AI RESEARCH
Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models
arXiv CS.AI
•
ArXi:2605.19150v1 Announce Type: cross State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured by their ability to model finite-state automaton (FSA) transitions, but come at a prohibitively high compute and memory cost. In contrast, most structured transition matrix forms are highly efficient both in runtime and memory consumption, but suffer from limited expressivity.