SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.12895 · 2026

LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning

Zheng-Jun Zha, Qiyu Kang, Xuhao Li, Xinrui He

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
xinruihe389-commits/LongSpike canonical 6 of 6
FunctionStatusWhere it lives
convert_a Ran xinruihe389-commits/LongSpike/checkpoints/convert_v3_to_v4.py
pointer only (licence: NOASSERTION) · get_code("c7ff13e906b45325")
convert_dt Ran xinruihe389-commits/LongSpike/checkpoints/convert_v3_to_v4.py
pointer only (licence: NOASSERTION) · get_code("a8e0252edc7e4667")
convert_kernel Ran xinruihe389-commits/LongSpike/checkpoints/convert_v3_to_v4.py
pointer only (licence: NOASSERTION) · get_code("d16920138a7346bd")
dequantize Ran xinruihe389-commits/LongSpike/src/dataloaders/audio.py
pointer only (licence: NOASSERTION) · get_code("ce310b19a858070f")
minmax_scale Ran xinruihe389-commits/LongSpike/src/dataloaders/audio.py
pointer only (licence: NOASSERTION) · get_code("1b76e4737067023f")
quantize Ran xinruihe389-commits/LongSpike/src/dataloaders/audio.py
pointer only (licence: NOASSERTION) · get_code("1631cd936e9b1a90")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Spiking Neural Networks (SNNs) are well-regarded for their biological plausibility and energy efficiency in processing sequential data. However, dominant SNN architectures typically rely on first-order Ordinary Differential Equations (ODEs) to govern neuronal state transitions. This first-order assumption imposes a "memoryless" bottleneck, limiting the model's capacity to capture the complex, long-range dependencies inherent in long-sequence tasks. In this work, we propose LongSpike, a novel SNN framework that integrates fractional-order State-Space Modeling (f -SSM) from control theory into the spiking domain. By extending traditional integer-order SSMs to the fractional-calculus regime, LongSpike enables the hierarchical integration of neuronal dynamics with long-memory kernels. To mitigate the computational overhead and parallelization challenges typically associated with fractional operators, we leverage a state-space formulation that supports efficient, parallel training. Empirical evaluations on challenging benchmarks, including Long Range Arena (LRA), large-scale WikiText-103, and Speech Commands, demonstrate that LongSpike outperforms state-of-the-art SNNs in accuracy while preserving sparse synaptic computation. The code is available at https://github.com/xinruihe389-commits/LongSpike.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.12895")
get_code_for_paper("2606.12895")
have("2606.12895")

Connect an agent — have() is free.