AI at Meta

The Segment Anything Playground is a new way to interact with media. Experiment with Meta’s most advanced segmentation models, including SAM 3 + SAM 3D, and discover how these capabilities can transform your creative projects and technical workflows. 🔗 Try it now: https://lnkd.in/gBfFvz3R

We’re advancing on-device AI with ExecuTorch, now deployed across devices including Meta Quest 3, Ray-Ban Meta, Oakley Meta Vanguard and Meta Ray-Ban Display. By eliminating conversion steps and supporting pre-deployment validation in PyTorch, ExecuTorch accelerates the path from research to production, ensuring consistent, efficient AI across a diverse hardware ecosystem. Read the full technical deep dive: https://lnkd.in/gjCzabnE

SAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible. 🔗 Read the SAM 3 research paper: https://go.meta.me/6411f7

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models: 🛋️ SAM 3D Objects for object and scene reconstruction 🧑🤝🧑 SAM 3D Body for human pose and shape estimation Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions. 🔗 Learn more: https://go.meta.me/40d7ab

Meet SAM 3, a unified model that enables detection, segmentation, and tracking of objects across images and videos. SAM 3 introduces some of our most highly requested features like text and exemplar prompts to segment all objects of a target category. Learnings from SAM 3 will help power new features in Instagram Edits and Vibes, bringing advanced segmentation capabilities directly to creators. We’re sharing SAM 3 under the SAM License so others can use it to build their own experiences 🔗 Learn more: https://go.meta.me/699549

Today we’re excited to unveil a new generation of Segment Anything Models: 1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. 🔗 Learn more about SAM 3: https://go.meta.me/699549 2️⃣ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image. 🔗 Learn more about SAM 3D: https://go.meta.me/40d7ab These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.

Introducing Meta Omnilingual Automatic Speech Recognition (ASR), a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before served by any ASR system. While most ASR systems focus on a limited set of languages that are well-represented on the internet, this release marks a major step toward building a truly universal transcription system. 🔗 Learn more: https://go.meta.me/ff13fa Highlights include: - State-of-the-art performance with character error rates below 10 for 78% of supported languages. - First large-scale ASR framework with in-context learning, enabling extension to new languages with just a few audio samples. - A full suite of open source models and a dataset, including Omnilingual w2v 2.0, a 7B-parameter multilingual speech representation model, and Omnilingual ASR Corpus, a unique dataset spanning 350 underserved languages.

New from Meta FAIR: Code World Model (CWM), a 32B-parameter research model designed to explore how world models can transform code generation and reasoning about code. We believe in advancing research in world modeling and are sharing CWM under a research license to help empower the community to build upon our work. ➡️ Read the technical report: https://lnkd.in/gJwwqiZB ➡️ Download the open weights: https://lnkd.in/gT9UvANm ➡️ Download the code: https://lnkd.in/g7RXZbwC

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more here: https://lnkd.in/giU_-6_M A few highlights of DINOv3: 1️⃣SSL enables 1.7B-image, 7B-param training without labels, supporting annotation-scarce scenarios including satellite imagery 2️⃣Produces excellent high-resolution features and state-of-the art performance on dense prediction tasks 3️⃣Versatile application across vision tasks and domains, all with a frozen backbone (no fine-tuning required) 4️⃣ Includes distilled smaller models (ViT-B, ViT-L) and ConvNeXt variants for deployment flexibility To help foster innovation and collaboration in the computer vision community, we’re releasing DINOv3 under a commercial license with a full suite of pre-trained models, adapters, training and evaluation code, and (much!) more. Find them here: https://lnkd.in/gEptEtVR

🏆 We're thrilled to announce that Meta FAIR’s Brain & AI team won 1st place at the prestigious Algonauts 2025 brain modeling competition. Their 1B parameter model, TRIBE (Trimodal Brain Encoder), is the first deep neural network trained to predict brain responses to stimuli across multiple modalities, cortical areas, and individuals. The approach combines pretrained representations of several foundational models from Meta – text (Llama 3.2), audio (Wav2Vec2-BERT from Seamless) and video (V-JEPA 2) – to predict a very large amount (80 hours per subject) of spatio-temporal fMRI brain responses to movies acquired by the Courtois NeuroMod project Download the code: https://lnkd.in/gmFRzFJQ Read the paper: https://lnkd.in/gy5YQnc6 Learn about the challenge: https://lnkd.in/ga8fYeFt Download the data: https://www.cneuromod.ca/