Morning Edition · Sunday, August 16, 2026Published at 2:12 AM EDT · New York
SAM 3 and DINOv3, fine-tuned on scientific imaging and served across 300 A100 accelerators, now return fully segmented three-dimensional volumes to researchers at the beamline.

A United States Department of Energy project called SYNAPS-I is running Meta's open-weight SAM 3 and DINOv3 models to segment X-ray and neutron imaging data in near real time. Lawrence Berkeley National Laboratory leads the effort with Argo…
Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.
The Global Intelligence Brief stays free.
Part of a tracked trend
Open-Vocabulary, Promptable Vision Foundation Models
Vision foundation models shift to text-promptable, open-vocabulary detection, segmentation, and real-time tracking of arbitrary concepts, generalizing perception beyond fixed label sets across images and video and pushing open perception models toward production use.
Start a discussion in Townsquare.
More from this edition
Comments
0No comments yet.