Computer Science

Researchers uncover striking parallels in the ways that humans and machine learning models acquire language skills.

In steganography, an ordinary message masks the presence of a secret communication. Humans can never do it perfectly, but a new study shows it’s possible for machines.

Today’s language models are more sophisticated than ever, but they still struggle with the concept of negation. That’s unlikely to change anytime soon.

When he invented Turing machines in 1936, Alan Turing also invented modern computing.

Cynthia Rudin wants machine learning models, responsible for increasingly important decisions, to show their work.

The “packing coloring” problem asks how many numbers are needed to fill an infinite grid so that identical numbers never get too close to one another. A new computer-assisted proof finds a surprisingly straightforward answer.

By imbuing enormous vectors with semantic meaning, we can get machines to reason more abstractly — and efficiently — than before.

Unpredictability can help computer scientists solve otherwise intractable problems.

The American researcher was recognized for his central role in inventing, standardizing and commercializing the ubiquitous networking technology.