Jaechang Kim

POSTECH Machine Learning Lab

251100.jpg

Hi, I’m Jaechang Kim. I’m a graduate student in POSTECH Machine Learning Lab since 2021, under supervision of Prof. Jungseul Ok. I was a research intern at Sony.

I am interested in building AI systems that can work with researchers as collaborators: helping them reason through problems, organize knowledge, and make complex model behavior easier to understand. My current research interests include:

Human-AI Collaboration for Research
Leveraging AI to support research productivity, reasoning, and discovery.
Trustworthy Machine Learning
Developing methods that explain the rationale behind machine learning model decisions and transfer this knowledge to humans.

Education & Experience

Ph.D. in POSTECH (2021.03 - 2026.08 (tentative))
Graduate School of Artificial Intelligence
Research Internship in Sony Global Corporation (2025.10 - 2026.02)
Automatic Discovery of Visual Prompts for Large Vision Language Models by Agentic Exploration
B.S. in POSTECH (2016.03 - 2021.02)
Department of Computer Science & Engineering
Software Internship in Naver (2020.07 - 2020.08)
Internal Tool Development
Research Internship in Netmarble AI Revolution Center (2018.06 - 2018.08)
Game-playing AI with Reinforcement Learning

Selected Publications

2026

  1. Agentic Model Predictive Questioning Control in Visual Design
    Kuang-Da Wang, Zhao Wang, Wei-Yao Wang, Yotaro Shimose, Jaechang Kim, and Shingo Takamatsu
    In ICML, 2026
  2. Visual Prompt Discovery via Semantic Exploration
    Jaechang Kim, Yotaro Shimose, Zhao Wang, Kuang-Da Wang, Jungseul Ok, and Shingo Takamatsu
    2026 Link
  3. Towards Faithful Agentic XAI: A Verification-centric Workflow and an Open-world Benchmark
    Jaechang Kim, Sunung Mun, Seungjoon Lee, Jaewoong Cho, and Jungseul Ok
    2026
  4. MMTB: Evaluating Terminal Agents on Multimedia-File Tasks
    Chiyeong Heo, Jaechang Kim, Junhyuk Kwon, Hoyoung Kim, Dongmin Park, Jonghyun Lee, and Jungseul Ok
    2026 Link

2025

  1. Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation
    Jaechang Kim, Jinmin Goh, Inseok Hwang, Jaewoong Cho, and Jungseul Ok
    In NAACL (oral presentation), 2025 Link
  2. Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models
    Sungjae Lee*, Hyejin Park*, Jaechang Kim, and Jungseul Ok
    In ACL (oral presentation), 2025 Link
  3. Active Prompt Learning with Vision-Language Model Priors
    Hoyoung Kim, Seokhee Jin, Changhwan Sung, Jaechang Kim, and Jungseul Ok
    In TMLR, 2025 Link

2023

  1. Activity-informed Industrial Audio Anomaly Detection via Source Separation
    Jaechang Kim*, Yunjoo Lee*, Hyun Mi Cho, Dong Woo Kim, Chi Hoon Song, and Jungseul Ok
    In ICASSP, 2023 Link

2022

  1. Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
    Jaechang Kim*, Yunjoo Lee*, Seunghoon Hong, and Jungseul Ok
    In ICASSP (oral presentation), 2022 Link

2021

  1. Gradient Inversion with Generative Image Prior
    Jinwoo Jeon*, Jaechang Kim*, Kangwook Lee, Sewoong Oh, and Jungseul Ok
    In NeurIPS, 2021 Link