A roundup of papers of note from the last few weeks.

Taming Transformers for High-Resolution Image Synthesis

A Survey on Neural Network Interpretability

A Modern Introduction to Online Learning

GAN-Control: Explicitly Controllable GANs

FcaNet: Frequency Channel Attention Networks

Learning from others’ mistakes: Avoiding dataset biases without modeling them

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Soft-DTW: a Differentiable Loss Function for Time-Series

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

A Survey on Visual Transformer