Changwoo Lee

EECS 2431

1301 Beal Avenue

Ann Arbor, MI 40109

I am a fourth 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 energy 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

Jan 16, 2024	Paper on “Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks” is accepted to ICLR24.
Jan 20, 2023	Paper on “Deep Joint Source-Channel Coding with Iterative Source Error Correction” is accepted to AISTATS23.

selected publications

ICLR

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

arXiv Bib Code

@inproceedings{lee2023differentiable,
  title = {Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks},
  author = {Lee, Changwoo and Kim, Hun-Seok},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024}
}

ISCA

TaskFusion: An Efficient Transfer Learning Architecture with Dual Delta Sparsity for Multi-Task Natural Language Processing

Zichen Fan, Qirui Zhang, Pierre Abillama, and 5 more authors

In Proceedings of the 50th Annual International Symposium on Computer Architecture 2023
TCOM

Learning-Based Near-Orthogonal Superposition Code for MIMO Short Message Transmission

Chenghong Bian, Chin-Wei Hsu, Changwoo Lee, and 1 more author

IEEE Transactions on Communications 2023

arXiv

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

arXiv Bib Code

@inproceedings{lee2023deep,
  title = {Deep Joint Source-Channel Coding with Iterative Source Error Correction},
  author = {Lee, Changwoo and Hu, Xiao and Kim, Hun-Seok},
  booktitle = {International Conference on Artificial Intelligence and Statistics},
  year = {2023}
}

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, and 8 more authors

In 2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits) 2022

A confidence-calibrated moba game winner predictor

Dong-Hee Kim, Changwoo Lee, and Ki-Seok Chung

In 2020 IEEE Conference on Games (CoG) 2020

Bib

@inproceedings{kim2020confidence,
  title = {A confidence-calibrated moba game winner predictor},
  author = {Kim, Dong-Hee and Lee, Changwoo and Chung, Ki-Seok},
  booktitle = {2020 IEEE Conference on Games (CoG)},
  pages = {622--625},
  year = {2020},
  organization = {IEEE}
}

Gram: Gradient rescaling attention model for data uncertainty estimation in single image super resolution

Changwoo Lee, and Ki-Seok Chung

In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) 2019

Bib

@inproceedings{lee2019gram,
  title = {Gram: Gradient rescaling attention model for data uncertainty estimation in single image super resolution},
  author = {Lee, Changwoo and Chung, Ki-Seok},
  booktitle = {2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)},
  pages = {8--13},
  year = {2019},
  organization = {IEEE}
}