<?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>🏆 ICLR 2025 on Elon&#39;s AD Insight</title>
    <link>https://auto-driving-blog.pages.dev/tags/-iclr-2025/</link>
    <description>Recent content in 🏆 ICLR 2025 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>Thu, 30 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://auto-driving-blog.pages.dev/tags/-iclr-2025/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>论文精读｜DriveTransformer：统一Transformer——告别BEV，拥抱稀疏Token并行交互</title>
      <link>https://auto-driving-blog.pages.dev/posts/paper-reading/%E8%AE%BA%E6%96%87%E7%B2%BE%E8%AF%BB-drivetransformer/</link>
      <pubDate>Thu, 30 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://auto-driving-blog.pages.dev/posts/paper-reading/%E8%AE%BA%E6%96%87%E7%B2%BE%E8%AF%BB-drivetransformer/</guid>
      <description>DriveTransformer 彻底抛弃了 BEV 表示——不再构建稠密 BEV 特征，而是让任务 query 直接与原始传感器特征交互。三种注意力（Sensor Cross-Attention、Task Self-Attention、Temporal Cross-Attention）构成统一框架，支持单阶段端到端训练。在 Bench2Drive 闭环评测中以 63.46 Driving Score 大幅超越 UniAD（45.81）和 VAD（42.35），且在鲁棒性上碾压 BEV 方案。获 ICLR 2025 接收。</description>
    </item>
  </channel>
</rss>
