<?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>训练技术 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E8%AE%AD%E7%BB%83%E6%8A%80%E6%9C%AF/</link><description>Recent content in 训练技术 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 11:14:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%AE%AD%E7%BB%83%E6%8A%80%E6%9C%AF/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM训练损失函数详解</title><link>https://guijiagi.com/posts/loss-function-llm-training/</link><pubDate>Thu, 02 Jul 2026 11:14:00 +0800</pubDate><guid>https://guijiagi.com/posts/loss-function-llm-training/</guid><description>从交叉熵到对比学习，系统梳理LLM训练中的各类损失函数及其作用</description></item><item><title>LLM蒸馏技术2026实践</title><link>https://guijiagi.com/posts/distillation-llm-2026/</link><pubDate>Thu, 02 Jul 2026 11:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/distillation-llm-2026/</guid><description>从Logit蒸馏到特征对齐，全面梳理大模型知识蒸馏的方法与实践</description></item></channel></rss>