SOURCE-LINKED INTELLIGENCE

CASCADE: A Spatio-Temporal-Causal Reasoning Representation and Dataset for Driving

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Reasoning is a promising route to the generalization that autonomous driving requires in the long tail, as it can infer how the elements of a scene depend on one another and traverse those dependencies to conclusions beyond what is observed. Yet it is hard to tell whether a model's conclusions follow the scene's dependencies, because no driving representation makes them explicit enough to test against. Text-based reasoning traces lack spatio-temporal grounding, spatio-temporal scene graphs lack causal links, and reasoning annotations at scale are increasingly model-generated and hard to verify

Read original source ↗ Open in workspace

recordType

paper

region

Global