About

I’m a Ph.D. candidate at Seoul National University (MILAB). My major is Natural Language Processing (NLP), and I’m interested in the Explainability and AI Safety for Language models. My current research topics are related to Knowledge localization, Fairness and Ethics, and AI Privacy.

Education

Seoul National University 2021.03 ~ 2025.08 (expected)
- Ph.D. Candidate in Artificial Intelligence
- Advisor: Prof. Kyomin Jung

Ajou University 2015.03 ~ 2019.02
- B.S. in Electronic Business, Software and B.A. in Business Administration (Triple Degrees)
- Ajou-people Award (College Representative)

Professional Experiences

Adobe Research 2023.02 ~ Present
- Collaborative Researcher (Research Scholarship)
- Remote working with Dr. David Seunghyun Yoon
- Previous Theme: Video Moment Retrieval, Trustworthy AI (CIKM 2024 accepted)
- Current Theme: Knowledge Unlearning (ICLR 2025 submitted)

LG AI Research 2023.09 ~ 2024.02
- Full-time Internship
- Working with Prof. Honglak Lee
- Theme: AI Safety, Fairness, Explainability (ACL 2024 accepted) 2023.09 ~ 2023.12
- Project: LLM Application (EXAONE) 2023.12 ~ 2024.02

Mentoring Experiences

- Hyukhun Koh (Ph.D. Student at Seoul National University)
- Haesung Pyun (Ph.D. Student at Seoul National University)
- Jahyun Koo (Ph.D. Student at Seoul National University)
- Minsung Kim (Ph.D. Student at Seoul National University)
- Kyeongman Park (M.S. Student at Seoul National University)
- Jiwon Moon (M.S. Student at Seoul National University)
- Junseok Kim (B.S. Student at Pohang University of Science and Technology)