Why VLMs Miss Small Objects, and When Zooming In Is Safe
A theory built on two quantities of the image interface: S, the number of visual tokens across an object's side, and L, the content a call must cover, which concludes that recognition improves gradually with S, and any search strategy, zoom agents included, obeys a recall-cost frontier.
Jun-Zhe Shi, Yuan Gan, Shi-Da Jiang
· 0 citations