Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
This work addresses the deployment bottleneck for VLA-driven robots in real-world tasks, though it appears incremental as it builds on prior analysis.
The authors tackled the challenge of deploying Vision-Language-Action (VLA) models on real robots by developing practical techniques to achieve fast, smooth, and accurate execution, resulting in robot speeds comparable to casual human operation and approaching hardware limits.
In deployment of the VLA models to real-world robotic tasks, execution speed matters. In previous work arXiv:2510.26742 we analyze how to make neural computation of VLAs on GPU fast. However, we leave the question of how to actually deploy the VLA system on the real robots open. In this report we describe a set of practical techniques to achieve the end-to-end result of running a VLA-driven robot at an impressive speed in real world tasks that require both accuracy and dexterity. The stack of technology ranges across calibration, planning & control, and learning based method to identify optimal execution speed. In the tasks we show, the robot even executes in a speed on par with casual human operation and approaching the hardware limit of our lightweight arm. The unaccelerated videos and inference traces are provided in https://dexmal.github.io/realtime-vla-v2/.