Avatar

Chanyoung Kim

MS/PhD Student

MICV Lab, Yonsei University


CV | Google Scholar | | |


Hello, Welcome :)

My name is Chanyoung Kim (김찬영), a 2nd-year MS/PhD student at Yonsei University, advised by professor Seong Jae Hwang in the Medical Imaging & Computer Vision Lab. I collaborate with Prof. Ming-Hsuan Yang (UC Merced & Google DeepMind) and Dr. Roberto Alcover-Couso (Amazon). I also serve as a Local Student Liaison Officer for MICCAI Student Board.

My research interests include vision-language alignment for visual dense prediction, spectral and graph-theoretic approaches to vision representation, and task-specific crafting of image representations from foundation models.

I am currently looking for a research internship position for the summer of 2025!

Contact

  • chanyoung@yonsei.ac.kr

    chanyoung@ieee.org

  • Engineering Research Park, Yonsei University, Seoul, Republic of Korea

Education

  • MS/PhD in Artificial Intelligence, 2023~Present

    Yonsei University, Seoul

  • BS in Intelligent Mechatronics Engineering, 2017~2023

    Sejong University, Seoul

Recent News🎉

  • [May 2025] One paper has been early accepted (< 9%) to MICCAI 2025!
  • [Feb 2025] Two papers (CASS & STORM) have been accepted to CVPR 2025!
  • [Feb 2025] EAGLE (CVPR 2024 Highlight) won Best Academic Paper Award at Yonsei University Fall 2024.
  • [Jan 2025] Initiated research collaboration with Roberto Alcover-Couso (Amazon).
  • [Jan 2025] Joined MICCAI Student Board as a Local Student Liaison Officer.
  • [Sep 2024] One paper has been accepted as a Spotlight🔦(< 3.4%) at MICCAI 2024!
  • [Aug 2024] Initiated research collaboration with Prof. Ming-Hsuan Yang (UC Merced & Google DeepMind).
  • [Mar 2024] One paper has been accepted to CVPR 2024 as a Highlight💫(< 2.8%)!
  • [Sep 2023] Joined MICV Lab at Yonsei University for my joint MS/PhD Program.

Research Experiences

  • Medical Imaging & Computer Vision Lab, Yonsei University, Seoul
    Mar 2023 - Present

    Graduate Student Researcher
    • Semantic Segmentation (CVPR 2024, CVPR 2025)
    • Medical Image Quality Signals (MICCAI 2024, arXiv 2025)
    • Multimodal Image Synthesis (CVPR 2025)
  • Computer Vision Lab, Korea University, Seoul
    Feb 2021 - Dec 2022

    Undergraduate Research Intern
    • Audio-Visual Representation (CVPR 2022, ECCV 2022, NeurIPSW 2021, arXiv 2023)

Publications

    🎨 Task-Specific Adaptation of Visual Foundation Model Features

  • Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation

    Chanyoung Kim, Dayun Ju, Woojung Han, Ming-Hsuan Yang, Seong Jae Hwang

    CVPR 2025

    Short version at "Transformers for Vision" Workshop @ CVPR 2025

    [ project / paper / arXiv / code ]

  • EAGLE🦅: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation

    Chanyoung Kim*, Woojung Han*, Dayun Ju, Seong Jae Hwang

    CVPR 2024 Highlight (Acceptance Rate < 2.8%)

    Short version at "Causal and Object-Centric Representations for Robotics" Workshop @ CVPR 2024

    [ project / paper / arXiv / code ]

    • ⚕️ Medical Image Quality Signal

  • Pathology-Aware Adaptive Watermarking for Text-Driven Medical Image Synthesis

    Chanyoung Kim*, Dayun Ju*, Jinyeong Kim, Woojung Han, Roberto Alcover-Couso, Seong Jae Hwang

    MICCAI 2025 Early Acceptance (Acceptance Rate < 9%)

    [ arXiv ]

  • Advancing Text-Driven Chest X-Ray Generation with Policy-Based Reinforcement Learning

    Woojung Han*, Chanyoung Kim*, Dayun Ju, Yumin Shim, Seong Jae Hwang

    MICCAI 2024 Spotlight (Acceptance Rate < 3.4%)

    [ project / arXiv / code ]

    • 🖼️ Multimodal Image Synthesis

  • Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis

    Woojung Han, Yeonkyung Lee, Chanyoung Kim, Kwanghyun Park, Seong Jae Hwang

    CVPR 2025

    [ arXiv ]

  • LISA: Localized Image Stylization with Audio via Implicit Neural Representation

    Seung Hyun Lee*, Chanyoung Kim*, Wonmin Byeon, Sang Ho Yoon, Jinkyu Kim, Sangpil Kim

    arXiv 2022

    [ arXiv ]

  • Sound-Guided Semantic Video Generation

    Seung Hyun Lee, Gyeongrok Oh, Wonmin Byeon, Chanyoung Kim, Won Jeong Ryoo, Sang Ho Yoon, Jihyun Bae, Jinkyu Kim*, Sangpil Kim*.

    ECCV 2022

    [ paper / dataset ]

  • Sound-Guided Semantic Image Manipulation

    Seung Hyun Lee, Wonseok Roh, Wonmin Byeon, Sang Ho Yoon, Chanyoung Kim, Jinkyu Kim*, Sangpil Kim*

    CVPR 2022

    [ project / paper / code ]

  • Audio-Guided Image Manipulation for Artistic Paintings

    Seung Hyun Lee, Nahyuk Lee, Chanyoung Kim, Wonjeong Ryoo, Jinkyu Kim, Sang Ho Yoon*, Sangpil Kim*

    NeurIPS 2021 Workshop on Machine Learning for Creativity and Design

    [ project ]

    • Other Publications

  • ORA3D: Overlap Region Aware Multi-view 3D Object Detection

    Wonseok Roh, Gyusam Chang, Seokha Moon, Giljoo Nam, Chanyoung Kim, Younghyun Kim, Jinkyu Kim*, Sangpil Kim*

    BMVC 2022

    [ arXiv ]

Academic Activities

Organizing Committees

  • MICCAI Student Board - Local Student Liaison Officer
    • Organizing workshops, webinars, and conference events for MICCAI 2025

Reviewer

  • CVPR 2024, 2025
  • ICCV 2025
  • NeurIPS 2025
  • ECCV 2024
  • WACV 2023, 2025

Teaching Experience

  • TA: Yonsei University (Fall 2023 ~ Spring 2024)
  • Lecturer: Samsung Electronics (Aug. 2023)
  • TA: LOTTE Corporation (Apr. 2023)
  • TA: LG CNS (Jul. 2021 ~ Aug. 2022)

Awards & Honors

  • Best Academic Paper Award at Yonsei University Fall 2024
  • LAB Start-up 2022
  • Korea University π-ville Demo Day 2021
  • Sejong Scholarship for Outstanding GPA
  • 2020 International Robot Contest
  • Seoul PM Hackathon
  • Medal of Contribution for XXIII Pyeongchang Olympic Winter Games