SOURCE-LINKED INTELLIGENCE

Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across shots. Existing video generators favor continuous motion and struggle to present complete shot sets when an entire narrative is packed along one temporal axis. We propose MovieGrid, a Multi-Grid Post-Training paradigm that decomposes a long video into shorter, temporally ordered chunks and arranges them on a spatial grid for joint modeling. This design reduces the number of shots handled by each temporal axis while enabling global information exchange across chunks. We construc

Read original source ↗ Open in workspace

recordType

paper

region

Global