rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference

Kaijun Zhou, Zhiyang Li, Le Chen, Jinyu Gu|September 16, 2026arXiv

Key Takeaway

Robots doing repetitive tasks can reuse cached visual features and neuron activations from previous executions, cutting VLA inference time by 30-40% without sacrificing accuracy—critical for real-time robot responsiveness.

Summary

This paper presents rMuscle, a framework that speeds up Vision-Language-Action (VLA) models for robot control by caching and reusing computation across repeated tasks.

efficiency applications agents

Key Terms

vision-language-action-model inference-latency activation-caching token-reuse