SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

2026-09-02

AI Summary

SolarWM通过可配置的多源数据引擎和适应框架，解决了跨异构数据源和视频模型训练的一致性问题，实现了长时序视频世界模型的构建。

Abstract

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.

Problem

• Heterogeneous Data Sources
• Video Backbones
• Inconsistent Supervision
• Reproducibility

Innovation

• reconfigurable multi-source data engine
• backbone-native adaptation framework
• unified three-stage recipe
• causal models for real-time interaction