<?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>🤖 EmbodiedGPT on Elon&#39;s AD Insight</title>
    <link>https://auto-driving-blog.pages.dev/tags/-embodiedgpt/</link>
    <description>Recent content in 🤖 EmbodiedGPT 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/-embodiedgpt/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>论文精读｜EmbodiedGPT：基于具身思维链的视觉-语言预训练</title>
      <link>https://auto-driving-blog.pages.dev/posts/paper-reading/embodiedgpt%E5%85%B7%E8%BA%AB%E6%80%9D%E7%BB%B4%E9%93%BE%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/embodiedgpt%E5%85%B7%E8%BA%AB%E6%80%9D%E7%BB%B4%E9%93%BE%E7%B2%BE%E8%AF%BB/</guid>
      <description>EmbodiedGPT 是由中国科学院上海AI实验室、香港大学等机构提出的端到端多模态具身基础模型，通过创新的&amp;rsquo;具身思维链&amp;rsquo;（Embodied Chain of Thought）范式，将视觉-语言预训练与具身规划紧密结合。该模型构建了大规模EgoCOT数据集，实现了从高层规划到低层控制的闭环系统，在具身规划、控制、视频描述和视觉问答等多个任务上取得了优异性能。</description>
    </item>
  </channel>
</rss>
