We propose \textbf{FLAMES (Fast Long-range Adaptive Memory for Event-based Systems)}, a novel hybrid framework integrating structured state-space dynamics with event-driven computation. At its core, the \textit{Spike-Aware HiPPO (SA-HiPPO) mechanism} dynamically adjusts memory retention based on inter-spike intervals, preserving both short- and long-range dependencies. To maintain computational efficiency, we introduce a normal-plus-low-rank (NPLR) decomposition, reducing complexity from O(N2) to O(Nr). FLAMES achieves state-of-the-art results on the Long Range Arena benchmark and event datasets like HAR-DVS and Celex-HAR. By bridging neuromorphic computing and structured sequence modeling, FLAMES enables scalable long-range reasoning in event-driven systems.
@article{arxiv.2504.01257,
title = {FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning},
author = {Biswadeep Chakraborty and Saibal Mukhopadhyay},
journal= {arXiv preprint arXiv:2504.01257},
year = {2025}
}