SOURCE-LINKED INTELLIGENCE

DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Generative world-action models (WAMs) jointly generate future video and vehicle actions, while their action branches remain primarily optimized by expert imitation. Yet imitation provides no explicit closed-loop geometric verdict for generated trajectories, making verification important during both training and deployment. Closed-loop evaluators can check collision and drivable-area violations, but require privileged scene state unavailable at deployment. Existing approaches often close this gap by learning a verifier from sensor features. For these geometric checks, the rule itself is explici

Read original source ↗ Open in workspace

recordType

paper

region

Global