AI RESEARCH

Geometric SSM: LTI State Space Models for Selective Tasks

arXiv CS.LG

ArXi:2505.17932v2 Announce Type: replace-cross A key claim in recent work on Selective State Space Models is that selectivity, the ability to focus on relevant information while filtering irrelevant inputs, requires breaking the Linear Time-Invariant (LTI) property through time-varying dynamics. We challenge this claim by nstrating that LTI systems can achieve selectivity when designed using principles from geometric control. We