IREX Unveils StreamVLM for Public Safety Video Analytics

Sep 11, 2026
StreamVLM lets public safety operators create video detectors by describing events or conditions in plain language. It works with existing camera networks and supports live alerts, investigations, and audit controls.

IREX unveiled StreamVLM, a vision language model detection engine that converts plain language descriptions into video analytics detectors, the company said in a press release. The cloud based system works across existing camera networks used by public safety agencies, local governments, and transportation authorities.

Operators can create detectors for conditions such as a person lying on the ground, flooding in an underpass, or graffiti appearing on a wall. StreamVLM evaluates selected frames from live camera feeds and sends alerts based on a confidence threshold, alert cooldown, and event type. Multiple detectors can run on one camera channel and can be changed without taking the system offline.

The platform logs detector creation, edits, and activation under the responsible operator. It also records prompts, uses role based access, and requires a Case ID for investigations.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

Guide
AI interconnect and networking startups

AI interconnect and networking startups

29 private startups developing the chips, optical switches and memory fabrics that move data through AI infrastructure.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.