Resume
Academic Achievements
- - Publications:
- * Learning to Generate Unit Test via Adversarial Reinforcement Learning (Arxiv Preprint)
- * Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback (Arxiv Preprint)
- * Adversarial Iterative Unit Test Generation with Large Language Models (Under Review)
- * Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents (ICLR 2025)
- * Read-only prompt optimization for Vision-Language Few-shot Learning (ICCV 2023)
- - Academic Services:
- * Conference Reviewer, ICLR 2025
- * Journal Reviewer, Pattern Recognition
- - Honors & Awards:
- * Donggyo Talent Award, Surim Foundation, Dec. 2023
- * Ilju Academy and Culture Foundation Scholarship, Ilju Foundation, Dec. 2018 ~ Feb. 2024
- * Semester high honor, Korea University, 2018S, 2018F, 2019S, 2019F, 2022S, 2022F, 2023S
Research Experience
- - Microsoft Research, Research Intern, Mar. 2025 - Jun. 2025, Vancouver, Canada
- - Microsoft Research, Research Intern, Sep. 2024 - Feb. 2025, Beijing, China
- - NAVER Corp, Research Intern, Jun. 2023 - Aug. 2023, Jeongja, Korea
Education
- - Korea Advanced Institute of Science and Technology (KAIST), Ph.D. Student in Artificial Intelligence, Mar. 2024 - Present
- - Korea University, B.S. in Statistics, Mar. 2018 - Feb. 2024
Background
- - Research Interests: decision-making agents in physical environment (embodied agent) and digital environment (e.g., computer use agent, coding agent)
- - Current Focus: robotic foundation models
- - Advisors: Kimin Lee, Jinwoo Shin