1. Two papers will be presented in Neurips workshop: BenchHub: A Unified Benchmark Suite for Holistic and Customizable LLM Evaluation (Efficient Reasoning Workshop) and ML-IAM: Emulating Integrated Assessment Models With Machine Learning (Tackling Climate Change with Machine Learning Workshop), Date: Dec 2025
2. Two papers accepted to EMNLP 2025 Findings: Uncovering Factor Level Preferences to Improve Human-Model Alignment and MUG-Eval, Date: Aug 2025
3. Three papers accepted to ACL 2025 — two in Findings and one as Main (Oral): LLM-as-an-Interviewer, Spotting Out-of-Character Behavior, and Diffusion Models Through a Global Lens, Date: May 2025
4. 'When Tom Eats Kimchi' paper got outstanding paper awards in NAACL C3NLP! Congrats to my interns, Date: Mar 2025
Research Experience
1. Carnegie Mellon University (CMU) - Visiting Scholar in HCII Computer Science, Host professor: Sherry Tongshuang Wu, Time: 2025.09-present
2. Korea Advanced Institute of Science and Technology (KAIST) - Master's student, Advisor: Alice Oh, Time: 2023.09-present
Education
1. Carnegie Mellon University (CMU) - Visiting Scholar in HCII Computer Science, Host professor: Sherry Tongshuang Wu, Time: 2025.09-present
2. Korea Advanced Institute of Science and Technology (KAIST) - M.S. in Computer Science, Advisor: Alice Oh, Time: 2023.09-present
3. Korea Advanced Institute of Science and Technology (KAIST) - B.S. in Electrical Engineering, GPA: 4.02/4.3, Major GPA: 4.15/4.3 (Summa Cum Laude), Time: 2019.03–2023.08
Background
Research interests: Developing AI systems and agents that serve as meaningful bridges, connecting individuals, societies, and humans with intelligent agents. Current focus: 1. How effectively can large language models (LLMs) assist humans in real-world contexts? 2. How well do they understand and represent diverse multicultural and multilingual societies?