ASTER: Adaptive Dynamic Layer-Skipping for Efficient Transformer Inference via Markov Decision Process

Fangxin Liu, Junjie Wang, Ning Yang, Zongwu Wang, Junping Zhao, Li Jiang, Haibing Guan

Published: 27 Oct 2025, Last Modified: 28 Feb 2026CrossrefEveryoneRevisionsCC BY-SA 4.0
Loading