Chunyuan Li
United States
Summary
👤
Senior🎓
Top SchoolChunyuan Li is a research scientist with a decade of experience at the intersection of deep learning and Bayesian probabilistic modeling, currently working on Agentic Vision at Google DeepMind. His PhD work at Duke advanced scalable Bayesian methods for neural network weight uncertainty and explored deep generative models (GANs, VAEs) as Bayesian components, applied across vision, NLP, and reinforcement learning. He has led vision-language research at ByteDance and contributed major multimodal projects at Microsoft Research, including the LLaVA series and GLIGen, driving both open-source and proprietary VLM development. Known for bridging rigorous Bayesian theory with practical, large-scale multimodal systems, he has a track record of moving research into production-grade models and benchmarks. An under-the-radar strength is his fluency across probabilistic inference, generative modeling, and real-time multimodal applications (video + voice), enabling novel agentic capabilities.
10 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Electrical and Computer Engineering, Doctor of Philosophy (Ph.D.), Electrical and Computer Engineering at Duke UniversityBachelor’s Degree, Bachelor’s Degree at Huazhong University of Science and TechnologyProgramming languages (1)
Github contributions (5)
uta-smile/WSISA
Jun 2021 - Apr 2022
Contributions:26 commits, 1 push in 9 months
chunyuan1/chunyuan1.github.io
Sep 2021 - Nov 2023
Contributions:21 pushes, 1 branch in 2 years 2 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.