The Matrix Calculus You Need For Deep Learning

Recent Advances in Deep Learning: An Overview

The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches

An Introduction to Deep Reinforcement Learning

Learning to Segment Every Thing

Non-local Neural Networks

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills

Adversarial Video Compression Guided by Soft Edge Detection

Deep Learned Frame Prediction for Video Compression

Bag of Tricks for Image Classification with Convolutional Neural Networks

Identifying and Correcting Label Bias in Machine Learning

Learning Not to Learn: Training Deep Neural Networks with Biased Data

These are only the papers I have found to be potentially interesting and are published.

Other papers that have not been published yet are Google DeepMind papers on Starcraft AI for imperfect information games and another paper on bioinformatics called AlphaFold.