<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Layernorm on 111qqz's blog</title><link>https://111qqz.com/en/tags/layernorm/</link><description>Recent content in Layernorm on 111qqz's blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>hust.111qqz@gmail.com (111qqz)</managingEditor><webMaster>hust.111qqz@gmail.com (111qqz)</webMaster><copyright>© 2011-2026 111qqz</copyright><lastBuildDate>Sat, 19 Sep 2026 16:00:00 +0800</lastBuildDate><atom:link href="https://111qqz.com/en/tags/layernorm/index.xml" rel="self" type="application/rss+xml"/><item><title>Attention 之后还缺什么：从 Residual Connection 到 Transformer Stack</title><link>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-09-19-transformer-block-residual-stream/</link><pubDate>Sat, 19 Sep 2026 16:00:00 +0800</pubDate><author>hust.111qqz@gmail.com (111qqz)</author><guid>https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-09-19-transformer-block-residual-stream/</guid><description>&lt;p&gt;&lt;a href="https://111qqz.com/en/post/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/2026-09-19-multi-head-attention/" &gt;上一篇&lt;/a&gt;结尾我写：Multi-Head Attention 仍然只是一个 information routing / read mechanism，一个完整的 Transformer layer 还包含 FFN、residual connection、layer normalization 等组件。&lt;/p&gt;</description></item></channel></rss>