Yizhi Song
Research Scientist at TikTok
Bellevue, Washington, United States
Summary
👤
Senior🎓
Top SchoolYizhi Song is a research scientist at Bytedance/TikTok with a PhD in Computer Science from Purdue and eight years of experience building generative and vision-language models. He has shipped research and applied work on diffusion-based image/video generation, MLLMs for video understanding, and now focuses on post-training of foundation models including reward-model design and RL. His internship work at Adobe produced a unified, self-supervised diffusion framework for generative object compositing, and prior roles at Qualcomm and Tsinghua delivered practical, high-performance computer vision systems. Comfortable bridging theory and product, he has moved ideas from fast academic prototypes to production-facing video understanding and editing tools. Based in Bellevue, WA, Yizhi combines deep academic training with hands-on engineering at major industry labs, often tackling the intersection of geometry, appearance, and temporal consistency in visual generative systems.
8 years of coding experience
2 years of employment as a software developer
Beijing No.4 High SchoolDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Purdue UniversityBachelor of Engineering - BE, Computer Science, Bachelor of Engineering - BE, Computer Science at Zhejiang UniversityGithub contributions (5)
song630/BS-Project
May 2018 - Sep 2021
Contributions:2 releases, 34 commits, 30 pushes in 3 years 5 months
song630/Traffic-Sign-Detection-Learning
Jul 2018 - Aug 2018
Contributions:46 commits, 39 pushes in 17 days
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.