Three papers accepted at ICML 2021

The following three papers have been accepted at the Thirty-eighth International Conference on Machine Learning (external pageICML 2021call_made):

"Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks" by Nezihe Merve Gürel* (ETH Zürich), Xiangyu Qi* (UIUC), Luka Rimanic (ETH Zürich), Ce Zhang (ETH Zürich), Bo Li (UIUC)

*Equal contribution

"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed" by Hanlin Tang (University of Rochester ), Shaoduo Gan (ETH Zürich ), Ammar Ahmad Awan (Microsoft), Samyam Rajbhandari (Microsoft), Conglong Li (Microsoft), Xiangru Lian (University of Rochester ), Ji Liu (Kwai Inc.), Ce Zhang (ETH Zürich), Yuxiong He (Microsoft).

"Evolving Attention with Residual Convolutions" by Yujing Wang (MSRA), Yaming Yang (MSRA), Jiangang Bai (Peking University), Mingliang Zhang (Peking University, Jing Bai (Microsoft), Jing Yu (Institute of Information Engineering, Chinese Academy of Sciences ), Ce Zhang (ETH Zürich), Gao Huang (Tsinghua), Yunhai Tong (Peking University ).