NC-SSM：超越对角状态空间模型的非交换群跟踪

1. 12:00
   arXiv · Machine Learning Theory

   超越对角状态空间模型：精确非阿贝尔群追踪、可解性障碍与几何物理流形

   NC-SSM 提出非对角状态空间模型框架，突破 SSM 转换矩阵可交换性限制，基于 Aff_D 仿射变换群（导出长度 580,000x 优势）实现精确非阿贝尔群追踪。在 Dyck-2 上达 74.36%、深度 AST 范围追踪达 30.26%（p = 0.0081），死推误差 0.04°，并验证严格等距性是无损长程关联记忆的数学必要条件。代码与可复现基准已公开。

Current heat 9·Comparable peak 10（Oct 2）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.