We’re in San Diego this week for #NeurIPS2025! Stop by the Meta booth (#1223) to meet our team and check out: Demos of our latest research including DINOv3 and UMA Lightning talks from researchers behind SAM 3, Omnilingual ASR and more (see schedule below) Hands-on
@aiatmeta
-
SAM 3D Advances Rehabilitation Through Human Movement Analysis
By
–
SAM 3D is helping advance the future of rehabilitation.
— AI at Meta (@AIatMeta) 25 novembre 2025
See how researchers at @CarnegieMellon are using SAM 3D to capture and analyze human movement in clinical settings, opening the doors to personalized, data-driven insights in the recovery process.
🔗 Learn more about SAM… pic.twitter.com/UkQyD2qLeVSAM 3D is helping advance the future of rehabilitation. See how researchers at @CarnegieMellon are using SAM 3D to capture and analyze human movement in clinical settings, opening the doors to personalized, data-driven insights in the recovery process. Learn more about SAM
-
Meta and ConservationX Launch SA-FARI Animal Dataset for Global Conservation
By
–
We partnered with @ConservationX to build the SA-FARI dataset with 10,000+ annotated videos including over 100 species of animals. We’re sharing this dataset to help with conservation efforts around the globe. Find it here:
-
SAM 3D: Extract 3D Objects from Images with Effects
By
–
— AI at Meta (@AIatMeta) 21 novembre 2025
So much fun! SAM 3D! You can extract a 3D object directly from an image！And add effects! x.com/AIatMeta/statu…
-
New Model Converts 2D Images to 3D Models With Textures Instantly
By
–
— AI at Meta (@AIatMeta) 21 novembre 2025
Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this
-
SAM3D Expected to Inspire Hundreds of Robotics Research Papers
By
–
— AI at Meta (@AIatMeta) 21 novembre 2025
My prediction: we’re about to see hundreds of robotics papers built on SAM3D. Waiting for the first one to drop SAM3 & SAM3D from @metaai are just too good to be true!
-
Getting Started with SAM 3D: Tips for Building Scenes
By
–
Here are a few tips to help you get started with SAM 3D in the Playground:
— AI at Meta (@AIatMeta) 21 novembre 2025
1️⃣ We encourage you to add multiple objects to build out a scene and apply effects to them to experience the full potential of SAM 3D.
2️⃣ When generating 3D models of multiple objects or people in a… pic.twitter.com/1ubiOwEzu6Here are a few tips to help you get started with SAM 3D in the Playground: We encourage you to add multiple objects to build out a scene and apply effects to them to experience the full potential of SAM 3D. When generating 3D models of multiple objects or people in a
-
Segment Anything Playground: Advanced Meta Segmentation Models SAM 3
By
–
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.
— AI at Meta (@AIatMeta) 21 novembre 2025
Check out some inspo and… pic.twitter.com/Deg7FXzI5CThe 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. Check out some inspo and
-
ExecuTorch Advances On-Device AI Across Meta Devices
By
–
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
-
SAM 3 Achieves 2x Performance with 4M Phrase Dataset
By
–
Collecting a high quality dataset with 4M unique phrases and 52M corresponding object masks helped SAM 3 achieve 2x the performance of baseline models. Kate, a researcher on SAM 3, explains how the data engine made this leap possible.
— AI at Meta (@AIatMeta) 20 novembre 2025
🔗 Read the SAM 3 research paper:… pic.twitter.com/gfCCBQUChlCollecting a high quality dataset with 4M unique phrases and 52M corresponding object masks helped SAM 3 achieve 2x the performance of baseline models. Kate, a researcher on SAM 3, explains how the data engine made this leap possible. Read the SAM 3 research paper: