← 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.
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.
Townsquare
Start a discussion in Townsquare.
More from this edition
- Apple Sues OpenAI, Alleging Former Engineers Stole Hardware Secrets for Its ChatGPT Devices
- Meta Starts Charging for Its Own Model With Muse Spark 1.1 and a New API
- Anthropic Returns Claude Fable 5 to Service and Proposes a Shared Jailbreak-Severity Scale
- Meta's Brain2Qwerty v2 Decodes Typed Sentences From Brain Scans at 61% Word Accuracy
- Cloudflare Splits AI Crawler Controls Into Search, Agent, and Training
- Meta Ships Muse Image and Previews Muse Video, Its First In-House Visual Models
- Musk and Altman Trade Barbs on X as Both Ship New Flagship Models
- Anthropic Publishes the Origin Story of Claude Code, Its Coding Agent
Comments
0No comments yet.