SpikingMoE adds LGN-inspired SDprompt routing to a spike-driven Transformer MoE, replacing MLPs with spike-compatible experts and reporting 94.09% top-1 on CIFAR-10 and 74.54% on CIFAR-100.
Differentiable spike: Rethinking gradient-descent for training spiking neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks
SpikingMoE adds LGN-inspired SDprompt routing to a spike-driven Transformer MoE, replacing MLPs with spike-compatible experts and reporting 94.09% top-1 on CIFAR-10 and 74.54% on CIFAR-100.