YOLO is a family of popular single-stage object detection models known for their speed and accuracy in real-time detection tasks. “You Only Look Once” means the model predicts bounding boxes and class probabilities for objects in an image in a single forward pass of the network, rather than region-by-region or in multiple stages​YOLO reframes object detection as a direct regression problem: it divides the image into a grid and, in one evaluation, outputs predictions for object bounding boxes and their classes for each region. This design makes YOLO extremely fast compared to two-stage detectors like R-CNN. Over successive versions (YOLOv1 through YOLOv8 and beyond), the architecture and training techniques have improved, yielding state-of-the-art results in object detection​YOLO models are widely used in applications requiring real-time processing, such as autonomous driving or live video analytics, where the benefit of detecting objects “all at once” is crucial.