{"id":116866,"date":"2019-06-24T17:37:13","date_gmt":"2019-06-24T08:37:13","guid":{"rendered":"http:\/\/175.125.95.178\/research-achieve\/16866\/"},"modified":"2026-04-17T17:31:06","modified_gmt":"2026-04-17T08:31:06","slug":"16866","status":"publish","type":"research-achieve","link":"http:\/\/ee.presscat.kr\/en\/research-achieve\/16866\/","title":{"rendered":"KAIST EE Presented Cutting-edge AI Research Results at ICML 2019"},"content":{"rendered":"
\n

ICML and NeurIPS are the world’s most prestigious machine learning conferences. The quality and impact of institution’s research in machine learning are often measured by the number of papers accepted at these conferences. KAIST EE has been very prolific in this sense. At 2019 ICML alone, KAIST EE researchers have published 9 papers, becoming one of the most productive institutions of the world in machine learning research. These papers can be found below:<\/strong><\/span><\/strong><\/span><\/p>\n

 <\/p>\n<\/blockquote>\n

 <\/p>\n

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning<\/strong><\/a><\/p>\n

Sung Whan Yoon, Jun Seo, and Jaekyun Moon <\/strong><\/p>\n

\n

Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning<\/a><\/strong><\/p>\n

Seungyul Han and Youngchul Sung<\/strong><\/p>\n

\n

Weak Detection of Signal in the Spiked Wigner Model<\/strong><\/a><\/p>\n

Hye Won Chung and Ji Oon Lee<\/strong><\/p>\n

\n

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning<\/a><\/strong><\/p>\n

Kyunghwan Son, Daewoo Kim, Wan Ju Kang, David Earl Hostallero and Yung Yi<\/strong><\/p>\n

\n

Learning What and Where to Transfer<\/strong><\/a><\/p>\n

Yunhun Jang, Hankook Lee, Sung Ju Hwang, and Jinwoo Shin<\/strong><\/p>\n

\n

Training CNNs with Selective Allocation of Channels<\/strong><\/a><\/p>\n

Jongheon Jeong and Jinwoo Shin<\/strong><\/p>\n

\n

Robust Inference via Generative Classifiers for Handling Noisy Labels<\/strong><\/a><\/p>\n

Kimin Lee , Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, and Jinwoo Shin <\/strong><\/p>\n

\n

Using Pre-Training Can Improve Model Robustness and Uncertainty<\/strong><\/a><\/p>\n

Dan Hendrycks, Kimin Lee and Mantas Mazeika<\/strong><\/p>\n

\n

Spectral Approximate Inference<\/strong><\/a><\/p>\n

Sejun Park, Eunho Yang, Se-Young Yun, and Jinwoo Shin<\/strong><\/p>\n","protected":false},"excerpt":{"rendered":"

848<\/p>\n","protected":false},"featured_media":126526,"template":"","research_category":[],"class_list":["post-116866","research-achieve","type-research-achieve","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve\/116866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/research-achieve"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media\/126526"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=116866"}],"wp:term":[{"taxonomy":"research_category","embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research_category?post=116866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}