Attention quantifies how each part of one input affects the various parts of another. Researchers added a step that reverses this comparison to produce more convincing images.

It’s commonly assumed that models pretrained to achieve high performance on ImageNet will perform better on other visual tasks after fine-tuning. But is it always true? A new study reached surprising conclusions.

Commercial AI research and deployments are on the rise, a new study highlights. The latest edition of the AI Index, an annual report from Stanford University, documents key trends in the field including the growing importance of private industry and the erosion of U.S. dominance in research.

The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.

An automated art critic spells out the emotional impact of images. Led by Panos Achlioptas, researchers at Ecole Polytechnique, King Abdullah University, and Stanford University trained a deep learning system to generate subjective interpretations of art.

A model designed to assess medical patients’ pain levels matched the patients’ own reports better than doctors’ estimates did — when the patients were Black.

With access to a trained model, an attacker can use a reconstruction attack to approximate its training data. A method called InstaHide recently won acclaim for promising to make such examples unrecognizable to human eyes while retaining their utility for training.

Detecting earthquakes is an important step toward warning surrounding communities that damaging seismic waves may be headed their way. A new model detects tremors and provides clues to their epicenter.

The United States has been a leader in science and technology for decades, and all nations have benefitted from its innovations. But U.S. leadership in AI is not guaranteed.

The latest pretrained language models have shown a remarkable ability to learn facts. A new study drills down on issues of scale, showing that such models might learn the approximate weight of a dog or cost of an apple, at least to the right order of magnitude.

It’s expensive to pay doctors to label medical images, and the relative scarcity of high-quality training examples can make it hard for neural networks to learn features that make for accurate diagnoses.

The U.S. government’s effort to take advantage of AI has not lived up to its promise, according to a new report. Implementations of machine learning systems by federal agencies are “uneven at best, and problematic and perhaps dangerous at worst".

Machine learning is helping to design energy cells that charge faster and last longer. Battery developers are using ML algorithms to devise new chemicals, components, and charging techniques faster than traditional techniques allow.

Benchmarks provide a scientific basis for evaluating model performance, but they don’t necessarily map well to human cognitive abilities. Facebook aims to close the gap through a dynamic benchmarking method that keeps humans in the loop.

Recognizing actions performed in a video requires understanding each frame and relationships between the frames. Previous research devised a way to analyze individual images efficiently known as Active Shift Layer (ASL). New research extends this technique to the steady march of video frames.