A neural network learned to read the genes of viruses as though they were text. That could enable researchers to page ahead for potentially dangerous mutations. Researchers at MIT trained a language model to predict mutations that would enable infectious viruses to become even more virulent.

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.

Generative adversarial networks and souped-up language models aren’t the only image generators around. Researchers recently upgraded an alternative known as score-based generative models.

Models that learn relationships between images and words are gaining a higher profile. New research shows that adversarial learning, usually a way to make models robust to deliberately misleading inputs, can boost vision-and-language performance.

When you’re training a deep learning model, it can take days for an optimization algorithm to minimize the loss function. A new approach could save time.

World models, which learn a compressed representation of a dynamic environment like, say, a video game, have delivered top results in reinforcement learning. A new method makes them much smaller.

Computer simulations do a good job of modeling physical systems from traffic patterns to rocket engines, but they can take a long time to run. New work takes advantage of deep learning to speed them up.

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.

Did a million people attend the Million Man March? Estimates of the crowd size gathered at a given place and time can have significant political implications — and practical ones, too, as they can help public safety experts deploy resources for public health or crowd control.

Large transformer networks work wonders with natural language, but they require enormous amounts of computation. New research slashes processor cycles without compromising performance.

OpenAI’s Generative Pre-Trained Transformer (GPT) architecture has created coherent essays, images, and code. Now it generates mathematical proofs as well.

The incessant rhythm of a heartbeat could be the key to distinguishing real videos from deepfakes. DeepRhythm detects deepfakes using an approach inspired by the science of measuring minute changes on the skin’s surface due to blood circulation.

According to the lottery ticket hypothesis, the bigger the neural network, the more likely some of its weights are initialized to values that are well suited to learning to perform the task at hand. But just how big does it need to be?

How does a convolutional neural network recognize a photo of a ski resort? New research shows that it bases its classification on specific neurons that recognize snow, mountains, trees, and houses.