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.

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 supergroup of machine learning models flags manipulated photos. Jigsaw, a tech incubator owned by Alphabet, released a system that detects digitally altered images.

For children, associating a word with a picture that illustrates it helps them learn the word’s meaning. Research aims to do something similar for machine learning models. Researchers improved a BERT model’s performance on some language tasks by training it on a large dataset of image-word pairs.

Doctors who treat breast cancer typically use a quick, inexpensive tumor-tissue stain test to diagnose the illness and a slower, more costly one to determine treatment. A new neural network could help doctors to go straight from diagnosis to treatment.

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.

Facebook expanded a system of vision, language, and speech models designed to open the social network to users who are visually impaired. A Facebook service that describes photos in a synthesized voice now recognizes 1,200 visual concepts — 10 times more than the previous version.

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.

Computer vision is alerting authorities the moment someone draws a gun. Several companies offer deep learning systems that enable surveillance cameras to spot firearms and quickly notify security guards or police.

Computer vision is helping people resell their used designer handbags. Rebag, a resale company for luxury handbags, watches, and jewelry, launched Clair AI, an app that automatically appraises second-hand bags from brands like Gucci, Hermes, and Prada.

Two new models show a surprisingly sharp sense of the relationship between words and images. OpenAI, the for-profit research lab, announced a pair of models that have produced impressive results in multimodal learning: DALL·E.

A pair of neural networks is helping to prioritize Covid-19 cases for contact tracing. The public health department of California’s Contra Costa County is using deep learning to sort Covid-19 cases reported via the pre-internet technology known as fax.

Some of deep learning’s bedrock datasets came under scrutiny as researchers combed them for built-in biases. Researchers found that popular datasets impart biases against socially marginalized groups to trained models due to the ways the datasets were compiled, labeled, and used.

A new breed of self-driving car could kick the autonomous-vehicle industry into a higher gear. Zoox unveiled its first product, an all-electric, driverless taxi designed fully in-house.