AI RESEARCH

SimScale: Learning to Drive via Real-World Simulation at Scale

arXiv CS.CV

ArXi:2511.23369v2 Announce Type: replace Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by human experts. To complement for the lack of data diversity, we