<?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>原理 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%8E%9F%E7%90%86/</link><description>Recent content in 原理 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Sat, 27 Jun 2026 15:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%8E%9F%E7%90%86/index.xml" rel="self" type="application/rss+xml"/><item><title>对齐税Alignment Tax原理分析</title><link>https://guijiagi.com/posts/alignment-tax-analysis/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/alignment-tax-analysis/</guid><description>对齐税Alignment Tax原理分析</description></item><item><title>模型量化技术原理与实践</title><link>https://guijiagi.com/posts/model-quantization-principles/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/model-quantization-principles/</guid><description>模型量化技术原理与实践</description></item><item><title>Attention 机制详解：从 Self-Attention 到 Multi-Query Attention</title><link>https://guijiagi.com/posts/attention-mechanism-explained/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/attention-mechanism-explained/</guid><description>深入解析 Transformer Attention 机制的数学原理、变体演进与复杂度分析</description></item></channel></rss>