AIBullisharXiv โ CS AI ยท 7h ago7/10
๐ง
Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension
Researchers establish the first comprehensive theoretical framework for spiking transformers, proving their universal approximation capabilities and deriving tight spike-count lower bounds. Using effective dimension analysis, they explain why spiking transformers achieve 38-57ร energy efficiency on neuromorphic hardware and provide concrete design rules validated across vision and language benchmarks with 97% prediction accuracy.