DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning

arXiv:2607.02865v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies show promising zero-shot generalization, but often fail under deployment-time distribution shift, leading to decreased robustness and inconsistent instruction following. While prior work commonly tackles this by finetuning on in-distribution data, it assumes demonstrations collected on tasks in the target environment. In this work, we propose DREAMSTEER, a deployment-time steering framework for pretr...