<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>[前馈式框架] on AI内参</title>
    <link>https://www.neican.ai/tags/%E5%89%8D%E9%A6%88%E5%BC%8F%E6%A1%86%E6%9E%B6/</link>
    <description>Recent content in [前馈式框架] on AI内参</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Wed, 27 May 2026 16:10:03 +0800</lastBuildDate>
    <atom:link href="https://www.neican.ai/tags/%E5%89%8D%E9%A6%88%E5%BC%8F%E6%A1%86%E6%9E%B6/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>超越“像素拼接”：VGGT-Edit如何让空间智能从“生成”迈向“编辑”</title>
      <link>https://www.neican.ai/insights/vggt-edit-20260527161003474-4/</link>
      <pubDate>Wed, 27 May 2026 16:10:03 +0800</pubDate>
      <guid>https://www.neican.ai/insights/vggt-edit-20260527161003474-4/</guid>
      <description>VGGT-Edit打破了传统3D编辑依赖2D图像处理的局限，通过残差场预测实现了秒级的原生3D语义编辑。这一技术突破不仅极大提升了空间重建的稳定性和效率，更为AR/VR、具身智能及空间计算的产业化落地提供了关键的技术基座。</description>
    </item>
  </channel>
</rss>
