SolarWM：面向长时程视频世界模型的开放数据与可扩展训练

摘要

我们提出SolarWM，这是一个完全开放的基础框架，用于构建从数据准备到长时程推理的交互式视频世界模型。跨异构数据源与视频主干网络进行训练颇具挑战性：数据集在时间尺度、相机几何、视觉质量、运动与描述风格上各不相同，而视频生成器则采用不同的表征与架构。因此，朴素的数据混合与模型特化的实现会产生不一致的监督信号，并导致结果难以复现和比较。 SolarWM通过可重构的多源数据引擎与主干原生适配框架来解决这一耦合问题。该引擎将来自10个数据集的143万个规范片段转换为统一且帧对齐的数据契约，涵盖视觉观测、度量相机几何、描述、质量元数据、选择决策与溯源信息，同时将源数据处理与数据混合构建相解耦。在共享的相机条件化、训练与推理接口下，我们基于Wan2.2、LTX-2.5和MiniMax-H3实例化了四个参数量为5B至33B的模型，同时保留其原生表征与优化目标。统一的三阶段方案结合了双向适配、教师强制的自回归初始化与分布匹配蒸馏。由此得到的因果模型在仅以5秒序列完成训练后，即可在从数分钟到数小时不等的推演中实现实时交互。通过开源所得到的数据、流水线、方案、权重与框架，SolarWM为交互式世界模型研究提供了可复现且可扩展的基础。

English

We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data sources and video backbones is challenging: datasets differ in temporal scale, camera geometry, visual quality, motion, and captioning styles, while video generators use distinct representations and architectures. Naive data mixing and model-specific implementations therefore produce inconsistent supervision and make results difficult to reproduce and compare. SolarWM addresses this coupling with a reconfigurable multi-source data engine and a backbone-native adaptation framework. The engine converts 1.43 million canonical clips from 10 datasets into a unified, frame-aligned contract covering visual observations, metric camera geometry, captions, quality metadata, selection decisions, and provenance, while decoupling source processing from mixture construction. Under shared camera-conditioning, training, and inference interfaces, we instantiate four 5B--33B models based on Wan2.2, LTX-2.5, and MiniMax-H3 while preserving their native representations and objectives. A unified three-stage recipe combines bidirectional adaptation, teacher-forced autoregressive initialization, and distribution matching distillation. The resulting causal models enable real-time interaction over rollouts ranging from minutes to hours after being trained on only 5s sequences. By releasing the resulting data, pipeline, recipes, weights, and framework, SolarWM provides a reproducible and extensible foundation for interactive world-model research.