real-time AI use cases for wearables and mobile are now possible we released RF-DETR nano, small and medium to give devs high accuracy models for low compute devices nano is 11 mAP higher and .17 ms faster than recent YOLO releases

🚀 300 signups in just 3 days! And we still have 2 weeks to go. Super excited that the #SensAI Hackademy team, together with @roboflow, will deliver one of our most practical and fun open lectures yet. 👉 In this hands-on workshop, you’ll learn how to: - Build a card detection

🌉 SF we are throwing a watch party of the first two episodes https://t.co/MotYBHMUrj Come hang out with the stars of the show 🤩 @thorwebdev from @elevenlabsio @kwindla from Daily and @pipecat_ai @josephofiowa from @roboflow Yorick the Robot Hand 🍿See you there!

detecting drones with RF-DETR tutorial stay tuned: https://t.co/6Iq051vC3P

we 💜 RMFG (And added more free GPU to your account. Let it rip)

RF-DETR, SOTA for object detection, was built by a team of 3 join the livestream to hear how we pulled that off

great initiative to get RF-DETR into RKNN Model Zoo, join in if this is something you'd want to build with

amazing how results can change by just using two open source libraries with the same model

Toolkit to fine-tune multimodal VLMs with a simple CLI and Python API, featuring ready-made recipes for Florence-2, PaliGemma 2, and Qwen2.5-VL

getting close to releasing the full video everything open source and available for you to build with

I can detect a shot, determine if it was made or missed, and mark it on the court

Working on a computer vision project for NHL with automatic player, puck, goalie and net detection to further automate some flows and interactivity Built a dataset model with Roboflow then using YOLO to track players and goals in real-time. Still early days but good progress!

🆕 Part 3 of our GPT-5 Coverage: GPT-5's Vision Checkup results, from Matvei Popov at @roboflow! https://t.co/FUyUkvZjg0 TLDR; it's the same as our existing SOTAs. GPT-5-Mini is particularly cost effective for a frontier VLM.

Our PageXML dataset is coming along nicely. Using @roboflow in our workflow because it's soooo much easier than doing this locally. (And they have really nice open-source policies/data/models). If you all want me to do a video/videos on using Roboflow, let me know.

From detecting defective tires to tracking trailers, @roboflow helps customers apply #ComputerVision across industries. See how they deliver speed and accuracy at scale with #IntelXeon processors and #GoogleCloud. https://t.co/ePyBn8cN2K

what player is that? in the upcoming supervision-0.27.0 release, you’ll be able to freely control text position, including applying custom offsets from the detection box supervision annotators are now so advanced, you can literally use them to create full visual content link:

visual AI running on glasses is the future zuck called this out in his personal super intelligence memo yesterday

autonomous metal fabrication factory being built robotics + AI unlocks huge opportunities

we basically did the same thing with DINOv2 and O365 to make RF-DETR

supervision, the open-source library I created 2 years ago, is crossing 30,000 stars on GitHub! thank you to everyone who helped me build this project! it took us 4,000+ commits, 1,000+ PRs and 100+ contributors to do it. link: https://t.co/xXMRaS3Guk

LocalAI 3.2 and 3.3 were released very quickly, TLDR: - 🔍 Object Detection! Just install the rfdetr-base model from @roboflow (🫶) in our gallery! - 🧩 All backends now are in our new Backend Gallery and are installed automatically - 📉 Smaller binary and container images