Introducing Ultralytics Platform. The ultimate end-to-end vision AI platform. 🚀
Deploying a great model is rarely the hard part. Operationalizing it is.
Most teams integrate up to six tools just to ship a single model. Each one introduces costly latency, significant budget overhead, and painful ambiguity when something breaks. 🧵
Ultralytics Platform solves this!
👉Get started:
https://t.co/rIGPAOASIC
Train Ultralytics YOLO26 on the KITTI dataset! 🚗
Detect cars, pedestrians, and cyclists in real-world driving environments, making it ideal for autonomous driving research, smart traffic monitoring, and urban mobility analysis applications.
Start training ➡️ https://t.co/gP8trnALAS
#Ultralytics #YOLO26 #AI #AutonomousDriving #MachineLearning
Apples counting in the production line with @ultralytics YOLO26🍏
The model has been fine-tuned on custom data, and although the dataset is not very large, it could be useful for the initial phase of work.
I'm considering creating a webpage to showcase all the demo use cases I've developed. Do you think this is worth pursuing, or would it be a waste of time?
Drop your thoughts in the comments below 👇👇👇
#apples #fruit #MachineLearning
#CVPR2026 - See you tomorrow! 🚀
We're excited to be exhibiting at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (@CVPR) in Denver!
Stop by our booth to learn about our latest research, including our new Ultralytics YOLO26 paper and experience live demos of cutting-edge vision AI.
📍 Booth 513
📅 June 5 - 7, 2026 | Colorado Convention Center, Denver
Learn more ➡️ https://t.co/UHdvAiJw2Q
Detect rusted vs healthy oil tanks with Ultralytics YOLO26!
Identify corrosion and surface damage in real time to support preventive maintenance, improve safety, and reduce risks in oil and gas operations.
Read more ➡️ https://t.co/6j9yMS0lcJ
#Ultralytics#YOLO26#OilAndGas #ComputerVision
Learn how Volley built an AI-powered racquet sports trainer. 🎾
Running Ultralytics YOLO11 on edge hardware across 250+ deployed units, volley monitors courts, tracks players, and detects the ball.
Read more ➡️ https://t.co/djeVxBLlmw
Ultralytics is heading to Edge AI London 🚀
Join Ultralytics and @Raspberry_Pi for a hands-on workshop exploring computer vision at the edge - from training to deployment on real hardware.
📍 London
📅 Workshop: June 9 | 3.40PM - 4.30PM
Learn more ➡️ https://t.co/wgEPVRIyfk
Pothole detection in real time using @ultralytics YOLO26 🕳️
Identify potholes accurately from images or video to support road maintenance, safety monitoring, and smart city infrastructure workflows.
More info👇
#AI#SmartCities#Ultralytics
I have been working on this for a very long time, finally it's live on Arxiv!
Introducing the long-awaited @Ultralytics YOLO26 paper: state-of-the-art real-time object detection, instance segmentation, image classification, keypoint detection, oriented bounding boxes detection and open-vocabulary detection models that run on any edge device 🔥
Meet me at @CVPR booth #513 if you have questions about the paper!
It was a lot of fun collaborating with my coauthors @arttestt and others.
Of course, it wouldn't be possible without the ultralytics package maintainers like @onuralpszr and rest of the team.
Auto-annotate datasets with SAM2.1 using Ultralytics Python package! 🧠
Generate segmentation labels automatically to speed up dataset creation, reduce manual labeling effort, and prepare high-quality data for training computer vision models.
Learn more ➡️ https://t.co/vSGTEkp9sO
#Ultralytics #Segmentation #Research
Introducing the research paper behind Ultralytics YOLO26.
For years, we've focused on building YOLO and getting it into the real world: into your products, your pipelines, your research. With YOLO26, we wanted to go a step further: we've published a research paper that shares the full story of how it works.
"Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models" covers:
✅Native NMS-free, end-to-end inference: no post-processing
✅DFL removal for a lighter, easier-to-export head
✅MuSGD, a hybrid optimizer adapted from LLM training
✅Progressive Loss + STAL for stronger small-object detection
✅One unified pipeline — detection, segmentation, pose, classification & OBB — plus YOLOE-26 for open-vocabulary, prompt-free inference
✅40.9–57.5 mAP on COCO at just 1.7–11.8 ms (T4 TensorRT)
A big thank you note to the authors who made it happen: Glenn Jocher, Jing Qiu, Mengyu Liu, Shuai Lyu, Fatih Akyon, and Muhammet Esat.
This community has shaped every version of YOLO, and this paper is our way of sharing back. Thank you for building alongside us. 💙
📰Read the paper and explore all our research → https://t.co/A8alH9g6Rl
Announcing SAHI v0.12 from a rooftop in Denver, where CVPR 2026 kicks off tomorrow 👌 One of our biggest releases yet:
• Up to 7x faster inference on large images, with batch inference and new postprocessing backends
• Open-vocabulary detection and segmentation: @ultralytics YOLOE, YOLO-World, YOLO26, GroundingDINO and more
• Torch-free core, so you install only what you need
• Docs now in English and 中文
Most of the heavy lifting on this one was done by @onuralpszr. Also big thanks to @muhammdrizwanmr plus everyone else who contributed.
At CVPR this week? Let's meet 😎
pip install -U sahi
Detect workers and monitor safety zones with Ultralytics YOLO26! 🦺
Identify workers while detecting entry into dangerous zones, helping construction teams improve compliance and reduce on-site risks.
Learn more ➡️ https://t.co/QV2EySNh9f
#Ultralytics#YOLO26#Construction#AI
Solar panels counting using @ultralytics YOLO26 🚀
Have you ever wondered how much electricity a house with 210+ solar panels can generate? I have used the YOLO26 for the detection of panels and Ultralytics Solutions for counting solar panels on a house roof. It's a great step toward analyzing electricity generation potential for entire communities.
More info 👇
#solar #plates #MachineLearning
Code 👇
""""""
from ultralytics import YOLO
# Load a YOLO26 model
model = YOLO("https://t.co/U2h0oBKE0p")
# Export the model to OpenVINO format
model.export(format="openvino") # creates 'yolo26n_openvino_model/'
# Load the exported OpenVINO model
ov_model = YOLO("yolo26n_openvino_model/")
# Run inference
results = ov_model("https://t.co/G8uMNtheVs")
# Run inference on a specific device, available devices: ["intel:gpu", "intel:npu", "intel:cpu"]
results = ov_model("https://t.co/G8uMNtheVs", device="intel:gpu")
""""""
Export Ultralytics YOLO26 models to OpenVINO for optimized inference! ⚡
Deploy on @Intel CPUs, GPUs, and edge devices with improved speed and efficiency, ideal for real-time AI applications and production deployments.
Learn more ➡️ https://t.co/YErrLvll6s
#Ultralytics #MachineLearning #Intel
From Annotation to Deployment: Building an Object Detection Pipeline with Geti™, Ultralytics YOLO26, and @Intel OpenVINO™ 🚀
Building production-ready computer vision pipelines doesn’t have to be complex. Learn how to design, train, optimize, and deploy object detection models for real-world manufacturing and industrial use cases.
📅 June 10, 2026 | 10:00AM - 11:00AM PT
📍 Online
Register now ➡️ https://t.co/cR2nEZwUWi