<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>视觉语言模型 | 余天予</title><link>https://yutianyu.cn/zh/tag/%E8%A7%86%E8%A7%89%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/</link><atom:link href="https://yutianyu.cn/zh/tag/%E8%A7%86%E8%A7%89%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/index.xml" rel="self" type="application/rss+xml"/><description>视觉语言模型</description><generator>Wowchemy (https://wowchemy.com)</generator><language>zh-Hans</language><lastBuildDate>Thu, 14 May 2026 00:00:00 +0000</lastBuildDate><image><url>https://yutianyu.cn/media/icon_hu0ee3417c3693759e075e80aecf96b070_11607_512x512_fill_lanczos_center_3.png</url><title>视觉语言模型</title><link>https://yutianyu.cn/zh/tag/%E8%A7%86%E8%A7%89%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B/</link></image><item><title>Deep Pre-Alignment for VLMs</title><link/><pubDate>Thu, 14 May 2026 00:00:00 +0000</pubDate><guid/><description/></item><item><title>Cross-Modal Omni Interaction Modeling for Phrase Grounding</title><link/><pubDate>Thu, 01 Oct 2020 00:00:00 +0000</pubDate><guid/><description/></item></channel></rss>