KyeongKook Seo

UNIST AIGS

50 UNIST-gil, Ulju-gun

Ulsan 44919, Korea

I am a Ph.D. student in Artificial Intelligence at UNIST, advised by Prof. Jaejun Yoo at the Lab of Advanced Imaging Technology (LAIT).

My research interests lie at the intersection of generative models, federated learning, safety AI, loss landscape geometry, and weight-space learning.

Previously, I received my M.S. in Artificial Intelligence from UNIST (2025) and my B.S. in Computer Science Engineering from Inha University (2022).

See my CV or publications for more details.

selected publications

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},
}

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,
}

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},
}