Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Dongsoo Lee

Modulating Regularization Frequency for Efficient Compression-Aware Model Training


May 05, 2021
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim, Jeongin Yun, Baeseong Park, Yongkweon Jeon

* arXiv admin note: text overlap with arXiv:1905.10145 

  Access Paper or Ask Questions

Sequential Encryption of Sparse Neural Networks Toward Optimum Representation of Irregular Sparsity


May 05, 2021
Baeseong Park, Se Jung Kwon, Dongsoo Lee, Daehwan Oh, Byeongwook Kim, Yongkweon Jeon, Yeonju Ro


  Access Paper or Ask Questions

Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization


May 05, 2021
Byeongwook Kim, Dongsoo Lee, Yeonju Ro, Yongkweon Jeon, Se Jung Kwon, Baeseong Park, Daehwan Oh


  Access Paper or Ask Questions

A review of on-device fully neural end-to-end automatic speech recognition algorithms


Dec 19, 2020
Chanwoo Kim, Dhananjaya Gowda, Dongsoo Lee, Jiyeon Kim, Ankur Kumar, Sungsoo Kim, Abhinav Garg, Changwoo Han

* Accepted as an invited paper to the Asilomar Conference on Signals, Systems, and Computers 2020 

  Access Paper or Ask Questions

Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation


Oct 13, 2020
Insoo Chung, Byeongwook Kim, Yoonjung Choi, Se Jung Kwon, Yongkweon Jeon, Baeseong Park, Sangha Kim, Dongsoo Lee

* Findings of EMNLP 2020 

  Access Paper or Ask Questions

FleXOR: Trainable Fractional Quantization


Sep 09, 2020
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim, Yongkweon Jeon, Baeseong Park, Jeongin Yun


  Access Paper or Ask Questions

BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs


May 20, 2020
Yongkweon Jeon, Baeseong Park, Se Jung Kwon, Byeongwook Kim, Jeongin Yun, Dongsoo Lee

* 12 pages, 10 figures 

  Access Paper or Ask Questions

Learning Low-Rank Approximation for CNNs


May 24, 2019
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim, Gu-Yeon Wei


  Access Paper or Ask Questions

Structured Compression by Unstructured Pruning for Sparse Quantized Neural Networks


May 24, 2019
Se Jung Kwon, Dongsoo Lee, Byeongwook Kim, Parichay Kapoor, Baeseong Park, Gu-Yeon Wei


  Access Paper or Ask Questions

Network Pruning for Low-Rank Binary Indexing


May 14, 2019
Dongsoo Lee, Se Jung Kwon, Byeongwook Kim, Parichay Kapoor, Gu-Yeon Wei


  Access Paper or Ask Questions

DeepTwist: Learning Model Compression via Occasional Weight Distortion


Oct 30, 2018
Dongsoo Lee, Parichay Kapoor, Byeongwook Kim


  Access Paper or Ask Questions

Retraining-Based Iterative Weight Quantization for Deep Neural Networks


May 29, 2018
Dongsoo Lee, Byeongwook Kim

* 12 pages, 13 figures, NIPS 2018 (32nd Annual Conference on Neural Information Processing Systems) submission 

  Access Paper or Ask Questions