# EdgeVLA: Efficient Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2507.14049 · HTML: https://mlsanity.com/paper/2507.14049/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)

## Builds on (most cited first, 5 of 5)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)

## Built on by (most cited first, 19 of 19)

- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots](https://mlsanity.com/paper/2511.05642/) (2025)
- [CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning](https://mlsanity.com/paper/2602.12532/) (2026)
- [HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness](https://mlsanity.com/paper/2603.17573/) (2026)
- [ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2511.18082/) (2025)
- [TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control](https://mlsanity.com/paper/2601.14945/) (2026)
- [LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics](https://mlsanity.com/paper/2603.03380/) (2026)
- [Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance](https://mlsanity.com/paper/2508.01057/) (2025)
- [AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation](https://mlsanity.com/paper/2509.21006/) (2025)
- [Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference](https://mlsanity.com/paper/2607.12659/) (2026)
- [PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models](https://mlsanity.com/paper/2606.22540/) (2026)
- [Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring](https://mlsanity.com/paper/2603.22899/) (2026)
- [2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness](https://mlsanity.com/paper/2604.09244/) (2026)
- [FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving](https://mlsanity.com/paper/2608.12932/) (2026)
- [Spike-driven Vision-Language-Action Model](https://mlsanity.com/paper/2609.39514/) (2026)
- [Multi-Link Safety Filtering for VLA Policies Around Moving Hazards](https://mlsanity.com/paper/2609.40007/) (2026)
- [REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models](https://mlsanity.com/paper/2610.12007/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) have emerged as a promising approach to address the data scarcity challenge in robotics, enabling the development of generalizable visuomotor control policies. While models like OpenVLA showcase the potential of this paradigm, deploying large-scale VLMs on resource-constrained mobile manipulation systems remains a significant hurdle. This paper introduces Edge VLA (EVLA), a novel approach designed to significantly enhance the inference speed of Vision-Language-Action (VLA) models. EVLA maintains the representational power of these models while enabling real-time performance on edge devices. We achieve this through two key innovations: 1) Eliminating the autoregressive requirement for end-effector position prediction, leading to a 7x speedup in inference, and 2) Leveraging the efficiency of Small Language Models (SLMs), demonstrating comparable training performance to larger models with significantly reduced computational demands. Our early results demonstrate that EVLA achieves comparable training characteristics to OpenVLA while offering substantial gains in inference speed and memory efficiency. We release our model checkpoints and training hrefhttps://github.com/kscalelabs/evla codebase to foster further research.