KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models

arXiv:2603.01581v2 Announce Type: replace-cross Abstract: 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. Meanwhile, as the bridge between AI and the physical world, existing embodied intelligence has overlooked the application of robotic kinematics. To address these issues, we innovatively combine token-domain VLA models with kinematic-domain prediction for SD, proposing a kinematic-rectified SD framework named KERV. We employ a kinematics-based Kalman Filter to predict actions and compensate for SD errors, avoiding costly re-inference. Moreover, we design a kinematics-based adjustment strategy to dynamically rectify the acceptance threshold, addressing the difficulty of threshold determination. Experimental results across diverse tasks and environments demonstrate that KERV achieves 27%~37% acceleration with nearly no Success Rate loss.

Related

• HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
• Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
• A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
• 2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
• Stable Language Guidance for Vision-Language-Action Models
• VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping

Source: arXiv cs.LG | 2026-04-28