<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Mamba | ViLab</title>
    <link>https://vilab.team/tag/mamba/</link>
      <atom:link href="https://vilab.team/tag/mamba/index.xml" rel="self" type="application/rss+xml" />
    <description>Mamba</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 19 Oct 2025 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>Mamba</title>
      <link>https://vilab.team/tag/mamba/</link>
    </image>
    
    <item>
      <title>Efficient spiking point mamba for point cloud analysis</title>
      <link>https://vilab.team/publication/efficient-spiking-point-mamba-for-point-cloud-analysis/</link>
      <pubDate>Sun, 19 Oct 2025 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/efficient-spiking-point-mamba-for-point-cloud-analysis/</guid>
      <description>&lt;p&gt;本文提出 Spiking Point Mamba (SPM)，这是首个将 Mamba 引入三维点云分析的脉冲神经网络。针对直接适配 Mamba 时存在的时序动态不匹配和脉冲引起的信息损失问题，作者设计了层次动态编码 (HDE) 以增强动态时序建模，并提出 Spiking Mamba Block (SMB) 来学习跨时间步特征并减少脉冲信息丢失。此外，采用非对称 SNN 训练策略进一步提升性能。SPM 可作为高效骨干网络，适用于点云分类、部件分割与重建等任务。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
