LongSpike integrates fractional-order state-space modeling into spiking neural networks, enabling better long-sequence performance than prior SNNs on LRA, WikiText-103, and Speech Commands benchmarks while retaining sparse computation.
Spikformer v2: Join the high accuracy club on imagenet with an snn ticket
5 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
5
Pith papers citing it
12
external citations · external index
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Spiking attention is a universal approximator of permutation-equivariant functions with ε-approximation requiring Ω(L_f² nd / ε²) spikes, but low effective dimensions (47-89) allow T=4 timesteps in practice.
Uncert estimates token importance via temporal uncertainty statistics from Dirichlet-modeled class evidence to enable pruning in spiking transformers.
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.
citing papers explorer
-
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
LongSpike integrates fractional-order state-space modeling into spiking neural networks, enabling better long-sequence performance than prior SNNs on LRA, WikiText-103, and Speech Commands benchmarks while retaining sparse computation.
-
Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension
Spiking attention is a universal approximator of permutation-equivariant functions with ε-approximation requiring Ω(L_f² nd / ε²) spikes, but low effective dimensions (47-89) allow T=4 timesteps in practice.
-
Uncertainty-Aware Token Importance Estimation in Spiking Transformers
Uncert estimates token importance via temporal uncertainty statistics from Dirichlet-modeled class evidence to enable pruning in spiking transformers.
-
Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.
- SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding