TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

VQA and Image Chunking for MLLMs (GPT-4V and Gemini)

1 点作者 joanfihu大约 1 年前

1 comment

joanfihu大约 1 年前
Handling large images with resolutions higher than 2048x2048 remains a challenge for MLLMs.<p>Image chunking splits large images into multiple smaller images. Then the model processes each image and uses information from all of them to answer a question.<p>I managed to get it to work with a 3840px X 20294px web page screenshot. It also works with documents that have figures (tables, charts, illustrations, etc).