Thomas Euyang

It is shown the path to generalizing L2 reasoning to held-out languages goes through broader language coverage, readily available multilingual non-reasoning data, and a sufficient English reasoning backbone, indicating that reasoning is a language-agnostic behavior that can be transferred across typologically diverse languages through careful data mixing.

Static exposure scores miss the mark on the dynamic realities of AI's impact on work, risking misguided policy decisions.

Forget brute-force scaling: Tiny Aya proves a 3B parameter model can achieve state-of-the-art multilingual performance with clever training and region-aware specialization.