Spiking Neural Networks (SNNs) provide an energy-efficient paradigm for visual recognition. We present SpikingMoE, which integrates a spike-driven Transformer with a Mixture-of-Experts (MoE) framework for dynamic computation. Inspired by the lateral geniculate nucleus (LGN), a spike-driven prompt (SDprompt) enables input-dependent expert routing in a biologically plausible manner. By replacing standard MLPs with spike-compatible expert modules and enforcing binary spike communication, SpikingMoE is designed for neuromorphic hardware. Experiments on CIFAR-10 and CIFAR-100 achieve 94.09% and 74.54% top-1 accuracy, showing that modular expert routing can be incorporated while retaining reasonable performance. To our knowledge, SpikingMoE is the first open-source SNN framework that integrates MoE into a spike-driven Transformer with LGN-inspired routing.
@article{arxiv.2605.23188,
title = {SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks},
author = {Yukai Yang and Chenxi Qin and Jungang Li and Xin Zhang and Wenwei Shao and Liqun Chen},
journal= {arXiv preprint arXiv:2605.23188},
year = {2026}
}