About me
Hi! I’m Jooyeol Yun. I am a Ph.D. candidate at Korea Advanced Institute of Science and Technology (KAIST) supervised Prof. Jaegul Choo.
My research interests are
- AI for graphic designers. 🎨
- Image generation and editing.
- Enhancing the quality of everyday images taken by casual users. 📷
Education
Ph.D. in Artificial Intelligence at Korea Advanced Institue of Science and Technology (KAIST)
M.S. in Artificial Intelligence at Korea Advanced Institue of Science and Technology (KAIST)
B.S. in Computer Science and Engineering at Korea University
International Conference Publications
Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention
Kyungmin Jo, Jooyeol Yun, Jaegul Choo
Computer Vision and Pattern Recognition CVPR, 2025, AcceptedEnabling Region-Specific Control via Lassos in Point-Based Colorization
Sanghyeon Lee, Jooyeol Yun, Jaegul Choo
Association for the Advancement of Artificial Intelligence AAAI, 2025, AcceptedDisentangling Subject-Irrelevant Elements against Subject in Personalized Text-to-Image Diffusion via Filtered Self-distillation
Seunghwan Choi, Jooyeol Yun, Jeonghoon Park, and Jaegul Choo
Winter Conference on Applications of Computer Vision WACV, 2025, AcceptedScaling Up Personalized Image Aesthetic Assessment via Task Vector Customization
Jooyeol Yun and Jaegul Choo
European Conference on Computer Vision ECCV, 2024, AcceptedLearning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis
Minho Park*, Jooyeol Yun*, Seunghwan Choi, and Jaegul Choo (*: equal contributions)
International Conference on Computer Vision ICCV, 2023, AcceptediColoriT: Towards Propagating Hints to the Right Region for Interactive Colorization via Leveraging Vision Transformer
Jooyeol Yun*, Sanghyeon Lee*, Minho Park*, and Jaegul Choo (*: equal contributions)
Winter Conference on Applications of Computer Vision WACV, 2023, AcceptedImproving Face Recognition with Large Age Gaps by Learning to Distinguish Children
Jungsoo Lee*, Jooyeol Yun*, Sunghyun Park, Yonggyu Kim, and Jaegul Choo (*: equal contributions)
British Machine Vision Conference BMVC, 2021, Accepted