A training-inference consistent framework for early exiting in language models with parallel decoding

International Journal of Machine Learning and Cybernetics 2026

View at publisher

Authors: Ziqian Zeng, Zelin Chen, Huiping Zhuang

DOI: 10.1007/s13042-025-02952-y

Cited by: 0

References: 41

Fields of Study & Subjects

Topic Modeling Natural Language Processing Techniques Advanced Neural Network Applications

References 41