# Meta's Promptable Vision Models Move From Benchmarks Into Assistive Robot Arms

University of Pittsburgh researchers built wheelchair-mounted manipulation on Segment Anything and DINO, in the same week Berlin's IFA show made embodied AI its main theme.

- Published: 2026-09-10T06:24:02.019Z
- Canonical: https://polylog.news/ai/2026-09-10/meta-s-promptable-vision-models-move-from-benchmarks-into-as
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/), [Polylog editors](https://polylog.news)

Meta published an account of University of Pittsburgh researchers using its Segment Anything and DINO models to build assistive robotics for people with limited upper-body mobility. The technical point is the perception layer. Open-vocabula…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-10/meta-s-promptable-vision-models-move-from-benchmarks-into-as (subscription information: https://polylog.news/pricing).