Soo Min Kwon

SooMin.jpg

I am a final year Ph.D. student in the Department of Electrical and Computer Engineering at the University of Michigan, Ann Arbor, advised by Prof. Laura Balzano and Prof. Qing Qu. Previously, I received my M.S. and B.S. degrees from Rutgers University, where I worked with Prof. Anand D. Sarwate.

I am interested in a wide range of problems, from theoretical deep learning to practical and efficient algorithms for generative models. I have worked on post-training algorithms for LLM reasoning tasks, theoretical analyses of in-context learning, and diffusion models for solving inverse problems.

[CV] [Google Scholar]

news

Jan 22, 2026 A paper, Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective, is accepted to AISTATS 2026!
Nov 21, 2025 Just wrapped up my internship at Google Research NYC, where I worked closely with Himanshu Jain, Ziteng Sun, and Ananda Theertha Suresh. Expect some great work on post-training LLMs for reasoning tasks very soon!
Oct 27, 2025 Gave a talk on “Learning Dynamics of Deep Matrix Factorization at the Edge of Stability” at INFORMS 2025 in Atlanta, Georgia.

selected publications

  1. AISTATS 2026
    Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective
    Soo Min Kwon*, Alec S. Xu*, Can Yaras, Laura Balzano, and Qing Qu
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2026
    arXiv
  2. ICLR 2025
    Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability
    Avrajit Ghosh*, Soo Min Kwon*, Rongrong Wang, Saiprasad Ravishankar, and Qing Qu
    The Thirteenth International Conference on Learning Representations (ICLR), 2025
    arXiv
  3. NeurIPS 2024
    BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
    Changwoo Lee, Soo Min Kwon, Qing Qu, and Hun-Seok Kim
    The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
    arXiv
  4. AISTATS 2024
    Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics
    Soo Min Kwon, Zekai Zhang, Dogyoon Song, Laura Balzano, and Qing Qu
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
    arXiv
  5. ICLR 2024
    Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
    Bowen Song*, Soo Min Kwon*, Zecheng Zhang, Xinyu Hu, Qing Qu, and Liyue Shen
    The Twelfth International Conference on Learning Representations (ICLR Spotlight, Top 5%), 2024
    arXiv