
my supervisor Prof. Sanja Fidler for their help when I first arrived in this country. Thank you Mia Ma for being by my side :)!
Your help is so important to me, and I will always be grateful ;P
Template: this/that, ce/cette, das/der, kono/sono and zhege/nage.