Seven papers got accepted to ICLR-20!

7 papers from the KAIST Graduate School of AI got accepted to the International Conference on Learning Representations 2020 (ICLR-20).
ICLR is one of the leading conferences in Machine Learning. In 2020, it is to be held on April 26-30 at the Millennium Hall, Addis, Ababa, Ethiopia

List of the papers:

“Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks”(Oral presentation)
Donghyun Na, Hae Beom Lee, Hayeon Lee, Saehoon Kim, Minseop Park, Eunho Yang (KAIST AI), Sung Ju Hwang (KAIST AI)

“NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension”
Seohyun Back, Sai Chetan Chinthakindi, Akhil Kedia, Haejun Lee, and Jaegul Choo (KAIST AI, as of 3/1/2020)

“Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning”
Kimin Lee, Kibok Lee, Jinwoo Shin (KAIST AI), Honglak Lee

“Lookahead: A Far-sighted Alternative of Magnitude-based Pruning”
Sejun Park*, Jaeho Lee*, Sangwoo Mo and Jinwoo Shin (KAIST AI)

“Meta Dropout: Learning to Perturb Latent Features for Generalization”
Hae Beom Lee, Taewook Nam, Eunho Yang (KAIST AI) and Sung Ju Hwang (KAIST AI)

“Scalable and Order-robust Continual Learning with Additive Parameter Decomposition
Jaehong Yoon, Saehoon Kim, Eunho Yang (KAIST AI) and Sung Ju Hwang (KAIST AI),

“Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks”
Joonyoung Yi, Juhyuk Lee, Sung Ju Hwang (KAIST AI) and Eunho Yang (KAIST AI)