AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models
Research
Source: arXiv cs.ROPublish time unverified
arXiv:2608.29208v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging internet-scale knowledge and multimodal reasoning. However, the intensive computational overhead of VLAs constrains on-device deployment, hindering real-time responses to environmental changes.