# LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model arXiv: https://arxiv.org/abs/2506.01546 ยท HTML: https://mlsanity.com/paper/2506.01546/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in World models for autonomous driving, one of 11 directions in World models. - Builds on 53 of its 57 references that are in the map. - First posted on arXiv 2 Jun 2025. ## Placed in - World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/) - End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/) ## Builds on (most cited first, 30 of 53) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022) - [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019) - [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023) - [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017) - [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024) - [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023) - [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024) - [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019) - [World Models](https://mlsanity.com/paper/1803.10122/) (2018) - [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023) - [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023) - [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020) - [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018) - [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024) - [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023) - [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023) - [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024) - [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023) - [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024) - [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023) - [DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving](https://mlsanity.com/paper/2309.09777/) (2023) - [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023) - [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024) - [SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://mlsanity.com/paper/2310.20700/) (2023) - [OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving](https://mlsanity.com/paper/2311.16038/) (2023) - [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018) ## Built on by (most cited first, 9 of 9) - [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025) - [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025) - [Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation](https://mlsanity.com/paper/2509.19296/) (2025) - [WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World](https://mlsanity.com/paper/2512.10958/) (2025) - [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026) - [Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challenges](https://mlsanity.com/paper/2603.09086/) (2026) - [OpenLongTail: Generative Scaling of Long-Tail Driving Data](https://mlsanity.com/paper/2607.09655/) (2026) - [World Models for Embodied Intelligence: From Plausible to Controllable to Actionable](https://mlsanity.com/paper/2609.16697/) (2026) - [ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation](https://mlsanity.com/paper/2604.17147/) (2026) ## Abstract (arXiv) Driving world models are used to simulate futures by video generation based on the condition of the current state and actions. However, current models often suffer serious error accumulations when predicting the long-term future, which limits the practical application. Recent studies utilize the Diffusion Transformer (DiT) as the backbone of driving world models to improve learning flexibility. However, these models are always trained on short video clips (high fps and short duration), and multiple roll-out generations struggle to produce consistent and reasonable long videos due to the training-inference gap. To this end, we propose several solutions to build a simple yet effective long-term driving world model. First, we hierarchically decouple world model learning into large motion learning and bidirectional continuous motion learning. Then, considering the continuity of driving scenes, we propose a simple distillation method where fine-grained video flows are self-supervised signals for coarse-grained flows. The distillation is designed to improve the coherence of infinite video generation. The coarse-grained and fine-grained modules are coordinated to generate long-term and temporally coherent videos. In the public benchmark NuScenes, compared with the state-of-the-art front-view model, our model improves FVD by 27% and reduces inference time by 85% for the video task of generating 110+ frames. More videos (including 90s duration) are available at https://Wang-Xiaodong1899.github.io/longdwm/.