Moving between speech and text across languages ↗
SeamlessM4T joins speech recognition, text translation, speech translation, and speech generation in one multilingual research model family.
Emerging · Meta AIOpen intelligence
Models, access, ideas to build on. A place to discover developments quickly, then stay with the questions that matter to you.
See the work.
Newest source publications first. These are source dates, not live activity.
Sketching music from words and melody ↗
MusicGen generates music from a text description and can use an input melody as an additional condition, providing a downloadable tool for research and creative prototyping.
Experimental · Meta AISAM 1: selecting an object with a point or a box ↗
The original 2023 Segment Anything release, now commonly called SAM 1, turns a click, box, or rough mask into an object segmentation, giving annotators and analysts an editable first pass across varied images.
Demonstrated · Meta AIPredicting a protein’s shape from its sequence ↗
ESMFold applies a protein language model to infer three-dimensional structure directly from an amino-acid sequence, with checkpoints and bulk prediction tools available to researchers.
Demonstrated · Meta Fundamental AI ResearchTranscribing speech on infrastructure you control ↗
Whisper provides downloadable speech-recognition models for transcription, language identification, translation into English, and caption-making without requiring a hosted speech service.
Demonstrated · OpenAIAdapting an image model to a visual practice ↗
Stable Diffusion's downloadable latent-diffusion weights and adaptation code allowed artists and developers to build local image generation, inpainting, fine-tuning, and LoRA workflows.
Demonstrated · CompVis and Stability AI ecosystemA local visual-inspection workbench ↗
Anomalib packages multiple anomaly-detection methods into a modular library for finding and localizing unusual regions in inspection images, with paths from experiments to optimized edge inference.
Experimental · Anomalib contributors and Open Edge PlatformA startup program is a relationship, not an outcome. ↗
NVIDIA Inception is a program through which startups can access technical resources and support.
Deployed · NVIDIAOhio’s shared supercomputer served thousands of learners and researchers. ↗
Ohio’s Legislative Service Commission reports that the Ohio Supercomputer Center served 9,725 clients from 2,345 organizations in FY 2024, including 65 academic institutions, and supported 209 courses teaching more than 6,750 students.
Deployed · Ohio Supercomputer Center / Ohio Legislative Service Commission