Patrick Deschere

New video: Using vision-language models (like Qwen) to autonomously navigate and interact with ui elements. See the demo by ML Engineer Matvei Popov from @roboflow here: youtu.be/Y8CR6IzLDaw

This week's webinar: Build computer vision apps with Roboflow and your favorite AI assistant. Tony França from @roboflow will show how to connect our new MCP Server to Claude and automate tasks. Come hang out with us: luma.com/mt2k9yld

I've watched this video way too many times... What's going on here? This timelapse shows a Neural Architecture Search (NAS) training run in @roboflow. Instead of picking one model size, NAS explores thousands of architectures, so you can find the optimal speed and accuracy.

Or check out the video walkthrough here: youtu.be/4HlYG1MacRk

Vision Events is available in Roboflow now. You can ingest data via Workflows, API, or Edge Device Backup. Read the full announcement here: blog.roboflow.com/vision-events/

New in Roboflow: Vision Events A centralized, searchable record of your computer vision deployments.

Come meet the @roboflow RF-DETR team at @iclr_conf this afternoon: Pavilion 4, Poster 3616!

This week's live session: How to track objects in video with SORT and OC-SORT algorithms, presented by Lee Clement, Machine Learning Engineer at @roboflow. Come hang out with us: luma.com/pd4hodix

We are using @roboflow NAS for a client and found a model that improved latency by nearly 25% (6.8ms to 5.1ms) for roughly the same accuracy. @josephofiowa : This is looking good.

We're doing a live session about turning your model predictions into useful business intelligence in roboflow. Come hang out: luma.com/3j75p0zp

Using @roboflow and a finetuned @AIatMeta's SAM3 model we are able to open the door to much more analysis than what was once possible. Computer vision is advancing quickly