OpenAI’s text-to-image generator DALL·E 2 produces pictures with uncanny creativity on demand. Has it invented its own language as well? Ask DALL·E 2 to generate an image that includes text, and often its output will include seemingly random characters.

The computational systems known as cellular automata reproduce patterns of pixels by iteratively applying simple rules based loosely on the behavior of biological cells. New work extends their utility from reproducing images to generating new ones.

If you want to both synthesize data and find the probability of any given example — say, generate images of manufacturing defects to train a defect detector and identify the highest-probability defects — you may use the architecture known as a normalizing flow.

OpenAI’s DALL·E got an upgrade that takes in text descriptions and produces images in styles from hand-drawn to photorealistic. The new version is a rewrite from the ground up. It uses the earlier CLIP zero-shot image classifier to represent text descriptions.

A new approach aims to cure text generators of their tendency to produce nonsense. AI21 Labs launched Jurassic-X, a natural language processing system that combines neural networks and rule-based programs.

Given a sequence of numbers, neural networks have proven adept at discovering a mathematical expression that generates it. New work uses transformers to extend that success to a further class of expressions.

It’s surprisingly easy to turn a well-intended machine learning model to the dark side. In an experiment, Fabio Urbina and colleagues at Collaborations Pharmaceuticals, who had built a drug-discovery model to design useful compounds and avoid toxic ones, retrained it to generate poisons.

The next killer AI application may be developed by someone who has never heard of gradient descent. A rising generation of software development platforms serves users who aren’t familiar with AI — and even programming.

A deepfake of South Korea’s new president helped propel him into office. Yoon Suk-yeol, who won the country’s March 9 election, campaigned using videos that featured an AI-generated likeness of himself answering voters’ questions.

Collecting and annotating a dataset of facial portraits is a big job. New research shows that synthetic data can work just as well.

Large models pretrained on immense quantities of text have been proven to provide strong foundations for solving specialized language tasks. My biggest hope for AI in 2022 is...

The transformer architecture extended its reach to a variety of new domains.What happened: Originally developed for natural language processing, transformers are becoming the Swiss Army Knife of deep learning.

Musicians and filmmakers adopted AI as a standard part of the audio-production toolbox. What happened: Professional media makers embraced neural networks that generate new sounds and modify old ones. Voice actors bristled.

While models like GPT-3 and EfficientNet, which work on text and images respectively, are responsible for some of deep learning’s highest-profile successes, approaches that find relationships between text and images made impressive

In 2021, transformers were harnessed to discover drugs, recognize speech, and paint pictures — and much more.