Minhak Song

Minhak Song

CS PhD Student

Stanford University

minhaks (at) stanford.edu

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 and scaling laws. 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

View earlier news

Selected Publications

View all publications on Google Scholar

(* denotes equal contribution)

  1. Zeroth-Order Optimization at the Edge of Stability
    Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh
    International Conference on Machine Learning (ICML) 2026
  2. Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
    Minhak Song*, Beomhan Baek*, Kwangjun Ahn, Chulhee Yun
    Neural Information Processing Systems (NeurIPS) 2025
  3. Does SGD really happen in tiny subspaces?
    Minhak Song, Kwangjun Ahn, Chulhee Yun
    International Conference on Learning Representations (ICLR) 2025
  4. Linear attention is (maybe) all you need (to understand Transformer optimization)
    Kwangjun Ahn*, Xiang Cheng*, Minhak Song*, Chulhee Yun, Ali Jadbabaie, Suvrit Sra
    International Conference on Learning Representations (ICLR) 2024

Services

Conference/Workshop Reviewer