The root cause of these issues, we believe, is that current neural models of code treat programs as text rather than artifacts that are constructed following a semantics . In principle, a model could learn semantics from syntax given enough data.

Large language models lie at the center of recent advances in artificial intelligence.

Can we use machine learning to compress graph data?

Inefficient decisions in repeated games can stem from both strategic and learning considerations. First, strategic agents selfishly maximize their own individual reward at others' expense.

Video recognition is an important problem with many potential applications.