<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>UI Understanding on AI 早报</title><link>https://ai-news.example.com/tags/ui-understanding/</link><description>Recent content in UI Understanding on AI 早报</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Mon, 06 Jul 2026 23:17:03 +0800</lastBuildDate><atom:link href="https://ai-news.example.com/tags/ui-understanding/feed.xml" rel="self" type="application/rss+xml"/><item><title>[EN] ScreenAI：谷歌发布针对UI和信息图表的视觉语言模型</title><link>https://ai-news.example.com/articles/en-screenaiui/</link><pubDate>Mon, 06 Jul 2026 23:17:03 +0800</pubDate><guid>https://ai-news.example.com/articles/en-screenaiui/</guid><description>Google Research 推出了 ScreenAI，一个仅 5B 参数的视觉语言模型，专门用于理解用户界面和信息图表。该模型基于 PaLI 架构与 pix2struct 的灵活分块策略，在多个基准测试中取得领先结果，并配套发布了三个新数据集以评估布局理解与问答能力。</description></item></channel></rss>