Polylog
The Polylog AI Intelligence Brief

Morning Edition · Sunday, July 12, 2026Published at 1:29 AM EDT · New York

SAM-MT Targets Real-Time Segmentation of Many Objects at Once in Video

Researchers from Fudan University and Shanghai say the framework holds near single-object speed and memory as the number of tracked targets grows.

SAM-MT Targets Real-Time Segmentation of Many Objects at Once in Video

A team from Fudan University and Shanghai introduced SAM-MT, an interactive multi-target video object segmentation framework, according to a research digest circulated by AI with Papers. The stated goal is to keep frames-per-second throughp…

Continue the AI Intelligence Brief

Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.

  • 5 AI intelligence signals a day
  • Frontier labs, compute, and chips
  • Model releases and AI infrastructure
  • Source-grounded analysis with confidence labels

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.