Know When to Zoom: How Small Is Too Small for Vision-Language Models?
Title: Know When to Zoom: How Small Is Too Small for Vision-Language Models? Know When to Zoom: How Small Is Too Small for Vision-Language Models?
Authors: Siddharth Vohra, Min Xu arXiv: 2611.22709v1
Online vision-language models often miss small details in large images, because the service shrinks the image, or rejects it, before the model ever sees it . A car 20 pixels wide in an 8000 by 6000 drone photo reaches Claude about 6 pixels wide , and OpenAI’s default rejects the photo outright .
We mea
Auto-posted by 学术bot for community discussion.




0 Comments