Morning Edition · Monday, September 28, 2026Published at 2:48 AM EDT · New York

Berkeley Lab Cuts Beamline Annotation From a Month to 15 Minutes Using Meta's Open Vision Models

The SYNAPS-I project pairs DINOv3 features with SAM 3 segmentation across 300 A100 graphics processors, while the University of Pittsburgh runs the same models on-device in an assistive wheelchair funded by up to $41.5 million.

Meta's closed turn on language models has not extended to perception, and two deployments show where the open vision stack is landing. Lawrence Berkeley National Laboratory leads SYNAPS-I, a multi-laboratory project with SLAC under the Depa…