<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Qwen3-VL on Yuxuan Tang</title><link>https://tyxkk2.me/tags/qwen3-vl/</link><description>Recent content in Qwen3-VL on Yuxuan Tang</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Sat, 16 May 2026 20:53:01 +0800</lastBuildDate><atom:link href="https://tyxkk2.me/tags/qwen3-vl/index.xml" rel="self" type="application/rss+xml"/><item><title>Qwen3-VL</title><link>https://tyxkk2.me/posts/qwen3-vl/</link><pubDate>Sat, 16 May 2026 20:53:01 +0800</pubDate><guid>https://tyxkk2.me/posts/qwen3-vl/</guid><description>A model note on Qwen3-VL: long-context vision-language modeling, video understanding, and multimodal agent ability.</description></item></channel></rss>