Hello! I am a Senior Research Scientist at Microsoft ASG. I received my Ph.D. in the Graduate School of AI at KAIST under the supervision of Prof. Se-Young Yun, and my M.S. in Industrial and Systems Engineering at KAIST under the supervision of Prof. Heeyoung Kim. I also have gained diverse research and industry experiences at organizations including Amazon AGI and Microsoft. My research focuses on advancing small foundation models, particularly in (multi-modal) language models.
Contact me: (first-name)(last-name)96 [at] gmail [dot] com [CV / Scholar / Github / LinkedIn]
(*: Equal Contribution)
DistiLLM: Towards Streamlined Distillation for Large Language Models
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
FINE Samples for Learning with Noisy Labels
Senior Researcher @Microsoft
Redmond, Washington, United States
Sep. 2025 - Present
Research Intern @Microsoft
Redmond, Washington, United States
Aug. 2024 - Nov. 2024 (12 Weeks)
Applied Scientist Intern @Amazon AGI
Sunnyvale, California, United States
Apr. 2024 - Jun. 2024
Winner, Qualcomm Innovation Fellowship Korea (2024)
DistiLLM: Towards Streamlined Distillation for Large Language Models
Silver Prize, 30th Samsung Humantech Paper Awards (2023)
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
Winner, Qualcomm Innovation Fellowship Korea (2022)
FINE Samples for Learning with Noisy Labels
Editor's Choice for Featured Article, IISE Transactions (2022)
Deep Gaussian Process Models for Integrating Multifidelity Experiments with Non-stationary Relationships
Korea Advanced Institue of Science and Technology (KAIST), Seoul, Korea, Mar. 2020 - Aug. 2025
Ph.D in Kim Jaechul Graduate School of Artificial Intelligence (Advisor: Se-Young Yun)
Dissertation: Optimizing the Training Strategies of Small Language Models for On-Device Applications
Korea Advanced Institue of Science and Technology (KAIST), Daejeon, Korea, Mar. 2018 - Feb. 2020
M.S. in Department of Industrial and Systems Engineering (Advisor: Heeyoung Kim)
Thesis: Deep Gaussian Process Models for Integrating Multifidelity Experiments with Non-stationary Relationships
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, Mar. 2014 - Feb. 2018
B.S. in Department of Industrial and Systems Engineering (Magna Cum Laude)