Model Releases
LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
arXiv:2610.03636v1 Announce Type: cross Abstract: Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistenc
arXiv:2610.03636v1 Announce Type: cross Abstract: Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistency: as the camera moves, objects lose permanence and scene structures shift. Existing post-training techniques, which assign a single scalar reward to the entire generation, are poorly suited to correcting these inconsistencies over long horizons. We introduce LoGo, which blends global and spatially localized rewards for camera-controlled video models. The local reward provides fine-grained credit assignment, which substantially improves 3D consistency, while the global reward preserves camera following and video quality. Across three base models, LoGo shows a clear advantage on DL3DV and TrajectoryBench, a new benchmark for long-horizon, complex-camera-control generation that current evaluations lack. LoGo effectively reduces local object shifts, artifacts, and global scene changes, illustrating the importance of credit assignment in post-training video models. Project website: https://ziqi-ma.github.io/logo-website/
Related
- EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generation
- EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation
- ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation
Source: arXiv cs.AI | 2026-10-05