H3-World：將語言理解轉化為世界控制

摘要

我們提出 H3-World，一個將 33B MiniMax-H3 影片生成器轉化為互動式世界模型的高效框架。我們的核心發現是，隨著大型影片生成器的能力日益增強，語言正逐漸成為一種自然的控制介面。以 MiniMax-H3 為例，它已支援透過自然語言指令對角色行為與鏡頭運動進行零樣本控制。在此基礎上，H3-World 將此粗略的語言介面轉化為精確且具時間定位的世界控制，且無需引入專門的動作模組。具體而言，我們將每個動作表示為角色指令與鏡頭指令的結構化組合，並將其與對應時間範圍的影片潛在特徵對齊。為使控制在時間上更為精確，我們進一步引入時間注意力路由，將每個指令限制在其預期的時間區間內，藉此減少動作之間的控制洩漏。重要的是，H3-World 直接重用在大規模影片預訓練期間所習得的語義表示，僅需進行輕量級適配。僅使用 8,000 筆遊戲畫面樣本、10,000 步 LoRA 最佳化步驟，以及 0.199% 的可訓練參數，H3-World 便能在維持強大生成品質的同時，實現有效的角色與鏡頭控制，並能泛化至未見過的情境。這些結果表明，大型影片生成器中所湧現的控制能力，可被高效率地轉化為互動式世界控制。

English

We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become more capable, language is emerging as a natural interface for control. MiniMax-H3, for example, already supports zero-shot control of character behavior and camera motion through natural-language instructions. Building on this, H3-World turns this coarse language interface into precise, temporally grounded world control, without introducing dedicated action modules. Specifically, we represent each action as a structured combination of character and camera instructions, and align them with the corresponding temporal video latents. To make the control temporally precise, we further introduce temporal attention routing, which restricts each instruction to its intended time interval and reduces control leakage across actions. Importantly, H3-World directly reuses the semantic representations learned during large-scale video pretraining and requires only lightweight adaptation. With only 8,000 gameplay samples, 10,000 LoRA optimization steps, and 0.199% trainable parameters, H3-World achieves effective character and camera control while preserving strong generation quality. It also generalizes to unseen scenarios. These results show that the control capabilities emerging in large video generators can be efficiently transformed into interactive world control.