WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World 事件

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World arXiv:2512.10958v2 Announce Type: replace Abstract: Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way to assess whether generated worlds preserve geometry, obey physics, or support reliable control. We introduce WorldLens, a full-spect