Doyup Lee
Research Scientist in AI
New York, New York, United States
Summary
🤩
RockstarDoyup Lee is a research scientist in AI with eight years of experience building foundation models and generative media systems, currently based in New York. He has been a core contributor to Runway’s Gen-3 and Gen-4 flagship products and led applied research teams at Kakao Brain focused on large-scale generative models for images, video, and 3D assets. His research blends representation learning, implicit neural representations, and agentic software to amplify creative processes and media AI. Trained through a PhD track at POSTECH, he has a strong background in multimodal and low-label learning, spatiotemporal forecasting, and robustness for visual models. Doyup pairs hands-on product impact with deep academic rigor, often translating advanced generative techniques into production-facing systems. An interesting through-line is his consistent focus on bridging creative workflows and foundational model research, aiming to make generative AI both practical and artistically expressive.
8 years of coding experience
Github Skills (84)
anomaly-detection10
python10
semi-supervised-learning10
deep-learning10
gpu10
gpu-acceleration10
numpy10
neural-network10
computer-vision10
tensor10
natural-language-processing10
autograd10
dcgan10
machine-learning10
generative-adversarial-network10
Programming languages (4)
Github contributions (5)
LeeDoYup/LeeDoYup
Jul 2020 - Aug 2025
Contributions:14 pushes, 1 branch in 5 years 1 month
LeeDoYup/RobustSTL
Feb 2019 - Jun 2020
Unofficial Implementation of RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series (AAAI 2019)
Contributions:9 commits, 4 PRs, 7 pushes in 1 year 4 months
time-series
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.