Peizhuo Li
Research Assistant at Galbot
Singapore, Singapore
Summary
🤩
Rockstar🎓
Top SchoolPeizhuo Li is a PhD researcher in robotics at the National University of Singapore with eight years of engineering experience focused on reinforcement learning and legged robot control. He combines academic rigor—currently pursuing doctoral work and teaching machine/deep learning for robotics—with hands-on implementation skills demonstrated by contributions to the SIGGRAPH 2020 deep-motion-editing library, where he improved motion retargeting, BVH parsing, and data handling. Based in Singapore and with prior industry internships at Continental and a current algorithm role at Galbot, he bridges applied research and product-oriented development. Notably, his background spans both mechanical engineering fundamentals and practical ML tooling, enabling him to translate locomotion research into robust control systems.
8 years of coding experience
2 years of employment as a software developer
Summer Exchange, Summer Exchange at Zhejiang UniversityDoctor of Philosophy (CDE-ENG), Mechanical Engineering (Robotics), Doctor of Philosophy (CDE-ENG), Mechanical Engineering (Robotics) at National University of Singapore
Chinese, English
Github Skills (6)
pytorch10
python10
animate9
animation9
deep-learning9
machine-learning8
Programming languages (4)
Github contributions (5)
DeepMotionEditing/deep-motion-editing
May 2020 - Oct 2021
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
Role in this project:
ML Engineer
ML EngineerContributions:53 commits, 21 PRs, 10 pushes in 1 year 5 months
Contributions summary:Peizhuo primarily focused on retargeting code within the deep-motion-editing library. They implemented code for BVH parsing and data handling, modifying existing scripts and adding new functionality to improve the retargeting process. The user also addressed compatibility issues, made updates to the test set, improved logging and output information, and removed redundant files. This indicates a focus on the core functionality of motion retargeting and improving the usability of the project.
style-transferend-to-endcomputer-animationdeep-learningoptical-flow
PeizhuoLi/neural-blend-shapes
May 2021 - Aug 2021
An end-to-end library for automatic character rigging, skinning, and blend shapes generation, as well as a visualization tool [SIGGRAPH 2021]
Contributions:35 commits, 1 PR, 10 pushes in 3 months
character-riggingend-to-endcomputer-graphicsblendrigging
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.