# Meta's Open Vision Models Cut a Month of Scientific Image Segmentation to About 15 Minutes

SAM 3 and DINOv3, fine-tuned on experimental imaging data and run across 300 A100 GPUs, anchor a flagship project in the US Department of Energy's Genesis Mission.

- Published: 2026-10-01T06:20:51.871Z
- Canonical: https://polylog.news/ai/2026-10-01/meta-s-open-vision-models-cut-a-month-of-scientific-image-se
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/), [Meta AI](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/)

Meta described how its open-weight vision models are being used inside SYNAPS-I, a project under the US Department of Energy's Genesis Mission led by Lawrence Berkeley National Laboratory with Argonne, Brookhaven, Oak Ridge and SLAC. The pr…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-01/meta-s-open-vision-models-cut-a-month-of-scientific-image-se (subscription information: https://polylog.news/pricing).