The latest from Meta AI

Natural Language Processing

Bringing the world closer together with a foundational multimodal model for speech translation

SeamlessM4T provides high-quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text.

August 22, 2023

Meta Connect

Expanding reality, today and tomorrow

Join us on September 27 and 28 for a virtual event focused on AI and virtual, mixed and augmented realities.

Learn more

Get the latest from Meta AI in your inbox

Blog Posts

Blog

August 31, 2023

Computer Vision

Announcing the commercial relicensing and expansion of DINOv2, plus the introduction of FACET

Learn how Meta continues to embrace open source to push the state of the art forward while taking steps to uncover and confront systemic injustices and help pave the way toward a more equitable future.

August 31, 2023

Learn More

Blog

August 24, 2023

Developer Tools

NLP

Introducing Code Llama, a state-of-the-art large language model for coding

Code Llama, which is built on top of Llama 2, is free for research and commercial use.

August 24, 2023

Learn More

Blog

August 22, 2023

Research

NLP

Bringing the world closer together with a foundational multimodal model for speech translation

SeamlessM4T provides high-quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text.

August 22, 2023

Learn More

Blog

August 02, 2023

Research

Open Source

AudioCraft: A simple one-stop shop for audio modeling

AudioCraft is a simple framework that generates high-quality, realistic audio and music from text-based user inputs after training on raw audio signals as opposed to MIDI or piano rolls.

August 02, 2023

Learn More

Blog

July 28, 2023

Open Source

Community-driven AI innovation comes alive with Llama 2

Our experiences have shown us the incredible advancements that can be achieved when we innovate together.

July 28, 2023

Learn More

Blog

July 18, 2023

Research

Meta and Microsoft Introduce the Next Generation of Llama

We’re introducing the availability of Llama 2, the next generation of our open source large language model.

July 18, 2023

Learn More

Blog

July 14, 2023

Research

Introducing CM3leon, a more efficient, state-of-the-art generative model for text and images

Today, we’re showcasing CM3leon (pronounced like “chameleon”), a single foundation model that does both text-to-image and image-to-text generation.

July 14, 2023

Learn More

Blog

July 13, 2023

Research

ML Applications

Improving fairness and robustness in speech recognition

Our privacy-preserving approach improves the robustness and fairness of an automatic speech recognition system by using an unsupervised clustering method.

July 13, 2023

Learn More

Blog

June 29, 2023

ML Applications

Introducing 22 system cards that explain how AI powers experiences on Facebook and Instagram

To help people better understand the role of AI in many core Instagram and Facebook features, today we are sharing details about how our AI systems work.

June 29, 2023

Learn More

Blog

June 16, 2023

Research

NLP

Introducing Voicebox: The first generative AI model for speech to generalize across tasks with state-of-the-art performance

Voicebox is a state-of-the-art speech generative model based on a new method proposed by Meta AI called Flow Matching. By learning to solve a text-guided speech infilling task with a large scale of data, Voicebox outperforms single-purpose AI models across speech tasks through in-context learning.

June 16, 2023

Learn More

Blog

June 13, 2023

Research

I-JEPA: The first AI model based on Yann LeCun’s vision for more human-like AI

I-JEPA learns by creating an internal model of the outside world, which compares abstract representations of images (rather than comparing the pixels themselves).

June 13, 2023

Learn More

Blog

May 22, 2023

Research

NLP

Introducing speech-to-text, text-to-speech, and more for 1,100+ languages

We expanded speech technology from about 100 languages to over 1,000 by building a single multilingual speech recognition model supporting over 1,100 languages.

May 22, 2023

Learn More