Embedded Files
Hi! I'm a Ph.D. student at KAIST AI under the supervision of Prof. Seong Joon Oh.
My research lies in the field of AI Safety, with a particular interest in building models that are fair, responsible, and transparent. Specifically, I work on machine unlearning, which seeks to selectively remove the influence of specific data in order to protect user privacy, copyright, and data ownership. Recently, I have been exploring unlearning techniques in both large language models (LLMs) and large vision-language models (LVLMs). More recently, I have developed a growing interest in designing pre-training pipelines better suited to post-training. Post-training tasks such as continual learning, knowledge editing, and machine unlearning have remained difficult to solve for a long time and I believe this may be because post-training is rarely taken into account at the pre-training stage. I am currently pursuing this direction as well.
Ongoing Research Topics: Unlearning, Red Teaming
Openings for Interns: One opening in Unlearning & One opening in Red Teaming
News
09/2026: Served as a program committee member for two NeurIPS 2026 workshops: PALM and ATTRIB.
09/2026: Started my PhD journey in STAI group at KAIST AI.
05/2026: 2 papers accepted @ ICML 2026 Workshop on the Impact of Memorization on Trustworthy Foundation Models.
01/2026: 1 paper accepted @ ICLR 2026.
11/2025: 🏆 Granted AI SeoulTech Graduate Scholarship by Seoul Scholarship Foundation ($3.5K).
09/2025: 1 paper accepted @ NeurIPS 2025.
07/2025: 1 paper accepted @ COLM 2025.
01/2025: Served as a visiting scholar at the Tübingen AI Center (Host: Prof. Dr. Seong Joon Oh).
03/2024: 🏆 Granted Digital Human & Entertainment Scholarship by Smilegate ($27K).
03/2024: 🏆 Granted Albatross Fellowship by Sogang University ($21K, top 10% rank honor).
Selected Publications
*Co-first Authors, ^Co-corresponding Authors, ᐩMentored Interns
[7] TULIP: Targeted LLM Unlearning at Layers Identified Per-Input
Yejin Kim, William F. Shen, Seokwon Jung, Daeun Parkᐩ, Seong Joon Oh.
Preprint.
[6] Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models [pdf]
Yejin Kim, Dongjun Hwang, Sungmin Cha^, Junsuk Choe^.
Preprint.
[5] Break the Output Geometry for Large Language Model Unlearning [pdf]
Yejin Kim, William F. Shen, Seokwon Jung, Seong Joon Oh.
ICML 2026 Workshop on the Impact of Memorization on Trustworthy Foundation Models.
[4] Alignment-aware Data Selection for Unlearning in Contrastive Vision-Language Models [pdf]
Dongjun Hwang, Yejin Kim, Beomyun Kwon, Junsuk Choe.
ICML 2026 Workshop on the Impact of Memorization on Trustworthy Foundation Models.
[3] Enhancing Multi-Image Understanding through Delimiter Token Scaling [pdf] [code]
Minyoung Lee, Yeji Park, Dongjun Hwang, Yejin Kim, Seong Joon Oh, Junsuk Choe.
ICLR 2026.
[2] OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation [pdf] [code]
Dongjun Hwang, Yejin Kim, Minyoung Lee, Seong Joon Oh, Junsuk Choe.
NeurIPS 2025.
[1] Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning [pdf] [code]
Yejin Kim*, Eunwon Kim*, Buru Chang^, Junsuk Choe^.
COLM 2025.
Page updated
Google Sites
Report abuse