AI RESEARCH
BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning
arXiv CS.CV
•
ArXi:2604.23165v1 Announce Type: new Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two fundamental issues: the restricted information capacity of binary spike coding and the dense token interactions