arXiv cs.NE
· Papers
TEFormer: Structured Bidirectional Temporal Enhancement Modeling in Spiking Transformers
arXiv:2601.18274v2 Announce Type: replace Abstract: In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence modeling. However, existing Spiking Transformers still lack a principled mechanism for effec