avatar

Sanghyun Jo

AI Researcher
OGQ · SNU AIBL Lab
shjo.april@gmail.com


About Me

I lead AI research and development at OGQ, where I have been building practical and interpretable machine learning systems since 2017. My work focuses on designing models that go beyond academic benchmarks—aiming instead for tangible, real-world impact through robustness, transparency, and usability.

Since 2021, I have been fortunate to be advised by Prof. Kyungsu Kim. As an external researcher in the SNU AIBL Lab, I’ve had the opportunity to collaborate closely and receive continued mentorship. His guidance has deeply shaped my thinking around explainable AI, data-efficient learning, and research integrity. Under his supervision, I’ve pursued AI that is not only powerful but also understandable and responsible.

News

Publications

  1. Under Review
    ISAC: Training-Free Instance-to-Semantic Attention Control for Improving Multi-Instance Generation
    Sanghyun Jo*, Wooyeol Lee*, Ziseok Lee*, Kyungsu Kim†
    arXiv:2505.20935
    PDF

  2. Under Review
    DiffEGG: Diffusion-Driven Edge Generation as a Pixel-Annotation-Free Alternative for Instance Annotation
    Sanghyun Jo*, Ziseok Lee*, Wooyeol Lee, Kyungsu Kim†
    arXiv:2503.07982
    PDF Code

  3. ICCV'25
    COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
    Sanghyun Jo*, Seo Jin Lee*, Seungwoo Lee, Seohyung Hong, Hyungseok Seo†, Kyungsu Kim†
    IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
    PDF Code Project Page

  4. ICCV'25
    Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
    Joowon Kim*, Ziseok Lee*, Donghyeon Cho, Sanghyun Jo, Yeonsung Jung, Kyungsu Kim†, Eunho Yang†
    IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
    PDF

  5. ECCV'24
    DHR: Dual Features-Driven Hierarchical Rebalancing in Inter-and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
    Sanghyun Jo, Fei Pan, In-Jae Yu, Kyungsu Kim†
    European Conference on Computer Vision (ECCV), 2024.
    PDF Code

  6. ECCV'24
    TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
    Sanghyun Jo*, Soohyun Ryu*, Sungyub Kim, Eunho Yang, Kyungsu Kim†
    European Conference on Computer Vision (ECCV), 2024.
    PDF Code

  7. ICCV'23
    MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
    Sanghyun Jo, In-Jae Yu, Kyungsu Kim†
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    PDF Code

  8. Under Review
    RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks
    Sanghyun Jo, In-Jae Yu, Kyungsu Kim†
    arXiv:2204.06754
    PDF Code

  9. ICIP'21
    Puzzle-CAM: Improved localization via matching partial and full features
    Sanghyun Jo, In-Jae Yu†
    IEEE International Conference on Image Processing (ICIP), 2021.
    PDF Code

Services

Conference Reviewers

Journal Reviewers

Awards

Talks


Powered by Jekyll and Minimal Light theme.