AI RESEARCH
NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving
arXiv CS.AI
•
ArXi:2509.25944v2 Announce Type: replace Understanding risk in autonomous driving requires not only perception and prediction, but also high-level reasoning about agent behavior and context. Current Vision Language Model (VLM)-based methods primarily ground agents in static images and provide qualitative judgments, lacking the spatio-temporal reasoning needed to capture how risks evolve over time.