publications

2026

1. ICML

   What Linear Probes Miss: Multi-View Probing for Weight-Space Learning

   Eunwoo Heo, KyeongKook Seo, and Jaejun Yoo

   In International Conference on Machine Learning (ICML), Jul 2026

   Poster

   arXiv OpenReview Bib Code Website

   @inproceedings{heo2026probes,
     title = {What Linear Probes Miss: Multi-View Probing for Weight-Space Learning},
     author = {Heo, Eunwoo and Seo, KyeongKook and Yoo, Jaejun},
     booktitle = {International Conference on Machine Learning (ICML)},
     year = {2026},
     month = jul,
     address = {Vancouver, Canada},
     note = {Poster},
     openreview = {vfqrmuVULL},
   }

2025

1. ICCV

   Understanding Flatness in Generative Models: Its Role and Benefits

   Taehwan Lee, KyeongKook Seo, Jaejun Yoo, and 1 more author

   In International Conference on Computer Vision (ICCV), Oct 2025

   arXiv Bib Website

   @inproceedings{lee2025flatness,
     title = {Understanding Flatness in Generative Models: Its Role and Benefits},
     author = {Lee, Taehwan and Seo, KyeongKook and Yoo, Jaejun and Yoon, Sung Whan},
     booktitle = {International Conference on Computer Vision (ICCV)},
     year = {2025},
     month = oct,
   }

2. ICLR

   PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models

   KyeongKook Seo, Dong-Jun Han, and Jaejun Yoo

   In International Conference on Learning Representations (ICLR), Apr 2025

   arXiv Bib Website

   @inproceedings{seo2025prism,
     title = {PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models},
     author = {Seo, KyeongKook and Han, Dong-Jun and Yoo, Jaejun},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2025},
     month = apr,
     address = {Singapore},
   }

2026

1. IPIU

   가중치 공간에서의 위상-기반 모델 분류

   Eunwoo Heo, KyeongKook Seo, and Jaejun Yoo

   In Workshop on Image Processing and Image Understanding (IPIU), Feb 2026

   우수포스터발표상 Bib

   true

   @inproceedings{seo2026topology_ipiu,
     title = {가중치 공간에서의 위상-기반 모델 분류},
     author = {Heo, Eunwoo and Seo, KyeongKook and Yoo, Jaejun},
     booktitle = {Workshop on Image Processing and Image Understanding (IPIU)},
     year = {2026},
     month = feb,
     address = {Korea},
   }

2025

1. IPIU

   원격 광혈류측정 기반 딥페이크 탐지 방법론들의 재현가능성 분석

   Kanghyun Kim, Chaerin Hwang, KyeongKook Seo, and 1 more author

   In Workshop on Image Processing and Image Understanding (IPIU), Feb 2025

   Bib

   @inproceedings{seo2025rppg_ipiu,
     title = {원격 광혈류측정 기반 딥페이크 탐지 방법론들의 재현가능성 분석},
     author = {Kim, Kanghyun and Hwang, Chaerin and Seo, KyeongKook and Yoo, Jaejun},
     booktitle = {Workshop on Image Processing and Image Understanding (IPIU)},
     year = {2025},
     month = feb,
     address = {Korea}
   }

2024

1. IPIU

   확률적 이진마스크를 통한 강력하고 효율적인 생성모델 연합학습

   KyeongKook Seo and Jaejun Yoo

   In Workshop on Image Processing and Image Understanding (IPIU), Feb 2024

   Bib

   @inproceedings{seo2024prism_ipiu,
     title = {확률적 이진마스크를 통한 강력하고 효율적인 생성모델 연합학습},
     author = {Seo, KyeongKook and Yoo, Jaejun},
     booktitle = {Workshop on Image Processing and Image Understanding (IPIU)},
     year = {2024},
     month = feb,
     address = {Korea}
   }

2026

1. Award

   IPIU 2026 우수포스터발표상 (Best Poster Presentation Award)

   KyeongKook Seo

   — for “가중치 공간에서의 위상-기반 모델 분류” (Heo, Seo, Yoo) , Feb 2026

2025

1. Award

   우수 포스터 대상 (Best Poster Grand Award)

   KyeongKook Seo

   — 2025 UNIST AI Technology Open Workshop, for PRISM (ICLR 2025); advisor: Jaejun Yoo , Oct 2025

2024

1. Patent

   MMD 손실함수를 이용한 이진 마스크 기반 생성 모델 연합 학습 시스템 및 이를 이용한 생성 모델 연합 학습 방법

   Jaejun Yoo, KyeongKook Seo, and Dongjun Han

   (Korea Patent Application No. 10-2024-0173205) , Nov 2024

   Bib

   @misc{seo2024patent_mmd,
     title = {MMD 손실함수를 이용한 이진 마스크 기반 생성 모델 연합 학습 시스템 및 이를 이용한 생성 모델 연합 학습 방법},
     author = {Yoo, Jaejun and Seo, KyeongKook and Han, Dongjun},
     year = {2024},
     month = nov,
   }