<?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>📐 数据效率 on Elon&#39;s AD Insight</title>
    <link>https://auto-driving-blog.pages.dev/tags/-%E6%95%B0%E6%8D%AE%E6%95%88%E7%8E%87/</link>
    <description>Recent content in 📐 数据效率 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>Fri, 24 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://auto-driving-blog.pages.dev/tags/-%E6%95%B0%E6%8D%AE%E6%95%88%E7%8E%87/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>论文精读｜NoRD：无需推理的高效数据驱动 VLA</title>
      <link>https://auto-driving-blog.pages.dev/posts/paper-reading/nord%E7%B2%BE%E8%AF%BB/</link>
      <pubDate>Fri, 24 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://auto-driving-blog.pages.dev/posts/paper-reading/nord%E7%B2%BE%E8%AF%BB/</guid>
      <description>NoRD 挑战 VLA 对大规模数据和推理标注的依赖，仅用 60% 数据 + 零推理标注即可达到可比性能。核心发现是标准 GRPO 在弱策略上由于难度偏差（Difficulty Bias）失效，引入 Dr.GRPO 后从 0.67% 提升扭转为 11.68% 的显著增益。</description>
    </item>
  </channel>
</rss>
