SOURCE-LINKED INTELLIGENCE

DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Faithfully evaluating end-to-end driving policies in simulation requires observations that are not merely photo-realistic, but preserve the scene features a policy relies on to make decisions. Existing platforms, however, exhibit a sim-to-real visual gap that corrupts policy perception, undermining their ability to assess a policy's closed-loop decision-making. To this end, we propose DreamStream, a generative, closed-loop simulator that achieves policy-oriented fidelity using a simulator-grounded autoregressive video model. Our video model is distilled from a large pretrained video model via

Read original source ↗ Open in workspace

recordType

paper

region

Global