Jiajun Fan

ICLR 2026

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

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.

Published in
International Conference on Learning Representations 2026 (ICLR 2026)
Paper
openreview.net/forum?id=RwdGIIjPlC

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}
}