Efficient VLA Model Inference

VLA: Vision-Language-Action

Ask about this topic

Overview

This topic studies how to run vision-language-action models fast enough for responsive, reliable robot control, including on edge devices. Common approaches prune or cache visual tokens, quantize or distill models, reduce action-generation steps, and overlap inference with observation and execution. Methods are tested on manipulation benchmarks such as LIBERO and RoboTwin, as well as real robots, using measures like latency, control frequency, memory, energy, and task success. The main tension is that faster inference can undermine closed-loop reliability or motion quality, so gains must be assessed in full task execution rather than by model speed alone.

Latest papers

CardsList

190 papers56 papers in the last four weeks, up 115% on the four weeks before. 0.3% of all new papers.

  1. Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

    Jul 2, 2026Ling Xu, Chuyu Han, Borui Li +6Efficient Neural Network InferenceEfficient VLA Model Inference

    Southeast University · Nanjing University · Microsoft Research +1

  2. Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models

    Jun 24, 2026Tiecheng Guo, Meng GuoRobotic ControlLanguage-Conditioned Robot Manipulation

    The authors are with the School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China.

  3. UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models

    Jun 22, 2026Lin Sun, Zhiwei Guan, Conglin Wang +7Efficient VLM InferenceEfficient VLA Model Inference

    JD.com, China · Yiwu Research Institute of Fudan University, China · Tianjin University, China

  4. Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

    Jun 18, 2026Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18Model CompressionEfficient VLA Model Inference

    Center for AI Research, VinUniversity · VinRobotics · University of Arkansas +10

  5. Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models

    Jun 17, 2026Navin Ranjan, Andreas SavakisMixed-Precision QuantizationVLM Quantization

    Rochester Institute of Technology Rochester, New York 14623, USA

  6. Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models

    Jun 13, 2026Shenhao Yan, Ge Wang, Qi Liu +7Efficient VLA ModelsEfficient VLM Inference

    Northeastern University · Ising AI · CUHK-Shenzhen

  7. Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

    Jun 13, 2026Dianqiao Lei, Lianlei ShanEfficient InferenceEfficient VLA Model Inference

    1Tsinghua University, Beijing, China.

  8. RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation

    Jun 12, 2026Xiangyu Huang, Zhenlin Hua, Han Zhou +2End-to-End Autonomous DrivingEfficient VLM Inference

    Carnegie Mellon University

  9. vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

    Jun 6, 2026Khanh D. Nguyen, Hung T. Ho, Chinh T. Nguyen +5AI Accelerator InferenceEfficient VLM Inference

    VinRobotics, Vietnam · Max Planck Research School for Intelligent Systems, Germany · University of Stuttgart, Germany +3

  10. TBD-VLA: Temporal Block Diffusion Vision Language Action Model

    Jun 5, 2026Sung-Wook Lee, Xuhui Kang, Yen-Ling KuoEfficient VLA Model InferenceEfficient VLA Models

    University of Virginia

  11. RhinoVLA Technical Report

    Jun 5, 2026Huixi Technology, :, Chen Zhang +13Efficient VLM InferenceEfficient VLA Model Inference

    Huixi Technology

  12. Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural Manipulation

    May 31, 2026Keith Truongcao, Christopher Nhu, Zijian An +3Efficient VLA Model InferenceRobotic Manipulation

    Department of Electrical Engineering, Drexel University, Philadelphia, USA

  13. VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

    May 28, 2026Mingjian Gao, Wenqiao Zhang, Yuqian Yuan +9Efficient VLM InferenceEfficient VLA Model Inference

    1Zhejiang University · 2Cornell University · 3National University of Singapore +1

  14. ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models

    May 28, 2026Ye Li, Huanan Liu, Kangye Ji +7Efficient VLM InferenceEfficient VLA Model Inference

