SOURCE-LINKED INTELLIGENCE

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across viewpoints. We present WorldCrafter, a video world model that learns a camera-queryable implicit 3D-aware memory for this purpose. The key insight is to let the requested viewpoint shape how multi-view evidence is compressed into the video generator's limited token budget. Trained jointly with the video generator, a memory encoder and pose-conditioned readout module integrate historical observations into a fixed set of target view-specific tokens b

Read original source ↗ Open in workspace

recordType

paper

region

Global