SolarWM：面向長時域視頻世界模型的開放數據與可擴展訓練

摘要

我們推出 SolarWM——一個完全開放的基礎架構，用於建構從資料準備到長時程推論的互動式影片世界模型。在異質資料來源與各種影片骨幹網路上訓練極具挑戰性：不同資料集的時間尺度、相機幾何、視覺品質、動態與描述文字風格各不相同，而影片生成器也各自採用不同的表徵與架構。因此，單純混合資料或針對特定模型作個別實作，會產生不一致的監督訊號，使結果難以重現與比較。為解決此耦合問題，SolarWM 結合了可重構的多來源資料引擎，以及以骨幹網路原生特性為本位的適配框架。該引擎將來自 10 個資料集的 143 萬個標準化片段，轉換為統一且逐幀對齊的資料契約，涵蓋視覺觀測、度量相機幾何、描述文字、品質後設資料、選擇決策與來源出處，同時將來源處理與混合資料建構解耦。在共享的相機條件化、訓練與推論介面下，我們基於 Wan2.2、LTX-2.5 與 MiniMax-H3 實例化了四個 5B 至 33B 參數規模的模型，同時保留其原生表徵與訓練目標。一套統一的三階段訓練配方結合了雙向適配、教師強迫自迴歸初始化與分佈匹配蒸餾。所得的因果模型僅以 5 秒序列訓練後，即可在長達數分鐘至數小時的推演中支援即時互動。透過公開釋出上述資料、流程、配方、權重與框架，SolarWM 為互動式世界模型研究提供了可重現且可擴展的基礎。

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.