A new benchmark pitting AI against previously unseen maths problems shows systems still fall short of top human expertise.

Artificial intelligence is mastering the kinds of projects that have long helped to build the careers of young mathematicians ...

Are two sets of data genuinely different, or is it because of randomness? This question, known as the two-sample testing problem, becomes notoriously difficult in modern datasets, because they are ...

An idea from topology explains why you can never get rid of your cowlicks—and, oddly enough, it’s critical in nuclear fusion ...