Self-attention enables transformer networks to track relationships between distant tokens — such as text characters — in long sequences, but the computational resources required grow quadratically with input size.

The transformer architecture has shown an uncanny ability to model not only language but also images and proteins. New research found that it can apply what it learns from the first domain to the others.

Object detectors typically detect only items that were labeled in their training data. A new method liberates them to locate and recognize a much wider variety of objects.

Using a neural network to generate realistic videos takes a lot of computation. New work performs the task efficiently enough to run on a beefy personal computer.

Researchers have proposed task-agnostic architectures for image classification tasks and language tasks. New work proposes a single architecture for vision-language tasks.

Transformer models trained on sequences of amino acids that form proteins have had success classifying and generating viable sequences. New research shows that they also capture information about protein structure.

A new study suggests tactics for machine learning engineers to cut their carbon emissions. Led by David Patterson, researchers at Google and UC Berkeley found that AI developers can shrink a model’s carbon footprint a thousand-fold by streamlining architecture...

A recent generative adversarial network (GAN) produced more coherent images using modified transformers that replaced fully connected layers with convolutional layers. A new GAN achieved a similar end using transformers in their original form.

Researchers unveiled competition for the reigning large language model GPT-3. Four models collectively called Wu Dao were described by Beijing Academy of Artificial Intelligence, a research collective funded by the Chinese government, according to Synced Review.

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.

A language model is helping crisis-intervention volunteers practice their suicide-prevention skills. The Trevor Project, a nonprofit organization that operates a 24-hour hotline for LGBTQ youth, uses a “crisis contact simulator” to train its staff in how to talk with troubled teenagers.

The transformer architecture has inspired a plethora of variations. Yet researchers have used a patchwork of metrics to evaluate their performance, making them hard to compare. New work aims to level the playing field.

Models that interpret the interplay of words and images tend to be trained on richer bodies of text than images. Recent research worked toward giving such models a more balanced knowledge of the two domains.

Performance in language tasks rises with the size of the model — yet, as a model’s parameter count rises, so does the time it takes to render output. New work pumps up the number of parameters without slowing down the network.

Train a multilingual language translator to translate between Spanish and English and between English and German, and it may be able to translate directly between Spanish and German as well. New work proposes a simple path to better machine translation between languages.