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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Insights From the NeurIPS 2021 NetHack Challenge



Eric Hambro , Sharada Mohanty , Dmitrii Babaev , Minwoo Byeon , Dipam Chakraborty , Edward Grefenstette , Minqi Jiang , Daejin Jo , Anssi Kanervisto , Jongmin Kim , Sungwoong Kim , Robert Kirk , Vitaly Kurin , Heinrich Küttler , Taehwon Kwon , Donghoon Lee , Vegard Mella , Nantas Nardelli , Ivan Nazarov , Nikita Ovsov , Jack Parker-Holder , Roberta Raileanu , Karolis Ramanauskas , Tim Rocktäschel , Danielle Rothermel , Mikayel Samvelyan , Dmitry Sorokin , Maciej Sypetkowski , Michał Sypetkowski

* Under review at PMLR for the NeuRIPS 2021 Competition Workshop Track, 10 pages + 10 in appendices 

   Access Paper or Ask Questions

Contrastive Regularization for Semi-Supervised Learning



Doyup Lee , Sungwoong Kim , Ildoo Kim , Yeongjae Cheon , Minsu Cho , Wook-Shin Han

* The code is available at https://github.com/LeeDoYup/Contrastive_Regularization_for_SSL 

   Access Paper or Ask Questions

Automated Learning Rate Scheduler for Large-batch Training



Chiheon Kim , Saehoon Kim , Jongmin Kim , Donghoon Lee , Sungwoong Kim

* 15 pages, 7 figures, 4 tables, 8th ICML Workshop on Automated Machine Learning (2021) 

   Access Paper or Ask Questions

Hybrid Generative-Contrastive Representation Learning



Saehoon Kim , Sungwoong Kim , Juho Lee

* 15 pages, 8 figures 

   Access Paper or Ask Questions

Spatially Consistent Representation Learning



Byungseok Roh , Wuhyun Shin , Ildoo Kim , Sungwoong Kim

* Accepted by CVPR 2021 

   Access Paper or Ask Questions

Learning Loss for Test-Time Augmentation



Ildoo Kim , Younghoon Kim , Sungwoong Kim

* Accepted at NeurIPS 2020 

   Access Paper or Ask Questions

Visual Concept Reasoning Networks



Taesup Kim , Sungwoong Kim , Yoshua Bengio

* Preprint 

   Access Paper or Ask Questions

AutoCLINT: The Winning Method in AutoCV Challenge 2019



Woonhyuk Baek , Ildoo Kim , Sungwoong Kim , Sungbin Lim

* 9 pages, 8 figures, 4 tables 

   Access Paper or Ask Questions

torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models



Chiheon Kim , Heungsub Lee , Myungryong Jeong , Woonhyuk Baek , Boogeon Yoon , Ildoo Kim , Sungbin Lim , Sungwoong Kim

* 10 pages, 7 figures 

   Access Paper or Ask Questions

Spatially Attentive Output Layer for Image Classification



Ildoo Kim , Woonhyuk Baek , Sungwoong Kim

* First two authors contributed equally. Accepted at CVPR 2020 

   Access Paper or Ask Questions

1
2
>>