SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
Published in International Conference on Learning Representations 2026 (ICLR 2026), 2026
Recommended citation: Ye Li, Yuan Meng, Zewen Sun, Kangye Ji, Chen Tang, Jiajun Fan, Xinzhu Ma, Shu-Tao Xia, Zhi Wang, Wenwu Zhu. "SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration." ICLR 2026. https://openreview.net/forum?id=RwdGIIjPlC
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.