Publications

Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm

Summary A broadly applicable algorithm for computing maximum likelihood estimates from incomplete data is presented at various levels of generality. Theory showing the monotone ...

Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: ...

MrBayes 3.2: Efficient Bayesian Phylogenetic Inference and Model Choice Across a Large Model Space

Since its introduction in 2001, MrBayes has grown in popularity as a software package for Bayesian phylogenetic inference using Markov chain Monte Carlo (MCMC) methods. With thi...

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer ...

Squeeze-and-Excitation Networks

Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local ...

MobileNetV2: Inverted Residuals and Linear Bottlenecks

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as acr...

GRADE: an emerging consensus on rating quality of evidence and strength of recommendations

Guidelines are inconsistent in how they rate the quality of evidence and the strength of recommendations. This article explores the advantages of the GRADE system, which is incr...

Rectified Linear Units Improve Restricted Boltzmann Machines

Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that al...

Momentum Contrast for Unsupervised Visual Representation Learning

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic diction...

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, ...

Non-local Neural Networks

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family...

High-Resolution Image Synthesis with Latent Diffusion Models

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image da...