Conference Papers: TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students (CHI'25); When to Give Feedback: Exploring Tradeoffs in the Timing of Design Feedback (C&C'24); Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education (CHI'24, Honorable Mention), and multiple other conference papers, posters, and workshop papers.
Research Experience
Research at UMich Lifelong Learning Lab; involved in projects such as helping teachers plan, develop, and monitor chatbot-integrated classes, and investigating large language models in diagnosing students' cognitive skills in math problem-solving.
Education
PhD: University of Michigan, Computer Science and Engineering (Advisor: Xu Wang); Master's and Bachelor's: KAIST (Advisor: Juho Kim).
Background
Research Interests: Human-AI interaction, computer-supported cooperative work, and learning at scale. Vision: End-learner Programming, where learners and instructors can customize existing or create new learning content, paths, and tools for their personal needs.
Miscellany
Personal Achievements: Successfully defended master's thesis; citation reached 100; solved 1500 LeetCode problems; will visit Yokohama to present TeachTune at CHI.