In brief
What the paper does.
SP-VLA unifies model scheduling and token pruning for VLA acceleration, achieving 1.5× lossless speedup in LIBERO and 2.4× in SimplerEnv, with up to 6% average performance gain.
Cite
Cite the paper.
@inproceedings{li2026spvla,
title={{SP-VLA}: A Joint Model Scheduling and Token Pruning Approach for {VLA} Model Acceleration},
author={Li, Ye and Meng, Yuan and Sun, Zewen and Ji, Kangye and Tang, Chen and Fan, Jiajun and Ma, Xinzhu and Xia, Shu-Tao and Wang, Zhi and Zhu, Wenwu},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=RwdGIIjPlC}
}