<?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>DP-SGD on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/dp-sgd/</link><description>Recent content in DP-SGD 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 10:26:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/dp-sgd/index.xml" rel="self" type="application/rss+xml"/><item><title>差分隐私在LLM中的应用：保护训练数据的新范式</title><link>https://guijiagi.com/posts/differential-privacy-llm/</link><pubDate>Thu, 02 Jul 2026 10:26:00 +0800</pubDate><guid>https://guijiagi.com/posts/differential-privacy-llm/</guid><description>深入探讨差分隐私技术在大语言模型训练和推理中的应用方法与最新进展</description></item></channel></rss>