Dongjun Lee

Ph.D student

KAIST AI

dgjun32 [AT] kaist.ac.kr / mando0302 [AT] gmail.com

About

I am a first year Ph.D. student at KAIST, advised by Prof. Kimin Lee and Jinwoo Shin, and I worked as research intern at Microsoft Research. I am interested in decision-making agents in physical environment (embodied agent) and digital environment (e.g., computer use agent, coding agent). I am currently focusing on robotic foundation models.

Publications

[P3] Learning to Generate Unit Test via Adversarial Reinforcement Learning

Dongjun Lee, Changho Hwang, Kimin Lee

Arxiv Preprint

[P2] Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback

Yongjin Yang, Sinjae Kang, Juyong Lee, Dongjun Lee, Seyoung Yun, Kimin Lee

Arxiv Preprint

[P1] Adversarial Iterative Unit Test Generation with Large Language Models

Dongjun Lee, Juyong Lee, Changho Hwang, Kimin Lee

Under Review

[C2] Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

Dongjun Lee*, Juyong Lee*, Kyuyoung Kim, Jihoon Tack, Jinwoo Shin, Yee Whye Teh, Kimin Lee

International Conference on Learning Representations (ICLR), 2025

[C1] Read-only prompt optimization for Vision-Language Few-shot Learning

Dongjun Lee*, Seokwon Song*, Jihee Suh, Junmyeong Choi, Sanghyeok Lee, Hyunwoo J.Kim

International Conference on Computer Vision (ICCV), 2023

[P3] Learning to Generate Unit Test via Adversarial Reinforcement Learning

Dongjun Lee, Changho Hwang, Kimin Lee

Arxiv Preprint

[P2] Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback

Yongjin Yang, Sinjae Kang, Juyong Lee, Dongjun Lee, Seyoung Yun, Kimin Lee

Arxiv Preprint

[P1] Adversarial Iterative Unit Test Generation with Large Language Models

Dongjun Lee, Juyong Lee, Changho Hwang, Kimin Lee

Under Review

[C2] Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

Dongjun Lee*, Juyong Lee*, Kyuyoung Kim, Jihoon Tack, Jinwoo Shin, Yee Whye Teh, Kimin Lee

International Conference on Learning Representations (ICLR), 2025

[C1] Read-only prompt optimization for Vision-Language Few-shot Learning

Dongjun Lee*, Seokwon Song*, Jihee Suh, Junmyeong Choi, Sanghyeok Lee, Hyunwoo J.Kim

International Conference on Computer Vision (ICCV), 2023

Education

Korea Advanced Institute of Science and Technology (KAIST)Mar. 2024 - Present

Ph.D. Student in Artificial Intelligence

Korea UniversityMar. 2018 - Feb. 2024

B.S. in Statistics

Experience

Microsoft ResearchMar. 2025 - Jun. 2025
Vancouver, Canada

Research intern

Microsoft ResearchSep. 2024 - Feb. 2025
Beijing, China

Research intern

NAVER CorpJun. 2023 - Aug. 2023
Jeongja, Korea

Research intern

Academic Services

Conference Reviewer, ICLR 2025

Journal Reviewer, Pattern Recognition

Honors & Awards

Donggyo Talent Award, Surim FoundationDec. 2023

Ilju Academy and Culture Foundation Scholarship, Ilju FoundationDec. 2018 ~ Feb. 2024

Semester high honor, Korea University2018S, 2018F, 2019S, 2019F, 2022S, 2022F, 2023S