DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation

Source: arXiv cs.RO·2026-09-01 12:00Publish time unverified

arXiv:2608.29078v1 Announce Type: new Abstract: Vision-language-action (VLA) models have made strong progress in language-conditioned robot manipulation, but improving their performance in a new workspace still often requires action-labeled data from that environment. Collecting such data by human teleoperation is costly, especially when each workspace, object arrangement, or task may require new demonstrations.