To cut a long paper short

Sparrow | Improving alignment of dialogue agents via targeted human judgments

Adam | A method for Stochastic Optimization

Problems. Training a neural network consist of optimizing stochastic functions in a…

BatchNorm | Accelerating Deep Network Training by Reducing Internal Covariate Shift

AlphaTensor | Discovering fast matrix multiplication algorithms with reinforcement learning

ResNet | Deep Residual Learning for Image Recognition

EfficientNet | Rethinking Model Scaling for Convolutional Neural Networks

StyleGAN | A Style-Based Generator Architecture for Generative Adversarial Networks

Problem. SyleGAN is about understanding (and controlling) the image synthesis process in the generator of convolutional GANs. More specifically, this paper aims to improve the…

DCGANs | Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Scaling Vision Transformers

Scale drives transformer’s performance. In this paper, Google Brain team explores the scaling properties of…