About me

Hi! I’m a first-year Ph.D. student in Machine Learning at Georgia Tech, where I’m advised by Prof. Zsolt Kira. Previously, I was an undergraduate researcher at Seoul National University, where I worked with Prof. Gunhee Kim.

My research focuses on developing embodied AI agents that learn through trial and error. I’m particularly interested in:

• Vision-Language-Action Models
• LLM/VLM Agents
• Reinforcement Learning

Publications

• FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games
  Jaewoo Ahn*, Junseo Kim*, Heeseung Yun, Jaehyeon Son, Dongmin Park, Jaewoong Cho, Gunhee Kim
  EMNLP 2025
  [project] [paper] [code]

• Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning
  Jaehyeon Son, Soochan Lee, Gunhee Kim
  ICLR 2025
  [paper] [code]

• When Meta-Learning Meets Online and Continual Learning: A Survey
  Jaehyeon Son*, Soochan Lee*, Gunhee Kim
  IEEE TPAMI 2024
  [paper]

• Learning to Continually Learn with the Bayesian Principle
  Soochan Lee, Hyeonseong Jeon, Jaehyeon Son, Gunhee Kim
  ICML 2024
  [paper] [code]

• Recasting Continual Learning as Sequence Modeling
  Soochan Lee, Jaehyeon Son, Gunhee Kim
  NeurIPS 2023
  [paper] [code]

Education

• Ph.D. in Machine Learning, Georgia Institute of Technology
  Aug. 2025 - Present

• B.S. in Statistics and Artificial Intelligence, Seoul National University
  Summa Cum Laude
  Mar. 2017 - Aug. 2023

Experience

• Krafton
  Mar. 2025 - Aug. 2025
  AI Fellowship Intern

• Vision & Learning Lab, Seoul National University
  Jul. 2022 - Mar. 2025
  Undergraduate Researcher

• NCSOFT
  Jul. 2021 - Aug. 2021
  Research Intern

Honors & Awards

• Krafton AI Fellowship
  Feb. 2025

• Songam Scholarship
  Mar. 2017 - Feb. 2023