Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative Decoding (SD) is a promising acceleration method which can be divided into two categories: drafter-based SD and retrieval-based SD. Each of the two methods demonstrates complementary advantages and limitations when applied to VLA models, leading to the hypothesis that a hybrid approach integrating these two methods will yield better performance. In this paper, we first conduct a series of detailed analyses to reveal the advantages and feasibility of hybrid utilization. However, even with the aforementioned key insights, implementing hybrid SD in VLA models presents several challenges: (1) draft rejection and persistent errors in retrieval-based SD; (2) difficulty in determining the hybrid boundary. To address these, we propose the HeiSD framework. We propose a retrieval-based SD optimization method in HeiSD, which contains a verify-skip mechanism and a sequence-wise relaxed acceptance strategy. Moreover, we proposed a kinematic-based fused metric in HeiSD to automatically determine the hybrid boundary. Experimental results demonstrate that HeiSD attains a speedup of up to 2.45x in simulation benchmarks and 2.06x~2.41x in real-world scenarios, while sustaining a high task success rate.
@article{arxiv.2603.17573,
title = {HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness},
author = {Zihao Zheng and Zhihao Mao and Sicheng Tian and Maoliang Li and Jiayu Chen and Xinhao Sun and Zhaobo Zhang and Xuanzhe Liu and Donggang Cao and Hong Mei and Xiang Chen},
journal= {arXiv preprint arXiv:2603.17573},
year = {2026}
}