Biography

Hello. I am a Ph.D. student in Electrical and Computer Engineering (ECE) at the University of Wisconsin-Madison, supervised by Prof. Kangwook Lee. 

Previously, I was a deep learning research engineer at Deep Learning Div. in KRAFTON. Also, I was an AI researcher at Applied AI Lab, NLP Center in NCSOFT Corp.
I received B.S. and M.S. degrees in Electrical Engineering (EE) from Korea Advanced Institute of Science and Technology (KAIST) in 2018 and 2020, respectively, supervised by Prof. Sae-Young Chung.

My research interests lie in Data-centric AI for practical and efficient Language Model Agents. Lately, I have been focusing on developing algorithms to refine data for various models, such as Small Language Models (sLMs), Graph Neural Networks (GNNs), Recommender Systems (RS), and so on.

Research Interest

• Data-centric AI, Language Model Agent.

• Other areas, such as Small Language Models (sLMs), Graph Neural Networks (GNNs), Recommender Systems (RS), and so on.

News

• (Aug. 2025) ✨ Excited to start my new academic journey at UW–Madison!

Publications

P: Preprint, C: Conference

• [P3] Distilling LLM Agent into Small Models with Retrieval and Code Tools
  Minki Kang, Jongwon Jeong, Seanie Lee, Jaewoong Cho, Sung Ju Hwang
  arXiv, 2025. (Preprint)

• [P2] T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models
  Minki Kang*, Jongwon Jeong*, Jaewoong Cho (*: Equally Contributed)
  arXiv, 2025. (Preprint)

• [C3] How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
  Wonkwang Lee, Jongwon Jeong*, Taehong Moon*, Hyeon-Jong Kim, Jaehyeon Kim, Gunhee Kim, Byeong-Uk Lee  (*: Equally Contributed)
  International Conference on Machine Learning (ICML) 2025. (Accepted)

• [C2] iGraphMix: Input Graph Mixup Method for Node Classification
  Jongwon Jeong, Hoyeop Lee, Hyui Geon Yoon, Beomyoung Lee, Junhee Heo, Geonsoo Kim, Kim Jin Seon
  International Conference on Learning Representations (ICLR) 2024.

• [P1] Human-like Evaluation Paradigms for Post-hoc Explanation Method Using Masked Language Model
  Vinnam Kim*, Jongwon Jeong*, Hyunsouk Cho, and Jeong Choi (*: Equally Contributed)
  Preprint, 2023.

• [C1] FPAdaMetric: False-Positive-Aware Adaptive Metric Learning for Session-Based Recommendation
  Jongwon Jeong, Jeong Choi, Hyunsouk Cho, and Sehee Chung
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2022, 36(4), 4039-4047.

Educations

• M.S. in Electrical Engineering, KAIST, Aug. 2018 - Aug. 2020.

• B.S. in Electrical Engineering (Cum Laude), KAIST, Mar. 2014 - Aug. 2018.

• Korea Science Academy of KAIST, Mar. 2011 - Feb. 2014.

Work Experience

• KRAFTON Inc., Oct.2023 – Aug. 2025.
  Deep Learning Research Engineer at Natural Language DL Team., Applied DL Dept., Deep Learning Div. (Full-time)

• NCSOFT Corp., Aug. 2020 – Oct. 2023.
  AI Researcher at Applied AI Lab., NLP Center. (Full-time)
  Fulfilled alternative mandatory military service for Sep. 2020 – Sep. 2023.

• Koh Young Technology, Mar. 2017 – Aug. 2017.
  Research Intern at Medical Vision Team. (Internship)
  KAIST EE Co-op Program

Honors

• Top Reviewer, Learning on Graphs (LoG), Nov. 2024.

• Graduation with Honors (Cum Laude), KAIST, Aug. 2018.

• National Science & Engineering Scholarship, Mar. 2016 - Mar. 2018.