AI RESEARCH
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
arXiv CS.LG
•
ArXi:2603.01581v2 Announce Type: replace-cross Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an optimization strategy that can boost inference speed. Two key issues emerge when integrating VLA and SD: first, SD relies on re-inference to address token errors, which is computationally expensive; second, to mitigate token errors, the acceptance threshold in SD requires careful adjustment. Existing works fail to address the above two issues effectively.