FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning

We propose $\mathbf{\text{FLAMES}}\mathbf{\text{(Fast}}\mathbf{\text{Long-range}}\mathbf{\text{Adaptive}}\mathbf{\text{Memory}}\mathbf{\text{for}}\mathbf{\text{Event-based}}\mathbf{\text{Systems)}}$, a novel hybrid framework integrating structured state-space dynamics with event-driven computation. At its core, the $\mathit{\text{Spike-Aware}}\mathit{\text{HiPPO}}\mathit{\text{(SA-HiPPO)}}\mathit{\text{mechanism}}$ 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 $\mathcal{O}(N^2)$ to $\mathcal{O}(Nr)$. 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.