Hello! I am a Ph.D. student at KAIST AI, co-advised by Hyunwoo Kim and Minjoon Seo. I am interested in developing models that can continually improve and reason, drawing inspiration from human cognition. My research investigates the knowledge acquisition dynamics of language models and explores architectural mechanisms for lifelong learning and hierarchical planning. Current research topics include neural memory, test-time adaptation, and diffusion language model. I hold a Master of Science in Artificial Intelligence from KAIST Graduate School of AI and a Bachelor’s degree in Business Administration and Economics from Korea University. I previously worked as an economist at Bank of Korea.
Publications
Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition
Jiyeon Kim*,
Hyunji Lee*,
Hyowon Cho,
Joel Jang,
Hyeonbin Hwang,
Seungpil Won,
Youbin Ahn,
Dohaeng Lee,
Minjoon Seo
International Conference on Learning Representations (ICLR) 2025
Oral
Workshop Best Paper Award
paper
code
workshop
How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
{Seongyun Lee*,
Geewook Kim*,
Jiyeon Kim*},
Hyunji Lee,
Hoyeon Chang,
Sue Hyun Park,
Minjoon Seo
International Conference on Learning Representations (ICLR) 2025
paper
ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval
Soyoung Yoon,
Eunbi Choi,
Jiyeon Kim,
Hyeongu Yun,
Yireun Kim,
Seung-won Hwang
Annual Meeting of the Association for Computational Linguistics (ACL) 2024
Oral
paper
code
Education
- KAIST - M.S. Artificial Intelligence
- Korea University - B.A. Business Administration & Economics
COCO Lab
Visit Us
Building 9, Kim Jaechul Graduate School of Artificial Intelligence, KAIST85 Hoegi-ro, Dongdaemun-gu, Seoul 02455
Republic of Korea