# Meta's Open DINO and SAM Vision Models Run Department of Energy Beamline Analysis and a Pittsburgh Assistive Robot

Berkeley Lab says segmentation that took a month of expert work per time step now takes about 15 minutes, and a new adapter called ElasticDino aims to give DINO features pixel-level resolution.

- Published: 2026-11-15T06:27:29.039Z
- Canonical: https://polylog.news/ai/2026-11-15/meta-s-open-dino-and-sam-vision-models-run-department-of-ene
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI (Genesis Mission)](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/), [Meta AI (University of Pittsburgh)](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/), [Polylog editors](https://polylog.news)

Lawrence Berkeley National Laboratory leads SYNAPS-I, one of the first projects under the Department of Energy (DOE) Genesis Mission. The project's segmentation pipeline runs on two Meta foundation models, Segment Anything Model 3 (SAM 3) a…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-15/meta-s-open-dino-and-sam-vision-models-run-department-of-ene (subscription information: https://polylog.news/pricing).