YOLO (You Only Look Once)

YOLO (You Only Look Once) is a family of single-stage, real-time object-detection models that predict bounding boxes and class probabilities in one forward pass of the network — trading a little accuracy for speed.

From the original 2016 paper to today's Ultralytics releases (YOLOv8, YOLO11) and open-vocabulary variants like YOLO-World, the YOLO family is the most widely used real-time object detector in computer vision. Here is our latest reporting and guides across YOLO versions, benchmarks, and how to choose one.