Geonmo Gu is a research scientist specializing in computer vision with nine years of experience building multimodal models and practical vision systems. Based in Seoul, he led large-scale multimodal representation efforts at NAVER—collecting 4 billion image-text pairs and publishing state-of-the-art composed image retrieval work (CVPR24, CVPRW24)—and created Graphit, a diffusion-based generative editor with demos on GitHub and HuggingFace. His prior work includes lightweight, real-time vision modules like M-LSD integrated into ControlNet and Visual ChatGPT, plus metric learning advances for image retrieval across top conferences. He briefly contributed to data-driven services at AWS before returning to NAVER AI Lab as a research scientist, blending production-savvy engineering with cutting-edge research. Known online as "Happy Computer Vision," he combines large-scale engineering (80 A100 GPUs) with reproducible open releases.
9 years of coding experience
7 years of employment as a software developer
Bachelor, Electrical and Electronics Engineering, Bachelor, Electrical and Electronics Engineering at Yonsei University
Master, Electrical and Electronics Engineering, Master, Electrical and Electronics Engineering at Korea Advanced Institute of Science and Technology
Contributions:1 PR, 17 pushes, 1 branch in 8 years 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.