# A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference

arXiv: https://arxiv.org/abs/2607.24148 · HTML: https://mlsanity.com/paper/2607.24148/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 37 of its 70 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 30 of 37)

- [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)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://mlsanity.com/paper/2402.04396/) (2024)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models](https://mlsanity.com/paper/2306.02272/) (2023)
- [PQCache: Product Quantization-based KVCache for Long Context LLM Inference](https://mlsanity.com/paper/2407.12820/) (2024)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration](https://mlsanity.com/paper/2311.12015/) (2023)
- [VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12894/) (2024)
- [XNOR Neural Engine: a Hardware Accelerator IP for 21.6 fJ/op Binary Neural Network Inference](https://mlsanity.com/paper/1807.03010/) (2018)
- [ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization](https://mlsanity.com/paper/2406.05981/) (2024)
- [Fast Matrix Multiplications for Lookup Table-Quantized LLMs](https://mlsanity.com/paper/2407.10960/) (2024)
- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs](https://mlsanity.com/paper/2005.09904/) (2020)
- [Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones](https://mlsanity.com/paper/1809.05780/) (2018)
- [DaDu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation](https://mlsanity.com/paper/2407.04292/) (2024)
- [VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference](https://mlsanity.com/paper/2503.02236/) (2025)
- [MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving](https://mlsanity.com/paper/2510.14557/) (2025)
- [LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator](https://mlsanity.com/paper/2501.10658/) (2025)
- [eSLAM: An Energy-Efficient Accelerator for Real-Time ORB-SLAM on FPGA Platform](https://mlsanity.com/paper/1906.05096/) (2019)
- [M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization](https://mlsanity.com/paper/2601.19213/) (2026)
- [BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge](https://mlsanity.com/paper/2401.11851/) (2024)

## Built on by (most cited first, 1 of 1)

- [ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference](https://mlsanity.com/paper/2610.08444/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment. Existing accelerators, such as Dadu-Corki, improve efficiency but treat VLA models as full-precision workloads, leaving substantial redundancy in both memory and computation underexploited. In this paper, we propose VQVLA, an algorithm-hardware co-design framework that accelerates VLA inference by exploiting weight similarity and execution dynamics. We first introduce MotionVQ, a motion-aware vector quantization scheme that dynamically adjusts quantization precision based on the robot's execution state, reducing memory access while preserving task success rate. We then propose a merged-centroid vectorized GEMM paradigm that operates on the codebook-index representation, eliminating redundant multiplications through spatial aggregation and temporal reuse of centroids. To realize these optimizations, we design an accelerator that efficiently supports dynamic precision selection and centroid-reuse computation. Experimental results show that VQVLA achieves 6.5x, 2.8x, 1.9x, 3.3x, and 4.3x speedup over the A100 GPU, Dadu-Corki, LUT-DLA, CodeGEMM, and ShiftAddLLM, respectively, with negligible accuracy degradation.