Yongwoo Kim

Ph.D. Student in Artificial Intelligence · Korea University

I am a Ph.D. student at Korea University, advised by Prof. Donghyun Kim. My research focuses on AI Safety and Machine Unlearning.

Yongwoo Kim

Publications

NeurIPS 2026
Consistency-Preserving Concept Erasure via Unsafe–Safe Pairing and Directional Fisher-weighted Adaptation
Yongwoo Kim*, Sungmin Cha*, Hyunsoo Kim, Jaewon Lee, Donghyun Kim
arXiv
Findings of EMNLP 2026
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
Yongwoo Kim*, Sojung An*, Yunjin Park, Jungwon Yoon, Dujin Lee, HyunBeom Cho, Jaewon Lee, Wonhyuk Lee, Youngchol Kim, JeongYeop Kim, Donghyun Kim
arXiv
Preprint
Erase at the Core: Representation Unlearning for Machine Unlearning
Jaewon Lee, Yongwoo Kim, Donghyun Kim
arXiv
EAAI
Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
Yongwoo Kim*, Sungmin Cha*, Donghyun Kim
PaperarXiv

* Equal contribution

Education

2024.09 – Present
Korea University
Ph.D. in Artificial Intelligence
2018.03 – 2024.08
Sejong University
B.S.

Honors & Awards

2026
AI Seoul Tech Scholarship