- ReSPack: A Large-Scale Rectilinear Steiner Tree Packing Data Generator and Benchmark (NeurIPS 2022 Workshop)
- Awards:
- ICORES 2025 Best Student Paper Award
- NeurIPS 2021 Competition - Machine Learning for Combinatorial Optimization: Overall 4th place (dual task), 2nd in student leaderboard (dual task)
- Talent Award of Korea 2016
- Zayed Future Energy Prize 2016 Global High School Winner ($100,000 USD)
Research Experience
- Research Intern at Fundamental Research Lab, LG AI Research (2022.03 - 2022.08)
Education
- Bachelor of Science: 2018.03 - 2023.02, Korea Advanced Institute of Science and Technology (KAIST), Dept. of Mathematical Sciences
- MS/Ph.D Integrated: 2023.03 - Present, Korea Advanced Institute of Science and Technology (KAIST), Kim Jaechul Graduate School of AI
Background
- Research Interests: Controllability and interpretability of LLM agents
- Professional Field: Theoretical foundations, reinforcement learning, preference alignment, and personalization
- Brief Introduction: As a theory-based practitioner, approaches controllability and interpretability as fundamentally mathematical concepts, aiming to formalize and guarantee these properties in reinforcement learning settings.