Jooyeol Yun

About me

Hi! I'm Jooyeol Yun, a Ph.D. candidate at the Kim Jaechul Graduate School of AI, KAIST, supervised by Prof. Jaegul Choo. My research focuses on:

• AI for graphic designers
• Generative modeling of design assets

Publications

• CVPR 2026 · Highlight

  Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure

  Jooyeol Yun, Jaegul Choo

  Project arXiv Code

• CVPR 2026

  Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models

  Seunghwan Choi, Jooyeol Yun, Youngdo Lee, Jaegul Choo

  Paper

• ICRA 2026

  ACG: Action Coherence Guidance for Flow-based Vision-Language-Action Models

  Minho Park, Kinam Kim, Junha Hyung, Hyojin Jang, Hoiyeong Jin, Jooyeol Yun, Hojoon Lee, Jaegul Choo

  arXiv

• ACL 2026 · Findings

  Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation

  Kyudan Jung, Hojun Cho, Jooyeol Yun, Soyoung Yang, Jaehyeok Jang, Jaegul Choo

  arXiv

• AAAI 2026 · Oral

  SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation

  Minho Park*, Taewoong Kang*, Jooyeol Yun, Seongwon Hwang, Jaegul Choo

  Project arXiv

• arXiv 2025

  DesignLab: Designing Slides Through Iterative Detection and Correction

  Jooyeol Yun, Heng Wang, Yotaro Shimose, Jaegul Choo, Shingo Takamatsu

  Project arXiv

• ICCV 2025 · Workshop

  Imagining the Unseen: Generative Location Modeling for Object Placement

  Jooyeol Yun, Davide Abati, Mohamed Omran, Jaegul Choo, Amirhossein Habibian, Auke Wiggers

  arXiv

• CVPR 2025

  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

  arXiv

• AAAI 2025

  Enabling Region-Specific Control via Lassos in Point-Based Colorization

  Sanghyeon Lee, Jooyeol Yun, Jaegul Choo

  arXiv

• WACV 2025

  Disentangling Subject-Irrelevant Elements against Subject in Personalized Text-to-Image Diffusion via Filtered Self-distillation

  Seunghwan Choi, Jooyeol Yun, Jeonghoon Park, Jaegul Choo

  Paper

• ECCV 2024

  Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization

  Jooyeol Yun, Jaegul Choo

  Project arXiv Code

• ICCV 2023

  Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis

  Minho Park*, Jooyeol Yun*, Seunghwan Choi, Jaegul Choo

  arXiv

• WACV 2023

  iColoriT: Towards Propagating Hints to the Right Region for Interactive Colorization via Leveraging Vision Transformer

  Jooyeol Yun*, Sanghyeon Lee*, Minho Park*, Jaegul Choo

  arXiv

• BMVC 2021

  Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children

  Jungsoo Lee*, Jooyeol Yun*, Sunghyun Park, Yonggyu Kim, Jaegul Choo

  arXiv

* denotes equal contribution.

Education