Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion

ArXi:2511.14178v2 Announce Type: replace-cross Vision-Language-Action (VLA) models have nstrated significant potential in real-world robotic manipulation. However, pre-trained VLA policies still suffer from substantial performance degradation during downstream deployment. Although fine-tuning can mitigate this issue, its reliance on costly nstration collection and intensive computation makes it impractical in real-world settings. In this work, we