Efficient VLA Inference

VLA: Vision-Language-Action Model

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

221 papers36 papers in the last four weeks, down 35% on the four weeks before. 0.3% of all new papers.

  1. ASPEN: Adaptive Semantic Reasoning via Command Persistence Prediction for Efficient Navigation VLAs

    Oct 26, 2026Vieri N. Akustia, Bin HuEfficient VLA InferenceVision-Language Navigation

  2. VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware

    Oct 26, 2026Borui Xu, Hongshi Tan, Wenqi Jiang +4Efficient VLA InferenceOn-Device Inference

  3. TRIAGE: Efficient Vision-Language-Action Inference Needs Both Reuse and Pruning

    Oct 25, 2026Sooyoung Kwon, Carlee Joe-Wong, Kyunghan LeeEfficient VLA InferenceVisual Token Pruning

  4. Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies

    Oct 23, 2026Jiabing Yang, Yuan Xu, Yixiang Chen +13Flow-Based VLAsEfficient VLA Inference

  5. When One Step Is Enough: An Empirical Study of Euler Integration in Flow-Matching Policies

    Oct 22, 2026Shivakanth Sujit, Luca Nunziante, Rousslan Fernand Julien Dossa +1Flow MatchingEfficient VLA Inference

  6. AGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models

    Oct 21, 2026Xuhong Qiu, Zhuoyu Wu, Qiawei Zheng +3VLM QuantizationEfficient VLA Inference

  7. PACT-VLA: Speculative Action-Chunk Verification with Pre-Commit Observations

    Oct 20, 2026Yixiang Zhu, Ruilong Wu, Yonghao Chen +3Vision-Language-Action ModelsRobustness of VLAs

  8. SPAR: Structural Pruning and Action Recovery for Vision-Language-Action Models

    Oct 19, 2026Shenli Zheng, Zhou Fang, Yuan Du +2Efficient VLA InferenceLVLM Pruning

  9. PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

    Oct 19, 2026Hojin Jeon, Jimin Lee, Taekwan Kim +6Efficient VLA InferenceVision-Language-Action Models

  10. Scene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing

    Oct 17, 2026Yujia Yang, Quan Yuan, Jiawei Fan +5Efficient VLA InferenceVLMs for Autonomous Driving

  11. MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models

    Oct 16, 2026Khuyen Pham, Tran Nguyen Le, Edoardo Fazzari +1Efficient VLA InferenceVision-Language-Action Models

  12. FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action Models

    Oct 15, 2026Jiuyi Xu, Chengyuan Qian, Zhengzhong Tu +2Efficient VLA InferenceVisual Token Compression

  13. Fast-VLA: You Only Think Once for Robot Manipulation

    Oct 15, 2026Kehong Gong, Guanli Hou, Xiaoxu Zheng +6Vision-Language-Action ModelsClosed-Loop Control of VLAs

  14. LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models

    Oct 15, 2026Qixin Sun, WenLong Gao, Xiansheng Chen +3Memory-Augmented VLMsICL for Robotics

  15. Causal Analysis of Robot Foundation Models Enables Efficiency Gains

    Oct 14, 2026Aiden Swann, Mathilde Papillon, Mozes Jacobs +13Vision-Language-Action ModelsEfficient VLA Inference

  16. TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

    Oct 13, 2026Jack Lu, Yurong You, Boyi Li +8Reasoning for VLAsVLMs for Robotics

  17. ΔΔ Flow Matching for Robot Foundation Models

    Oct 11, 2026Kuangji Zuo, Tuo An, Xinying Guo +9Flow Matching for Action GenerationRobot Foundation Models

  18. Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning

    Oct 11, 2026Seongmin Park, Jaewon Lee, Yujun Heo +4VLM QuantizationEfficient VLA Inference

  19. Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution

    Oct 10, 2026Wenbo Yu, Jifan Li, Wenke Xia +5Inference-Time GuidanceEfficient VLA Inference

  20. Memory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies

    Oct 9, 2026Yilin Wu, Rutav Shah, Shuaiyi Huang +5Memory-Augmented VLMsVisuomotor Policy Learning

  21. REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models

    Oct 8, 2026Houlong Xiong, Zhenqi Qiu, Zechen Wang +8Robotic ControlVision-Language-Action Models

  22. SpikingVLA: Asynchronous Spiking Vision-Language-Action Models

    Oct 7, 2026Jingya Wang, Dehao Zhang, Shuai Wang +3Efficient VLA InferenceSpiking Neural Networks

  23. CARE: Certifying Acceleration for Vision-Language-Action Inference

    Oct 6, 2026Rui Liu, Tong Zheng, Jindong Gu +1Efficient VLA InferenceVision-Language-Action Models

  24. ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference

    Oct 6, 2026Zou Qingyun, Bin Gao, Wenju Zhao +3Energy-Efficient MLVLM Quantization