Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration

Zhengyang Zhuge; Peisong Wang; Xingting Yao; Jian Cheng

2024 ICML ICML 2024

Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference Acceleration

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Zhengyang Zhuge, Peisong Wang, Xingting Yao, Jian Cheng

Topics

Machine Learning > Application Areas > Efficient Computing Deep Learning > Architectures > Transformers Deep Learning > Optimization & Theory > Efficient Computing

Keywords

spiking transformer token sparsification dual alignment inter alignment intra alignment timestep-wise anchor token

Download PDF