    Tsinghua University · University of Illinois at Urbana-Champaign

  15. Ω-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling

    May 27, 2026Xinyu Wang, Mingze Li, Sicheng Lyu +6Post-Training QuantizationEfficient VLA Model Inference

    McGill University · Université de Montréal · Mila – Quebec AI Institute +2

  16. ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

    May 19, 2026Arash Akbari, Arman Akbari, Masih Eskandar +11Neural Network QuantizationVLM Quantization

    1Northeastern University · University of Georgia · 3Cisco Systems

  17. Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

    May 15, 2026Jin Shi, Brady Zhang, Yishun LuVLM DistillationEfficient VLA Model Inference

    Department of Mechanical Engineering University College London London, United Kingdom · Department of Engineering Science University of Oxford Oxford, United Kingdom

  18. Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs

    May 13, 2026Jiahui Niu, Kefan Gu, Yucheng Zhao +5Efficient VLA Model InferenceSpeculative Decoding

    State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Dexmal +1

  19. OOM-Free Alpamayo via CPU-GPU Memory Swapping for Vision-Language-Action Models

    May 12, 2026Seungwoo Roh, Huiyeong Kim, Jong-Chan KimVLMs for Autonomous DrivingEfficient VLA Model Inference

    Graduate School of Automobile and Mobility, Kookmin University, Korea

  20. LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models

    May 11, 2026Boyang Shen, Kaixiang Yang, Hao Wang +4Efficient VLM InferenceEfficient VLA Model Inference

    1Huazhong University of Science and Technology · 2Wuhan United Imaging Surgical Co.,Ltd. (UIS)

  21. Understanding Asynchronous Inference Methods for Vision-Language-Action Models

    May 4, 2026Ayoub AgouzoulRobotic ControlEfficient VLM Inference

    École polytechnique · Systems Group, ETH Zürich

  22. Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference

    May 4, 2026Yudong Liu, Yuan Li, Zijia Tang +12Efficient VLM InferenceEfficient VLA Model Inference

    1Duke University · 2Qualcomm AI Research · University of Florida

  23. Motubrain: An Advanced World Action Model for Robot Control

    Apr 30, 2026Motubrain Team, Chendong Xiang, Fan Bao +17Robotic ControlWorld Models for Robotics

    Motubrain Team

  24. CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies

    Apr 27, 2026Fan Du, Feng Yan, Jianxiong Wu +8Robotic ControlEfficient VLA Model Inference

    1Southern University of Science and Technology · 2Xi’an Jiaotong University · 3United Nova Technology +1

  25. Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment

    Apr 27, 2026Kaijun Zhou, Qiwei Chen, Da Peng +3AI Accelerator InferenceEdge Inference

    School of Computer Science, Shanghai Jiao Tong University

  26. Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

    Apr 20, 2026Jinghui Lu, Jiayi Guan, Zhijian Huang +47Trajectory GenerationVLMs for Autonomous Driving

  27. Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation

    Apr 11, 2026Yiming Wu, Huan Wang, Zhenghao Chen +2Hardware-Aware NASRobotic Manipulation

    The University of Hong Kong, China · Westlake University, China · The University of Newcastle, Australia

  28. 2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness

    Apr 10, 2026Zihao Zheng, Sicheng Tian, Zhihao Mao +8Efficient VLA Model InferenceVision-Language-Action Models

    School of Computer Science, Peking University · School of Artificial Intelligence, Beijing Normal University · School of Computer Science, China University of Geosciences (Wuhan) +2

  29. A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

    Apr 7, 2026Kaidong Zhang, Jian Zhang, Rongtao Xu +20Flow-Based VLA ModelsVision-Language-Action Models

    SYSU · Spatialtemporal AI · MBZUAI

  30. SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation

    Apr 7, 2026Wuyang Luan, Junhui Li, Weiguang Zhao +2Efficient VLA Model InferenceVision-Language-Action Models

    Jilin University · Chongqing University · University of Liverpool +1