Zhongwen Xu

Reseacher Seed at 字节跳动

Beijing, China
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Zhongwen Xu is a Principal Researcher based in Hong Kong with 11 years of experience specializing in reinforcement learning, large language model reasoning, and world-model-based agents. He has held senior research and leadership roles at Tencent, Sea AI Lab, and DeepMind, and taught a PhD-level RL course at the National University of Singapore, combining academic rigor with industry-scale engineering. His recent work explores scaling RL agents to play thousands of 3D video games and using RL-driven agents to probe LLM reasoning, reflecting a rare blend of empirical systems-building and theoretical insight. Trained with PhD work across University of Technology Sydney and University of Queensland and early research stints at Google Brain and Carnegie Mellon, he moves seamlessly between research, mentorship, and product-focused teams. Notably, he has experience in meta-gradient methods and JAX at DeepMind, signaling deep expertise in modern ML tooling and optimization techniques.
code11 years of coding experience
job9 years of employment as a software developer
bookDoctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at The University of Queensland
bookDoctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at University of Technology Sydney
bookBachelor’s Degree Computer Science, Bachelor’s Degree Computer Science at Zhejiang University
languagesChinese, Chinese, English
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (35)

reinforcement-learning-environments10
parallel-processing10
gpu10
box2d10
pybind1110
jax10
jit10
reinforcement-learning9
robotics9
rl-environment9
tpu9
statistics9
mujoco9
bayesian-methods8
python8

Programming languages (5)

C++CLuaJupyter NotebookPython

Github contributions (5)

github-logo-circle
zhongwen/predictron

Dec 2016 - Jan 2017

Tensorflow implementation of "The Predictron: End-To-End Learning and Planning"
Contributions:70 commits, 12 PRs, 59 pushes in 20 days
tensorflow
zhongwen/zhongwen.github.io

Apr 2015 - Dec 2016

Contributions:40 pushes, 1 branch in 1 year 8 months
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.
Request Free Trial