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.
Spikformer V2: join the high accuracy club on imagenet with an SNN ticket
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
baseline 1polarities
baseline 1representative citing papers
Uncert estimates token importance via temporal uncertainty statistics from Dirichlet-modeled class evidence to enable pruning in spiking transformers.
SVL pretraining enables SNNs to reach 85.4% top-1 accuracy on zero-shot 3D classification while outperforming prior SNNs on detection, segmentation, and action recognition with added open-world QA capability.
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
-
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.
-
SVL: Spike-based Vision-language Pretraining for Efficient 3D Open-world Understanding
SVL pretraining enables SNNs to reach 85.4% top-1 accuracy on zero-shot 3D classification while outperforming prior SNNs on detection, segmentation, and action recognition with added open-world QA capability.
-
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.