# Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance

arXiv: https://arxiv.org/abs/2507.22424 · HTML: https://mlsanity.com/paper/2507.22424/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)
- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)
- Efficient LLM inference and serving / [Fast autoregressive visual generation](https://mlsanity.com/inference/fast-autoregressive-visual-generation/)

## Builds on (most cited first, 30 of 30)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution](https://mlsanity.com/paper/2411.02359/) (2024)
- [What Can RL Bring to VLA Generalization? An Empirical Study](https://mlsanity.com/paper/2505.19789/) (2025)
- [RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation](https://mlsanity.com/paper/2406.04339/) (2024)
- [PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding](https://mlsanity.com/paper/2503.02310/) (2025)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [Learning Harmonized Representations for Speculative Sampling](https://mlsanity.com/paper/2408.15766/) (2024)
- [Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting](https://mlsanity.com/paper/2404.18911/) (2024)
- [LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding](https://mlsanity.com/paper/2410.03355/) (2024)
- [MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric](https://mlsanity.com/paper/2403.07839/) (2024)
- [RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model](https://mlsanity.com/paper/2409.19590/) (2024)
- [Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control](https://mlsanity.com/paper/2412.01034/) (2024)
- [RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors](https://mlsanity.com/paper/2412.10713/) (2024)
- [Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration](https://mlsanity.com/paper/2412.00061/) (2024)
- [LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models](https://mlsanity.com/paper/2502.06352/) (2025)
- [Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation](https://mlsanity.com/paper/2405.18688/) (2024)

## Built on by (most cited first, 30 of 32)

- [Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2508.13073/) (2025)
- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey](https://mlsanity.com/paper/2510.17111/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models](https://mlsanity.com/paper/2603.07904/) (2026)
- [KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models](https://mlsanity.com/paper/2603.01581/) (2026)
- [DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation](https://mlsanity.com/paper/2602.22896/) (2026)
- [Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs](https://mlsanity.com/paper/2605.13778/) (2026)
- [Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment](https://mlsanity.com/paper/2604.24447/) (2026)
- [ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge](https://mlsanity.com/paper/2512.20276/) (2025)
- [HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness](https://mlsanity.com/paper/2603.17573/) (2026)
- [Experiences from Benchmarking Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2511.11298/) (2025)
- [TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control](https://mlsanity.com/paper/2601.14945/) (2026)
- [Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA](https://mlsanity.com/paper/2604.02965/) (2026)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model](https://mlsanity.com/paper/2603.18091/) (2026)
- [Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2607.07608/) (2026)
- [When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding](https://mlsanity.com/paper/2511.01282/) (2025)
- [ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models](https://mlsanity.com/paper/2603.17850/) (2026)
- [Dynamic Execution Commitment of Vision-Language-Action Models](https://mlsanity.com/paper/2605.11567/) (2026)
- [Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models](https://mlsanity.com/paper/2606.15285/) (2026)
- [PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models](https://mlsanity.com/paper/2606.22540/) (2026)
- [CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention](https://mlsanity.com/paper/2608.04396/) (2026)
- [Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action Model](https://mlsanity.com/paper/2602.18813/) (2026)
- [Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think](https://mlsanity.com/paper/2606.20246/) (2026)
- [Draft-and-Target Sampling for Video Generation Policy](https://mlsanity.com/paper/2603.13438/) (2026)
- [VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success](https://mlsanity.com/paper/2604.05323/) (2026)
- [Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference](https://mlsanity.com/paper/2608.04428/) (2026)
- [WA-SpecDec: World-Aware Speculative Decoding for Vision-Language-Action Models](https://mlsanity.com/paper/2608.08725/) (2026)
- [Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification](https://mlsanity.com/paper/2608.15636/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. While Speculative Decoding (SD) has shown efficacy in accelerating Large Language Models (LLMs) by incorporating efficient drafting and parallel verification, allowing multiple tokens to be generated in one forward pass, its application to VLA models remains unexplored. This work introduces Spec-VLA, an SD framework designed to accelerate VLA models. Due to the difficulty of the action prediction task and the greedy decoding mechanism of the VLA models, the direct application of the advanced SD framework to the VLA prediction task yields a minor speed improvement. To boost the generation speed, we propose an effective mechanism to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model. Empirical results across diverse test scenarios affirm the effectiveness of the Spec-VLA framework, and further analysis substantiates the impact of our proposed strategies, which enhance the acceptance length by 44%, achieving 1.42 times speedup compared with the OpenVLA baseline, without compromising the success rate. The success of the Spec-VLA framework highlights the potential for broader application of speculative execution in VLA prediction scenarios.