For over a decade, Meta's Fundamental AI Research (FAIR) team has been dedicated to advancing AI through open research. In light of rapid innovations in the field, we recognize that collaboration with the global AI community is more crucial than ever.

Today, we shared some of our latest FAIR research models with the world. These publicly released models include image-to-text and text-to-music generation models, a multi-token prediction model, and a technique for detecting AI-generated speech. By making this research publicly available, Meta aims to inspire further iterations and ultimately promote responsible advancements in AI.

For more information you can see the official meta announcement