Think twice, act once: Token-aware compression and action reuse for efficient inference in vision-language-action models

SSRN Electronic Journal 2026 Preprint Open access

Read full text
Authors: Xudong Tan, Yaoxin Yang, Hancheng Ye, Jialin Zheng, Bizhe Bai, Xinyi Wang, Dongzhan Zhou, Chenxi Li, Jia Hao, Tao Chen
DOI: 10.2139/ssrn.7397683
Cited by: 0

Fields of Study & Subjects

Multimodal Machine Learning Applications Advanced Neural Network Applications Semantic Web and Ontologies

Publication details

Journal / source
SSRN Electronic Journal
Publication date
1 January 2026
Language
EN
Document type
Preprint