rMuscle reuses internal VLA state across repetitive robot tasks

rMuscle caches visual-token outputs and neuron activation patterns across similar repeated vision-language-action executions. On RTX 4090, Jetson Thor, LIBERO, RoboTwin and physical manipulation tasks, the authors report 1.29x-1.42x faster inference while preserving the original real-robot success rates. The benefit targets repetitive factory-style work rather than general robot behavior.

For robotics teams with repeated trajectories, internal-state reuse can lower latency without changing the VLA model. The workload assumptions are narrow and no code is linked. Reproduce on the actual camera, task variation and safety envelope before planning deployment.