Donghoon Ahn
Research Assistant at University of California, Berkeley
Seoul, South Korea
Summary
🤩
Rockstar🎓
Top SchoolDonghoon Ahn is a computer vision researcher and incoming PhD student at UC Berkeley—advised by Alexei Efros—specializing in generative models with a deep focus on diffusion-based image, video, and 3D generation. As an undergraduate researcher at Korea University and KAIST, he contributed to NeurIPS 2023 and ECCV 2024 papers exploring score debiasing, attention-guided sampling, and geometry-aware score distillation, reflecting a blend of theoretical and practical research. He brings nine years of technical experience including building Spring-based intranet systems during military service, demonstrating an unusual mix of production engineering and cutting-edge ML research. Donghoon is driven by the idea of embedding physical inductive biases into generative models to improve real-world consistency and personalization, and is actively seeking PhD lab collaborations starting next fall.
9 years of coding experience
3 years of employment as a software developer
Computer Science and Engineering, 4.36 / 4.5 (all) 4.43 / 4.5 (major), Computer Science and Engineering, 4.36 / 4.5 (all) 4.43 / 4.5 (major) at 고려대학교
Github Skills (31)
pytorch10
diffusion-models10
stable-diffusion10
diffusers10
flax10
text2image10
audio10
deep-learning10
image-generation10
flux10
jax10
typescript8
geometry7
microsoft7
electron7
Programming languages (6)
Github contributions (5)
sunovivid/Problem-Solving
Apr 2020 - Jun 2022
Contributions:35 commits, 27 pushes, 1 branch in 2 years 2 months
sunovivid/sunovivid
May 2022 - Sep 2024
Contributions:12 pushes, 1 branch in 2 years 4 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.