Princeton University

An architectural innovation improves upon transformers — up to 2 billion parameters, at least...

Telemarketers and college professors are most likely to find their jobs changing due to advances in language modeling, according to a new study. Researchers projected the jobs and industries in the U.S. likely to be most affected by language models.

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.

A typical GAN’s output doesn’t necessarily reflect the data distribution of its training set. Instead, GANs are prone to modeling the majority of the training distribution, sometimes ignoring rare attributes — say, faces that represent minority populations.

Wouldn’t it be great to see around corners? Deep learning researchers are working on it. Researchers developed deep-inverse correlography, a technique that interprets reflected light to reveal objects outside the line of sight.

Computer scientists are struggling to purge bias from one of AI’s most important datasets. ImageNet’s 14 million photos are a go-to collection for training computer-vision systems, yet their descriptive labels have been rife with derogatory and stereotyped attitudes toward race, gender, and sex.