<?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>机器人操作 on Elon&#39;s AD Insight</title>
    <link>https://auto-driving-blog.pages.dev/tags/%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%93%8D%E4%BD%9C/</link>
    <description>Recent content in 机器人操作 on Elon&#39;s AD Insight</description>
    <image>
      <title>Elon&#39;s AD Insight</title>
      <url>https://auto-driving-blog.pages.dev/images/share.png</url>
      <link>https://auto-driving-blog.pages.dev/images/share.png</link>
    </image>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Tue, 28 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://auto-driving-blog.pages.dev/tags/%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%93%8D%E4%BD%9C/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>论文精读｜LIBERO：面向终身机器人学习的知识迁移基准</title>
      <link>https://auto-driving-blog.pages.dev/posts/paper-reading/libero%E7%B2%BE%E8%AF%BB/</link>
      <pubDate>Tue, 28 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://auto-driving-blog.pages.dev/posts/paper-reading/libero%E7%B2%BE%E8%AF%BB/</guid>
      <description>LIBERO 是首个面向终身决策学习（LLDM）的机器人操作基准，包含 130 个语言条件任务和 4 个任务套件。它系统研究了五种知识迁移场景下的策略架构、终身学习算法、任务顺序、预训练效果等关键问题。一个反直觉的发现：简单的顺序微调在正向迁移上反而优于 EWC、ER 等经典终身学习方法。</description>
    </item>
  </channel>
</rss>
