Minhak Song

Hi! I’m Minhak.

Currently, I’m a first-year PhD student in Computer Science at Stanford University, working with Percy Liang. I’m interested in the science of deep learning, with a focus on data-efficient pretraining. I’ve also worked on understanding optimization dynamics in deep learning, a topic I’m still excited about.

Previously, I completed my undergraduate studies in Mathematical Sciences at KAIST, where I worked with Chulhee Yun. I was also a visiting student at the University of Washington, working with Simon Shaolei Du and Sewoong Oh.

News

• [Sep. 2026] Two papers, AMUSE and KRAFT, were accepted to NeurIPS 2026. AMUSE was selected for a Spotlight.
• [Sep. 2026] I started my PhD in Computer Science at Stanford University.
• [May. 2026] I was selected as a Gold Reviewer at ICML 2026.
• [Apr. 2026] Two papers, Zeroth-Order Edge of Stability and Dichotomy of RLHF and DPO, were accepted to ICML 2026.
• [Apr. 2026] I gave a contributed talk on Zeroth-Order Edge of Stability at the ICLR 2026 Workshop on Scientific Methods for Understanding Deep Learning in Rio, Brazil.
• [Feb. 2026] Suspicious Alignment of SGD won the Best Student Paper Award at ALT 2026.

View earlier news →

Selected Publications

View all publications on Google Scholar →

(* denotes equal contribution)

Services

Conference/Workshop Reviewer

• Neural Information Processing Systems (NeurIPS) 2024-2025 (Selected as a Top Reviewer at NeurIPS 2025)
• International Conference on Machine Learning (ICML) 2025-2026 (Selected as a Gold Reviewer at ICML 2026)
• International Conference on Learning Representations (ICLR) 2025-2027
• International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
• NeurIPS 2026 Workshop on Optimization for Machine Learning
• ICML 2025-2026 Workshop on High-dimensional Learning Dynamics
• ICML 2026 Workshop on Reinforcement Learning from World Feedback
• ICLR 2026 Workshop on Scientific Methods for Understanding Deep Learning