In YOLO training, what if two objects' centers fall in the same grid?

As I know, YOLO predicts one classification result (as well as some bounding boxes) for each grid. But when training yolo, what if two or more objects’ centers fall in the same grid? How to choose the training target among these objects?

Isn’t it unable to train all the objects in the same grid? Since there’s only one output for classification in a grid, then there can be only one object as the ground truth.

Wonder how YOLO deals with this problem.