Bipolar Self-attention for Spiking Transformers

NeurIPSSpotlight2025

Authors
Shuai Wang, Malu Zhang, Jingya Wang, Dehao Zhang, Yimeng Shan, Jieyuan Zhang, Yichen Xiao, Honglin Cao, Haonan Zhang, Zeyu Ma, Yang Yang, Haizhou Li
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Harnessing the event-driven characteristic, Spiking Neural Networks (SNNs) present a promising avenue toward energy-efficient Transformer architectures…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

transformer attention efficient

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive