AI 中文总结
针对现有驾驶世界生成方法局限，提出M$^\text{4}$World模型，通过灵活接口与多阶段训练实现对象操纵及长时流稳定，引入后训练与生成模型，并用新管道评估，实验证明其在驾驶模拟中有高质量、可控性与稳定性。
AI 中文摘要
驾驶世界生成已成为可扩展自动驾驶模拟的核心能力，但现有方法在对象级可控性和长时稳定性方面仍有局限。我们提出了M$^\text{4}$World，一个多视图多模态生成式驾驶世界模型，可合成未来环绕视图视频流和同步激光雷达扫描，支持交互式对象操纵和稳定的分钟级流。通过灵活的条件接口实现细粒度对象操纵，通过多阶段训练框架实现稳定的分钟级流。在此基础上，引入了高效的少剪辑后训练和视觉参考条件生成模型。还介绍了基于VLM的自动判断管道。综合实验表明M$^\text{4}$World具有高生成质量、精确可控性和稳定的分钟级流，展示了其在可控、可扩展驾驶模拟中的潜力。
英文摘要
Driving-world generation has emerged as a core capability for scalable autonomous-driving simulation, yet existing methods remain limited in object-level controllability and long-horizon stability. We present M$^\text{4}$World, a Multi-view and Multimodal generative driving world model that synthesizes future surround-view video streams and synchronized LiDAR scans while supporting interactive object Manipulation and stable Minute-long streaming. Fine-grained object manipulation is realized through a flexible conditioning interface that supports explicit control over both the spatial layout and visual appearance of individual objects. Stable minute-long streaming, on the other hand, is achieved through a multi-stage training framework that enables online causal generation in only four denoising steps while maintaining coherent world dynamics throughout extended rollouts. Building on these components, we introduce an efficient few-clip post-training as well as a suite of visual reference-conditioned generation models, preserving general generation ability while allowing rare-case customization for long-tail controllability. To assess controllability beyond realism, we further introduce an automated VLM-based judging pipeline that evaluates scene-level condition adherence, view-wise object controllability, and cross-view object consistency. Comprehensive experiments show that M$^\text{4}$World consistently delivers high generation quality, precise controllability, and stable minute-long streaming. Together with downstream long-tail augmentation and scene editing, these results demonstrate the potential of M$^\text{4}$World for controllable, scalable driving simulation.
Comments24 pages, 13 figures
