AI RESEARCH
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
arXiv CS.CV
•
ArXi:2603.17117v1 Announce Type: new Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial memory remains a key bottleneck: explicit 3D structures can improve reprojection-based consistency but struggle to depict moving objects, while implicit memory often produces inaccurate camera motion even with correct poses.