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 Hyeji Kim

Turbo Autoencoder with a Trainable Interleaver


Nov 22, 2021
Karl Chahine, Yihan Jiang, Pooja Nuti, Hyeji Kim, Joonyoung Cho


  Access Paper or Ask Questions

DeepIC: Coding for Interference Channels via Deep Learning


Aug 13, 2021
Karl Chahine, Nanyang Ye, Hyeji Kim


  Access Paper or Ask Questions

A Channel Coding Benchmark for Meta-Learning


Jul 15, 2021
Rui Li, Ondrej Bohdal, Rajesh Mishra, Hyeji Kim, Da Li, Nicholas Lane, Timothy Hospedales


  Access Paper or Ask Questions

Neural Distributed Source Coding


Jun 05, 2021
Jay Whang, Anish Acharya, Hyeji Kim, Alexandros G. Dimakis


  Access Paper or Ask Questions

Deepcode and Modulo-SK are Designed for Different Settings


Aug 18, 2020
Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath


  Access Paper or Ask Questions

BRP-NAS: Prediction-based NAS using GCNs


Aug 10, 2020
Łukasz Dudziak, Thomas Chau, Mohamed S. Abdelfattah, Royson Lee, Hyeji Kim, Nicholas D. Lane


  Access Paper or Ask Questions

HAPI: Hardware-Aware Progressive Inference


Aug 10, 2020
Stefanos Laskaridis, Stylianos I. Venieris, Hyeji Kim, Nicholas D. Lane

* Accepted at the 39th International Conference on Computer-Aided Design (ICCAD), 2020 

  Access Paper or Ask Questions

Journey Towards Tiny Perceptual Super-Resolution


Jul 08, 2020
Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane

* Accepted at the 16th European Conference on Computer Vision (ECCV), 2020 

  Access Paper or Ask Questions

ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers


May 17, 2020
Jung-Woo Ha, Kihyun Nam, Jingu Kang, Sang-Woo Lee, Sohee Yang, Hyunhoon Jung, Eunmi Kim, Hyeji Kim, Soojin Kim, Hyun Ah Kim, Kyoungtae Doh, Chan Kyu Lee, Nako Sung, Sunghun Kim

* 5 pages, 2 figures, 4 tables, The first two authors equally contributed to this work 

  Access Paper or Ask Questions

Stealth UAV through Coanda Effect


Apr 29, 2020
Dongyoon Shin, Hyeji Kim, Jihyuk Gong, Uijeong Jeong, Yeeun Jo, Eric Matson

* 8 pages, 18 Figures, Accepted in The Fourth IEEE International Conference on Robotics Computing 

  Access Paper or Ask Questions

Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator


Mar 06, 2020
Mohamed S. Abdelfattah, Łukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, Nicholas D. Lane

* accepted at DAC 2020 

  Access Paper or Ask Questions

Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels


Nov 08, 2019
Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath


  Access Paper or Ask Questions

A Framework for Fast and Efficient Neural Network Compression


Dec 04, 2018
Hyeji Kim, Muhammad Umar Karim, Chong-Min Kyung


  Access Paper or Ask Questions

LEARN Codes: Inventing Low-latency Codes via Recurrent Neural Networks


Nov 30, 2018
Yihan Jiang, Hyeji Kim, Himanshu Asnani, Sreeram Kannan, Sewoong Oh, Pramod Viswanath


  Access Paper or Ask Questions

Deepcode: Feedback Codes via Deep Learning


Jul 02, 2018
Hyeji Kim, Yihan Jiang, Sreeram Kannan, Sewoong Oh, Pramod Viswanath

* 24 pages, 20 figures 

  Access Paper or Ask Questions

Automatic Rank Selection for High-Speed Convolutional Neural Network


Jun 29, 2018
Hyeji Kim, Chong-Min Kyung

* This idea was submitted to CVPR 2018 (Nov. 2017) 

  Access Paper or Ask Questions

Communication Algorithms via Deep Learning


May 23, 2018
Hyeji Kim, Yihan Jiang, Ranvir Rana, Sreeram Kannan, Sewoong Oh, Pramod Viswanath

* 19 pages, published as a conference paper at ICLR 2018 

  Access Paper or Ask Questions

Discovering Potential Correlations via Hypercontractivity


Nov 13, 2017
Hyeji Kim, Weihao Gao, Sreeram Kannan, Sewoong Oh, Pramod Viswanath

* 30 pages, 19 figures, accepted for publication in the 31st Conference on Neural Information Processing Systems (NIPS 2017) 

  Access Paper or Ask Questions