<?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>灾难性遗忘 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E7%81%BE%E9%9A%BE%E6%80%A7%E9%81%97%E5%BF%98/</link><description>Recent content in 灾难性遗忘 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>Mon, 13 Jul 2026 04:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E7%81%BE%E9%9A%BE%E6%80%A7%E9%81%97%E5%BF%98/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型微调中的灾难性遗忘问题</title><link>https://guijiagi.com/posts/article-67/</link><pubDate>Mon, 13 Jul 2026 04:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/article-67/</guid><description>深入分析大模型微调中灾难性遗忘的成因、影响和缓解策略，涵盖正则化、回放、参数隔离等方法</description></item><item><title>LLM持续学习实践：让模型与时俱进</title><link>https://guijiagi.com/posts/continual-learning-llm/</link><pubDate>Thu, 02 Jul 2026 10:46:00 +0800</pubDate><guid>https://guijiagi.com/posts/continual-learning-llm/</guid><description>探讨大语言模型持续学习的方法、挑战与工程实践，防止灾难性遗忘</description></item><item><title>持续学习Continual Learning</title><link>https://guijiagi.com/posts/continual-learning/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/continual-learning/</guid><description>大模型持续学习的挑战与方案，在学新不忘旧的道路上探索实践路径</description></item></channel></rss>