logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Efficient state space model via fast tensor convolution and block diagonalization

delete2026-08-18
delete0
PRE
AI
T
Tongyi Liang
H
Han‐Xiong Li *
DOI：10.1016/j.knosys.2026.116691delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
<ul class="list"> <li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content"> <div class="u-margin-s-bottom" id="d1e2034"> Proposed eSSM, a novel MIMO state space layer for efficient long-sequence modeling. </div></span></li> <li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content"> <div class="u-margin-s-bottom" id="d1e2039"> eSSM reduces parameters via diagonalization, convolution, and bidirectional kernels. </div></span></li> <li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content"> <div class="u-margin-s-bottom" id="d1e2044"> eSSM matches SOTA accuracy with far fewer parameters and shorter training. </div></span></li> </ul>
Keywords:
Deep learning
Neural networks
State space models
Sequence modeling

Journal

K
Knowledge-Based Systems
IF:
7.6
Papers:
1.2W
Citations:
4.5W

Organization

No organization information available