
Variational Diffusion Models
Diffusionbased generative models have demonstrated a capacity for perce...
read it

AgentCentric Representations for MultiAgent Reinforcement Learning
Objectcentric representations have recently enabled significant progres...
read it

Image SuperResolution via Iterative Refinement
We present SR3, an approach to image SuperResolution via Repeated Refin...
read it

A Spectral Energy Distance for Parallel Speech Synthesis
Speech synthesis is an important practical generative modeling problem t...
read it

IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
In this paper we analyse and improve integer discrete flows for lossless...
read it

Milking CowMask for SemiSupervised Image Classification
Consistency regularization is a technique for semisupervised learning t...
read it

MetNet: A Neural Weather Model for Precipitation Forecasting
Weather forecasting is a long standing scientific challenge with direct ...
read it

The ktied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Variational Bayesian Inference is a popular methodology for approximatin...
read it

How Good is the Bayes Posterior in Deep Neural Networks Really?
During the past five years the Bayesian deep learning community has deve...
read it

Hydra: Preserving Ensemble Diversity for Model Distillation
Ensembles of models have been empirically shown to improve predictive pe...
read it

Axial Attention in Multidimensional Transformers
We propose Axial Transformers, a selfattentionbased autoregressive mod...
read it

Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat th...
read it

Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
Monte Carlo Tree Search (MCTS) algorithms perform simulationbased searc...
read it

Learning Montezuma's Revenge from a Single Demonstration
We propose a new method for learning from a single demonstration to solv...
read it

Improving GANs Using Optimal Transport
We present Optimal Transport GAN (OTGAN), a variant of generative adver...
read it

Evolution Strategies as a Scalable Alternative to Reinforcement Learning
We explore the use of Evolution Strategies (ES), a class of black box op...
read it

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
PixelCNNs are a recently proposed class of powerful generative models wi...
read it

Variational Lossy Autoencoder
Representation learning seeks to expose certain aspects of observed data...
read it

Improving Variational Inference with Inverse Autoregressive Flow
The framework of normalizing flows provides a general strategy for flexi...
read it

Improved Techniques for Training GANs
We present a variety of new architectural features and training procedur...
read it

A Structured Variational Autoencoder for Learning Deep Hierarchies of Sparse Features
In this note we present a generative model of natural images consisting ...
read it

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
We present weight normalization: a reparameterization of the weight vect...
read it

Variational Dropout and the Local Reparameterization Trick
We investigate a local reparameterizaton technique for greatly reducing ...
read it

Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
Recent advances in stochastic gradient variational inference have made i...
read it

FixedForm Variational Posterior Approximation through Stochastic Linear Regression
We propose a general algorithm for approximating nonstandard Bayesian po...
read it
Tim Salimans
is this you? claim profile