Jaechang Kim

Hello, I’m jaechang Kim. I’m a graduate student in POSTECH Machine Learning Lab since 2021, under supervision of Prof. Jungseul Ok.

My current research focuses primarily on leveraging Large Language Models (LLMs) to enhance explainable AI. I explore how the reasoning and linguistic capabilities of LLMs can help interpret complex models and facilitate knowledge extraction. Besides this core direction, my broader research interests include:

  • Trustworthy Machine Learning: Developing methods to explain the rationale behind machine learning model decisions and effectively transfer this knowledge to humans.

  • Diverse ML Applications: Investigating a variety of applications, such as automated theorem proving and sound source separation.

Publication (you may check here)

pre-print

  • Hoyoung Kim, Seokhee Jin, Changhwan Sung, Jaechang Kim, and Jungseul Ok, “Active Prompt Learning with Vision-Language Model Priors,” 2024
  • Jaechang Kim, Jeongyeon Hwang, Soheun Yi, Jaewoong Cho, and Jungseul Ok, “Addressing Feature Imbalance in Sound Source Separation,” 2023

major conferences

  • Jaechang Kim, Jinmin Goh, Inseok Hwang, Jaewoong Cho, and Jungseul Ok, “Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation,” in NAACL (oral presentation), 2025
  • Sungjae Lee*, Hyejin Park*, Jaechang Kim, and Jungseul Ok, “Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models,” in ACL (oral presentation), 2025
  • Jaechang Kim*, Yunjoo Lee*, Hyun Mi Cho, Dong Woo Kim, Chi Hoon Song, and Jungseul Ok, “Activity-informed Industrial Audio Anomaly Detection via Source Separation,” in ICASSP, 2023
  • Jaechang Kim*, Yunjoo Lee*, Seunghoon Hong, and Jungseul Ok, “Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution,” in ICASSP (oral presentation), 2022
  • Jinwoo Jeon*, Jaechang Kim*, Kangwook Lee, Sewoong Oh, and Jungseul Ok, “Gradient Inversion with Generative Image Prior,” in NeurIPS 2021 (and FL-ICML’21), 2021

domestic conferences

  • Hyejin Park*, Byungchan Ko*, Jaechang Kim*, Hoyoung Kim, Jinwoo Jeon, and Jungseul Ok, “Effect of Privacy Preserving in Personalized Federated Learning with Heterogeneous Data from Wearable Devices,” KSC2021, 2021

Education

  • Ph.D. in POSTECH Graduate School of Artificial Intelligence (2021 ~ )
  • B.S. in POSTECH Department of Computer Science & Engineering (2016 ~ 2021)

Work Experience

  • Internship in Naver (2020.07 ~ 2020.08)

  • Internship with Prof. Sungwoo Park (2019.05 ~ 2019.10) https://www.datamonad.com/

  • Internship in Netmarble AI Revolution Center (2018.06 ~ 2018.08)