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. BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model

    Feb 24, 2026Haosheng Li, Weixin Mao, Zihan Lan +6Efficient VLA InferenceVisual Token Pruning

  2. QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models

    Feb 23, 2026Jingxuan Zhang, Yunta Hsieh, Zhongwei Wan +5Efficient VLA InferenceVLA Post-Training

  3. Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

    Feb 22, 2026Zaijing Li, Bing Hu, Rui Shao +5Efficient VLA InferenceMemory-Augmented VLMs

  4. ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge

    Dec 23, 2025Yuntao Dai, Hang Gu, Teng Wang +6Efficient VLA InferenceVision-Language-Action Models

  5. AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving

    Sep 17, 2025Yuechen Luo, Fang Li, Shaoqing Xu +11Autonomous DrivingReasoning for VLAs

  6. SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning

    Sep 6, 2025Hanzhen Wang, Jiaming Xu, Yushun Xiang +4Efficient VLA InferenceVision-Language-Action Models

  7. VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting

    Jul 7, 2025Juyi Lin, Amir Taherin, Arash Akbari +11Robotic ControlEfficient VLA Inference