# Berkeley Lab Runs Meta's SAM 3 and DINOv3 in a Five-Lab X-Ray and Neutron Pipeline Under the Genesis Mission

A grapevine micro-CT analysis that took a month per time step now takes about 15 minutes on 300 A100 GPUs at the National Energy Research Scientific Computing Center.

- Published: 2026-10-18T06:13:15.484Z
- Canonical: https://polylog.news/ai/2026-10-18/berkeley-lab-runs-meta-s-sam-3-and-dinov3-in-a-five-lab-x-ra
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/), [AI Weekly](https://aiweekly.co/alerts/metas-sam-3-and-dinov3-power-doe-genesis-mission-pipeline), [OpenSourceForU](https://www.opensourceforu.com/2026/07/meta-open-weight-ai-cuts-science-analysis-to-15-minutes/), [Runtime Wire](https://runtimewire.com/article/berkeley-lab-meta-models-doe-genesis-mission)

Lawrence Berkeley National Laboratory leads SYNAPS-I (SYnergistic Neutron And Photon Science - Intelligence), a multi-lab Department of Energy (DOE) initiative with Argonne, Brookhaven, Oak Ridge and SLAC. Its goal is to cut the analysis of…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-18/berkeley-lab-runs-meta-s-sam-3-and-dinov3-in-a-five-lab-x-ra (subscription information: https://polylog.news/pricing).