https://vilab.team/tag/%E7%8A%B6%E6%80%81%E7%A9%BA%E9%97%B4%E6%A8%A1%E5%9E%8B/ 状态空间模型 Hugo Blox Builder (https://hugoblox.com)en-usSun, 19 Oct 2025 00:00:00 +0000 https://vilab.team/media/icon_hu2896232876136423579.png https://vilab.team/tag/%E7%8A%B6%E6%80%81%E7%A9%BA%E9%97%B4%E6%A8%A1%E5%9E%8B/ https://vilab.team/publication/efficient-spiking-point-mamba-for-point-cloud-analysis/ Sun, 19 Oct 2025 00:00:00 +0000 https://vilab.team/publication/efficient-spiking-point-mamba-for-point-cloud-analysis/ <p>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。</p> https://vilab.team/publication/semamil-semantic-reordering-with-retrieval-guided-state-spac/ Fri, 01 Aug 2025 00:00:00 +0000 https://vilab.team/publication/semamil-semantic-reordering-with-retrieval-guided-state-spac/ <p>本文针对全切片图像分类中多实例学习忽略上下文、Transformer计算复杂、状态空间模型打乱语义顺序的问题，提出SemaMIL方法。该方法包含语义重排模块，通过可逆置换将语义相似的图像块聚类排列；以及语义引导检索状态空间模块，选择代表性查询子集调整状态空间参数，实现高效全局建模。在四个WSI数据集上验证了方法的有效性。</p> https://vilab.team/publication/incomplete-multi-modal-brain-tumor-segmentation-via-learnabl/ Tue, 10 Jun 2025 00:00:00 +0000 https://vilab.team/publication/incomplete-multi-modal-brain-tumor-segmentation-via-learnabl/ <p>本文提出一种可学习排序状态空间模型（LS3M），用于不完整多模态脑肿瘤分割。该方法基于Mamba架构高效建模长距离依赖，并引入可微置换矩阵，根据模态特定特征对输入序列进行动态重排序，从而保留3D脑MRI中关键的空间归纳偏置与长程语义相关性。LS3M能够充分利用可用模态信息，提升分割性能。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/ Tue, 10 Jun 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/ <p>热烈祝贺张哲宇同学！论文《Incomplete multi-modal brain tumor segmentation via learnable sorting state space model》已发表在 <em>CVPR</em>。</p> <h2 id="incomplete-multi-modal-brain-tumor-segmentation-via-learnable-sorting-state-space-model">Incomplete multi-modal brain tumor segmentation via learnable sorting state space model</h2> <p><strong>祝贺张哲宇同学！该论文已发表在 <em>CVPR</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Incomplete multi-modal brain tumor segmentation via learnable sorting state space model" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu12446196012194697519.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu11624591397241064252.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu8784721236978794445.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu12446196012194697519.webp" width="760" height="210" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Zheyu Zhang、Yayuan Lu、Feipeng Ma、Yueyi Zhang、Huanjing Yue、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>CVPR</em></li> <li><strong>发表时间：</strong> 2025年6月10日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11094296/" target="_blank" rel="noopener">论文链接</a> · <a href="https://openaccess.thecvf.com/content/CVPR2025/papers/Zhang_Incomplete_Multi-modal_Brain_Tumor_Segmentation_via_Learnable_Sorting_State_Space_CVPR_2025_paper.pdf" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出一种可学习排序状态空间模型（LS3M），用于不完整多模态脑肿瘤分割。该方法基于Mamba架构高效建模长距离依赖，并引入可微置换矩阵，根据模态特定特征对输入序列进行动态重排序，从而保留3D脑MRI中关键的空间归纳偏置与长程语义相关性。LS3M能够充分利用可用模态信息，提升分割性能。</p>