avatar

Sanghyun Jo

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


Biography

I lead AI research and development at OGQ, where I have been building practical and interpretable machine learning systems since 2017. My primary focus is on designing models that prioritize tangible real-world impact through robustness, transparency, and usability rather than chasing purely academic benchmarks.

Since 2021, I have been conducting research under the supervision of Prof. Kyungsu Kim at the SNU AIBL Lab. This collaboration has deeply influenced my approach to explainable AI and data-efficient learning. Integrating these insights, I strive to develop AI systems that are not only powerful but also understandable and responsible.

News

Publications

  1. Under Review
    EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
    Sanghyun Jo* †, Donghwan Lee*, Eunji Jung*, Seong Je Oh, Kyungsu Kim†
    arXiv:2512.21545
    PDF First & Co-corresponding author

  2. Under Review
    On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering
    Ziseok Lee*, Minyeong Hwang*, Sanghyun Jo, Wooyeol Lee, Jihyung Ko, Young Bin Park, Jae-Mun Choi, Eunho Yang†, Kyungsu Kim†
    arXiv:2512.10339
    PDF Co-author

  3. 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 First Author

  4. ICLR'26
    TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
    Sanghyun Jo*, Ziseok Lee*, Wooyeol Lee, Jonghyun Choi, Jaesik Park†, Kyungsu Kim†
    International Conference on Learning Representations (ICLR), 2026.
    PDF First Author

  5. 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 First Author

  6. 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 Code Project Page Co-author

  7. 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 First Author

  8. 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 First Author

  9. 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 First Author

  10. Preprint
    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 First Author

  11. 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 First Author; 140+ Citations

Services

Conference Reviewers

Journal Reviewers

Awards

Talks


Powered by Jekyll and Minimal Light theme.