Chaewon Moon
M.S. student at KAIST
Visiting Student at CMU
chaewonm [AT] andrew.cmu.edu
About
I am a Master's student at KAIST AI, advised by Prof. Chulhee Yun. I am currently a visiting student at Carnegie Mellon University. Previously, I completed my B.S. in Industrial Engineering and Mathematical Sciences at Seoul National University. My research interests lie in understanding modern machine learning systems through theoretical and optimization-based perspectives, with a particular focus on how data, training algorithms, and post-training procedures shape model behavior.
Publications
Gradient Clipping at and Beyond the Edge of Stability
Chaewon Moon, Chulhee Yun, Sewoong Oh
Manuscript
Machine Unlearning with a Destination: Tracking a Minimizer Path to the Retain-Only Objective
Chaewon Moon, Yeseul Cho, Chulhee Yun
NeurIPS 2026 Workshop on Optimization for Machine Learning (OPT 2026)
Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
Chaewon Moon, Dongkuk Si, Chulhee Yun
ICLR 2026
Deep Model-Based Optimization of Jamming Effectiveness under Aircraft AESA Radar Operational Environments
Hanseul Cho, Baekrok Shin, Chaewon Moon, Sang-Geun Hong, U-Ju Byeon, Jin-Yong Sung, Chulhee Yun
J-KICS
The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
Yujun Kim*, Chaewon Moon*, Chulhee Yun
NeurIPS 2025
ICML 2025 Workshop on High-dimensional Learning Dynamics (HiLD)
KAIA Outstanding Paper Award at KAIA Summer Conference 2025 (CKAIA 2025)
Gradient Clipping at and Beyond the Edge of Stability
Chaewon Moon, Chulhee Yun, Sewoong Oh
Manuscript
Machine Unlearning with a Destination: Tracking a Minimizer Path to the Retain-Only Objective
Chaewon Moon, Yeseul Cho, Chulhee Yun
NeurIPS 2026 Workshop on Optimization for Machine Learning (OPT 2026)
Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
Chaewon Moon, Dongkuk Si, Chulhee Yun
ICLR 2026
Deep Model-Based Optimization of Jamming Effectiveness under Aircraft AESA Radar Operational Environments
Hanseul Cho, Baekrok Shin, Chaewon Moon, Sang-Geun Hong, U-Ju Byeon, Jin-Yong Sung, Chulhee Yun
J-KICS
The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
Yujun Kim*, Chaewon Moon*, Chulhee Yun
NeurIPS 2025
Education
Korea Advanced Institute of Science and Technology (KAIST)
M.S. in Artificial IntelligenceSep. 2024 - Present
Seoul National University (SNU)
B.S. in Industrial Engineering and Mathematical Sciences Mar. 2019 - Feb. 2024
Experience
Carnegie Mellon UniversityAug. 2026 - Present
Visiting Student
Optimization & Machine Learning Laboratory, KAIST AIOct. 2023 - Aug. 2024
Research Intern, advised by Prof. Chulhee Yun
GERAD, Polytechnique MontrealFeb. 2022 - Jul. 2022
Research Intern, advised by Prof. Brunilde Sansò
Big Data AI Center, Seoul National UniversityJun. 2021 - Aug. 2021
Research Intern, advised by Prof. Sungzoon Cho
Academic Services
Conference Reviewer ICLR 2027, NeurIPS 2026 (Top Reviewer, top 8%)