<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>多模态模型 on AI 早报</title><link>https://ai-news.example.com/tags/%E5%A4%9A%E6%A8%A1%E6%80%81%E6%A8%A1%E5%9E%8B/</link><description>Recent content in 多模态模型 on AI 早报</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Tue, 07 Jul 2026 09:50:10 +0800</lastBuildDate><atom:link href="https://ai-news.example.com/tags/%E5%A4%9A%E6%A8%A1%E6%80%81%E6%A8%A1%E5%9E%8B/feed.xml" rel="self" type="application/rss+xml"/><item><title>[EN] Google发布ScreenAI：面向UI与信息图的视觉语言模型</title><link>https://ai-news.example.com/articles/en-googlescreenaiui/</link><pubDate>Tue, 07 Jul 2026 09:50:10 +0800</pubDate><guid>https://ai-news.example.com/articles/en-googlescreenaiui/</guid><description>Google Research推出ScreenAI，一种基于PaLI架构并融合pix2struct灵活分块策略的视觉语言模型，专为理解用户界面和信息图设计。该模型仅5B参数，在WebSRC、MoTIF等UI及信息图任务上达到最先进水平，并在Chart QA、DocVQA等任务上同类最佳。</description></item></channel></rss>