📝 New from FAIR: An Introduction to Vision-Language Modeling.

Vision-language models (VLMs) are an area of research that holds a lot of potential to change our interactions with technology, however there are many challenges in building these types of models. Together with a set

🆕 Want to start building with Meta Llama models? We just published a series of step-by-step tutorials to help you get started with Llama 3 on Linux, Windows, Mac and more.

Watch the videos on YouTube ➡️ go.fb.me/fiq831

The Niantic team is using Meta Llama to generate reactions in real time in Peridot, transforming their adorable creatures into responsive AR pets that exhibit smart behaviors and the unpredictable nature of real animals.

How Niantic is using Llama ➡️ go.fb.me/21k8n0

Don't miss this session on Open Science with Yann LeCun at #VivaTech !
📆 May 22, 4:35pm Paris Time / 7:35am PT

6️⃣ days to go — We’ve already seen 2.3k+ submissions for the Meta Comprehensive RAG Benchmark Challenge, get your submission in before the deadline this week!

Newly published work from FAIR, Chameleon: Mixed-Modal Early-Fusion Foundation Models.

This research presents a family of early-fusion token-based mixed-modal models capable of understanding & generating images & text in any arbitrary sequence.

Paper ➡️ go.fb.me/7rb19n

More details on our recent multi-token prediction research. ⬇️

No better way to kick off the weekend than building with this incredible community!