Yunjey Choi
Tech Lead & Research Scientist at NAVER Corp
South Korea
Summary
🤩
Rockstar🎓
Top SchoolYunjey Choi is a tech lead and research scientist with 10 years of experience building and shipping generative vision models at NAVER AI Lab, where he now leads the Generation Team focused on visual imagination. His research contributions include core roles in StarGAN and StarGAN v2—CVPR papers with widespread academic and community impact—and practical work on evaluation metrics presented at ICML 2020. He bridges research and engineering, authoring reproducible PyTorch and TensorFlow implementations, dataset pipelines, evaluation tooling (LPIPS, FID), and training infrastructure that power both papers and open-source users. Known for turning cutting-edge ideas into well-documented code, he has influenced models that together have thousands of citations and GitHub stars. Trained at 고려대학교 with top academic standing, he combines strong theoretical grounding with hands-on ML engineering and a knack for making complex generative systems usable in practice.
10 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Computer Science, Major GPA: 4.38/4.5, Bachelor's degree, Computer Science, Major GPA: 4.38/4.5 at 고려대학교
Korean, English
Github Skills (22)
pytorch10
python10
evaluation10
dcgan10
machine-learning10
cgan10
data-loading10
dqn10
deeplearning-ai10
unsupervised-learning10
deep-learning10
image-generation10
tensorflow10
neural-network10
generative-model10
Programming languages (4)
Github contributions (5)
yunjey/domain-transfer-network
Dec 2016 - Jan 2017
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
Role in this project:
ML Engineer
ML EngineerContributions:52 commits, 41 pushes, 2 branches in 26 days
Contributions summary:Yunjey contributed to the TensorFlow implementation for unsupervised cross-domain image generation. They added code to download the SVHN dataset. Further commits included model version updates, implementing key components of the domain transfer network, including the discriminator, generator, and content extractor. Their work involved defining the model's architecture, loss functions, and optimizers.
deep-learningunsuperviseddomaintensorflowcross-domain
yunjey/pytorch-tutorial
Mar 2017 - Jul 2020
PyTorch Tutorial for Deep Learning Researchers
Role in this project:ML Engineer
ML EngineerContributions:138 commits, 39 PRs, 108 pushes in 3 years 4 months
Contributions summary:Yunjey added tutorials related to Deep Q-Networks (DQN) and Generative Adversarial Networks (GANs) to the PyTorch tutorial repository. These contributions involved creating and modifying code, including Jupyter Notebooks and Python scripts, to demonstrate deep learning concepts and model implementations. The changes focused on adding and editing tutorial files to the specified folder directory. Furthermore, code for saving the trained models was included.
deep-learningpytorchresearchersneural-networks
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.