I am a second-year Ph.D. candidate in Electrical and Computer Engineering at Seoul National University, advised by Prof. Kyomin Jung. My current research focuses on how to make LLMs self-improve by consolidating environmental feedback. More broadly, my interests include reinforcement learning and efficient inference for LLMs.

News

Nov. 2025 One paper has been accepted to AAAI 2026!
Aug. 2025 Two papers have been accepted to EMNLP 2025!
Sep. 2024 One paper has been accepted to Findings of EMNLP 2024!

Publications

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dohyung Kim, Jiwon Jeon, Dongsheng Li, Yuqing Yang
Preprint [Code]
Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR
Dohyung Kim, Minbeom Kim, Jeonghye Kim, Sangmook Lee, Sojeong Rhee, Kyomin Jung
Preprint [Code]
Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
Sangmook Lee*, Dohyung Kim*, Hyukhun Koh, Nakyeong Yang, Kyomin Jung
AAAI 2026 [Code]
ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
Jeonghye Kim, Sojeong Rhee, Minbeom Kim, Dohyung Kim, Sangmook Lee, Youngchul Sung, Kyomin Jung
EMNLP 2025 [Code]
Conditional [MASK] Discrete Diffusion Language Model
Hyukhun Koh, Minha Jhang, Dohyung Kim, Sangmook Lee, Kyomin Jung
EMNLP 2025 [Code]
Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
Hyukhun Koh, Dohyung Kim, Minwoo Lee, Kyomin Jung
Findings of EMNLP 2024 [Code]

Education

Ph.D. Candidate in Electrical and Computer Engineering
Seoul National University
2025.03 — Present
B.S. in Electrical and Computer Engineering
Seoul National University, Cum Laude
2019.03 — 2025.02