<?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>模型优化 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E4%BC%98%E5%8C%96/</link><description>Recent content in 模型优化 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>Thu, 02 Jul 2026 11:12:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E4%BC%98%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>嵌入层优化：从查找到计算</title><link>https://guijiagi.com/posts/embedding-layer-optimization/</link><pubDate>Thu, 02 Jul 2026 11:12:00 +0800</pubDate><guid>https://guijiagi.com/posts/embedding-layer-optimization/</guid><description>解析LLM嵌入层的优化策略，从查找表到矩阵分解与动态嵌入</description></item><item><title>微调 vs Prompt 工程：何时该选哪个？</title><link>https://guijiagi.com/posts/fine-tuning-vs-prompt/</link><pubDate>Wed, 24 Jun 2026 14:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/fine-tuning-vs-prompt/</guid><description>系统对比 Prompt 工程与微调的适用场景、成本、效果，提供决策矩阵和混合方案</description></item></channel></rss>