# LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation

arXiv: https://arxiv.org/abs/2610.03636 · HTML: https://mlsanity.com/paper/2610.03636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 42 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 30 of 40)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [DiffusionNFT: Online Diffusion Reinforcement with Forward Process](https://mlsanity.com/paper/2509.16117/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025)
- [CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation](https://mlsanity.com/paper/2406.02509/) (2024)
- [WorldScore: A Unified Evaluation Benchmark for World Generation](https://mlsanity.com/paper/2504.00983/) (2025)
- [Efficiently Reconstructing Dynamic Scenes One D4RT at a Time](https://mlsanity.com/paper/2512.08924/) (2025)
- [Infinite Worlds with Versatile Interactions](https://mlsanity.com/paper/2607.07534/) (2026)
- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [DreamX-World 1.0: A General-Purpose Interactive World Model](https://mlsanity.com/paper/2606.16993/) (2026)
- [MIND: Benchmarking Memory Consistency and Action Control in World Models](https://mlsanity.com/paper/2602.08025/) (2026)
- [Epipolar Geometry Improves Video Generation Models](https://mlsanity.com/paper/2510.21615/) (2025)
- [WorldCompass: Reinforcement Learning for Long-Horizon World Models](https://mlsanity.com/paper/2602.09022/) (2026)
- [VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward](https://mlsanity.com/paper/2603.26599/) (2026)
- [VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation](https://mlsanity.com/paper/2601.23286/) (2026)
- [GeoVideo: Introducing Geometric Regularization into Video Generation Model](https://mlsanity.com/paper/2512.03453/) (2025)
- [TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents](https://mlsanity.com/paper/2607.13988/) (2026)
- [World-R1: Reinforcing 3D Constraints for Text-to-Video Generation](https://mlsanity.com/paper/2604.24764/) (2026)
- [Taming Camera-Controlled Video Generation with Verifiable Geometry Reward](https://mlsanity.com/paper/2512.02870/) (2025)

## Abstract (arXiv)

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/