# Berkeley Lab Runs Meta's Open Vision Models Across 300 GPUs to Cut Beamline Analysis From a Month to Minutes

The SYNAPS-I project uses SAM 3 and DINOv3 on Department of Energy infrastructure, replacing expert image annotation that previously took weeks per dataset.

- Published: 2026-08-30T06:24:05.945Z
- Canonical: https://polylog.news/ai/2026-08-30/berkeley-lab-runs-meta-s-open-vision-models-across-300-gpus
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/), [Berkeley Lab News Center](https://newscenter.lbl.gov/2026/07/22/berkeley-lab-to-lead-13-new-genesis-mission-ai-projects/), [TechTimes](https://www.techtimes.com/articles/321456/20260724/meta-open-source-ai-cuts-doe-beamline-analysis-month-minutes.htm)

Lawrence Berkeley National Laboratory is running Meta's open vision models inside the Department of Energy's Genesis Mission, and has published the first results. The project, SYNAPS-I, runs with SLAC National Accelerator Laboratory and tar…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-30/berkeley-lab-runs-meta-s-open-vision-models-across-300-gpus (subscription information: https://polylog.news/pricing).