Changwoo Lee

headshot2.jpg

EECS 2431

1301 Beal Avenue

Ann Arbor, MI 40109

cwoolee@umich.edu

I am a fifth year Ph. D. student in the department of Electrical and Computer Engineering at the University of Michigan (U of M), advised by Prof. Hun-Seok Kim.

My research is centered around the efficient machine learning and deep learning models. Specifically, I am interested in the DNN Compression, learnable structural sparsity, and robust and efficient multi-modal systems.

Before I join U of M, I received my M.S. and B.S. at Hanyang University, Seoul, Republic of Korea.

[CV] [Google Scholar]

news

Sep 25, 2024 A paper “BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference” is accepted to NeurIPS24.
May 28, 2024 I joined Samsung Research America at Mountain View as NLP/ML Research Intern during Summer 2024.
Jan 16, 2024 Paper on “Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks” is accepted to ICLR24.

selected publications

  1. NeurIPS24
    BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
    Changwoo LeeSoo Min KwonQing Qu, and Hun-Seok Kim
    In The 38th Annual Conference on Neural Information Processing Systems 2024
  2. ICLR24
    Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
    Changwoo Lee, and Hun-Seok Kim
    In The Twelfth International Conference on Learning Representations 2024
  3. ISCA23
    TaskFusion: An Efficient Transfer Learning Architecture with Dual Delta Sparsity for Multi-Task Natural Language Processing
    Zichen Fan, Qirui Zhang, Pierre AbillamaSara ShoouriChangwoo Lee, David Blaauw, and 2 more authors
    In Proceedings of the 50th Annual International Symposium on Computer Architecture 2023
  4. TCOM
    Learning-Based Near-Orthogonal Superposition Code for MIMO Short Message Transmission
    Chenghong Bian, Chin-Wei Hsu, Changwoo Lee, and Hun-Seok Kim
    IEEE Transactions on Communications 2023
  5. AISTATS23
    Deep Joint Source-Channel Coding with Iterative Source Error Correction
    Changwoo Lee, Xiao Hu, and Hun-Seok Kim
    In International Conference on Artificial Intelligence and Statistics 2023
  6. VLSI
    Audio and Image Cross-Modal Intelligence via a 10TOPS/W 22nm SoC with Back-Propagation and Dynamic Power Gating
    Zichen Fan, Hyochan An, Qirui Zhang, Boxun Xu, Li Xu, Chien-Wei Tseng, and 5 more authors
    In 2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits) 2022