# New Vision Papers From SJTU and KAUST Push Promptable Perception as Meta's SAM 3 and DINOv3 Run US National Lab Imaging

Shanghai Jiao Tong University claims the best RGB-only result for category-level 9D pose at NeurIPS 2026, and Berkeley Lab says Meta's open models cut one annotation task from a month to 15 minutes.

- Published: 2026-10-15T06:37:42.045Z
- Canonical: https://polylog.news/ai/2026-10-15/new-vision-papers-from-sjtu-and-kaust-push-promptable-percep
- 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), [AI Weekly](https://aiweekly.co/alerts/metas-sam-3-and-dinov3-power-doe-genesis-mission-pipeline)

Two research groups released perception work this week that changes how vision-language models hand spatial information to downstream modules. A team from Shanghai Jiao Tong University (SJTU) presented SchemaPose at NeurIPS 2026 and claims…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-15/new-vision-papers-from-sjtu-and-kaust-push-promptable-percep (subscription information: https://polylog.news/pricing).