# Berkeley Lab Runs Meta's SAM 3 and DINOv3 on 300 A100 GPUs to Label X-ray Scans in About 15 Minutes

New arXiv research on auditable human-agent teams for X-ray experiments addresses the harder problem: sustained autonomous operation of physical instruments.

- Published: 2026-11-11T06:08:31.146Z
- Canonical: https://polylog.news/ai/2026-11-11/berkeley-lab-runs-meta-s-sam-3-and-dinov3-on-300-a100-gpus-t
- 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/), [arXiv cs.AI](https://arxiv.org/abs/2611.12933), [AI Weekly](https://aiweekly.co/alerts/metas-sam-3-and-dinov3-power-doe-genesis-mission-pipeline)

Lawrence Berkeley National Laboratory leads SYNAPS-I, one of the first projects under the White House's Genesis Mission for AI-driven science. According to Meta, the project's segmentation pipeline uses two of Meta's open models. Segment An…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-11/berkeley-lab-runs-meta-s-sam-3-and-dinov3-on-300-a100-gpus-t (subscription information: https://polylog.news/pricing).