AI RESEARCH
CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop Evaluation
arXiv CS.CV
•
ArXi:2603.21104v1 Announce Type: cross Generating safety-critical driving scenarios requires understanding why dangerous interactions arise, rather than merely forcing collisions. However, existing methods rely on heuristic adversarial agent selection and unstructured perturbations, lacking explicit modeling of interaction dependencies and thus exhibiting a realism--adversarial trade-off. We present CounterScene, a framework that endows closed-loop generative BEV world models with structured counterfactual reasoning for safety-critical scenario generation.