Yifeng Jiang
Research Scientist
NVIDIA
E-mail: yifengj at nvidia dot com
About
I am a Research Scientist in 3D Deep Learning at NVIDIA (Toronto AI Lab), based in Santa Clara, CA, USA. Previously, I received my Ph.D. in Computer Science from Stanford University, advised by Prof. C. Karen Liu, and my M.S. in Electrical and Computer Engineering from Georgia Tech. Prior to attending graduate school, I got my Bachelor's degree from Shanghai Jiao Tong University, where I was a member of the University of Michigan – Shanghai Jiao Tong University Joint Institute.
As a character animation researcher, I explore new methods that combine machine learning and simulation-based techniques to build AI-driven Digital Humans, and to enable humanoid robots with naturalistic movements through physics simulation. Besides motion generation, I have worked on human motion inference using wearable sensors, such as smart glasses, and on developing next-generation human simulations for biomechanics and healthcare applications.
Research
Constrained Diffusion with Trust Sampling
William Huang, Yifeng Jiang, Tom Van Wouwe, C. Karen Liu
Neural Information Processing Systems (NeurIPS), 2024
[Paper]
Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild
Lingni Ma, Yuting Ye, Fangzhou Hong, Vladimir Guzov, Yifeng Jiang, Rowan Postyeni, Luis Pesqueira, Alexander Gamino, Vijay Baiyya, Hyo Jin Kim, Kevin Bailey, David S. Fosas, C. Karen Liu, Ziwei Liu, Jakob Engel, Renzo De Nardi, Richard Newcombe
European Conference on Computer Vision (ECCV), 2024
[Website] [Paper] [Data]
DASH: Modularized Human Manipulation Simulation with Vision and Language for Embodied AI
Yifeng Jiang, Michelle Guo, Jiangshan Li, Ioannis Exarchos, Jiajun Wu, and C. Karen Liu
ACM SIGGRAPH / Eurographics Symposium on Computer Animation (SCA), 2021
[arXiv] [Video] [Talk Slides] [Code]
SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning
Yifeng Jiang, Tingnan Zhang, Daniel Ho, Yunfei Bai, C. Karen Liu, Sergey Levine, and Jie Tan
IEEE International Conference on Robotics and Automation (ICRA), 2021
[arXiv] [Video] [Talk Slides] [Code] [Google AI Blog]
Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation
Yifeng Jiang, Tom Van Wouwe, Friedl De Groote, and C. Karen Liu
ACM Transactions on Graphics (Proceedings of SIGGRAPH), 2019
[arXiv] [Video] [Talk Slides] [Code: Part1] [Code: Part2]
Data-Driven Approach to Simulating Realistic Human Joint Constraints
Yifeng Jiang and C. Karen Liu
IEEE International Conference on Robotics and Automation (ICRA), 2018
[arXiv] [Video] [Code: training] [Code: usage]Side Projects
Two extensions of “Modelling with implicit surfaces that interpolate”, a mini-project advised by Dr. Greg Turk, Georgia Tech
[PDF]
Dexterous Laparoscopic Electrosurgical Tool, with Tianlai Dong, Ziyue Xia and Zhaoyun Xiong, Bachelor Thesis (Capstone Design), advised by Dr. Kai Xu, Shanghai Jiao Tong University (SJTU)
[PDF]
Implementations of both single-cycle and pipeline MIPS computers in Verilog that support a subset of MIPS instruction set, with Bo Li and Peng Yuan, Computer Organizations Course, SJTU
[PDF]
Transform a digital photo into a pencil drawing: Re-implementation of the paper "Combining Sketch and Tone for Pencil Drawing Production" by Lu et al., Digital Image Processing Course, Rensselaer Polytechnic Institute (RPI)
[PDF]Awards
Meta Research PhD Fellowship Finalist, Meta Inc., 2023
School of Engineering Fellowship, Stanford University, 2019
IC Travel Grant, School of Interactive Computing, Georgia Tech, 2018
Outstanding Graduate of Shanghai, Shanghai Municipal Education Commission, 2016
Shanghai Scholarship for Distinguished Undergrads, Shanghai Municipal Education Commission, 2015
Professional Activities
Conference & Journal Reviewers: RSS, IROS, CoRL, ACM ToG, SIGGRAPH, SIGGRAPH Asia, RA-L, T-RO, IMWUT (UbiComp), EuroGraphics
Miscellaneous and Resources
I am fan of classical music. Here is an introductory list where I picked some of the most well-known pieces - those I feel being accessible to people who are interested in classical music, but do not know where to start. My favorite musician is Tchaikovsky.
I am also interested in psychology. Psychology and Life (Chinese Edition Here) is one of the best introductory books. I found reasoning about Nature vs Nurture a very good way to combat unconscious biases. I also enjoyed a lot watching Dr. Tal Ben-Shahar's open course on Positive Psychology (Chinese Translations Here). Finally, a wonderful (full of humor) introductory course at Yale.
My favorite books are Gone with the Wind and The Three-Body Problem.
An small visual catalog I made of some of the over 400 kinds of trees on Stanford campus.