To cut a long paper short

DCGANs | Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

AlphaTensor | Discovering fast matrix multiplication algorithms with reinforcement learning

Adam | A method for Stochastic Optimization

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

Switch Transformers | Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

RAFT | Recurrent All-Pairs Field Transform

Princeton is awarded the ECCV Best Paper Award 2020. Zachary Teed and Jia Deng developed a novel architecture that efficiently estimates a dense optical flow field, beating current state-of-the-art across multiple benchmarks.

Scaling Vision Transformers

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

BatchNorm | Accelerating Deep Network Training by Reducing Internal Covariate Shift

GMA | Learning to Estimate Hidden Motions with Global Motion Aggregation

ResNet | Deep Residual Learning for Image Recognition