無限世界與多樣互動

摘要

我們提出LingBot-World 2.0（亦稱LingBot-World-Infinity），此為LingBot-World的高階迭代版本，具備四項獨特升級。(1) 我們的模型實現了無限互動範圍，同時維持一致的輸出品質，此優勢來自精心設計的因果預訓練範式。(2) 透過從基礎模型中蒸餾出即時變體，我們的系統確保了快速回應時間，足以驅動60 fps的720p影像串流。(3) 相較於前一版本，本次更新引入了高度多樣化的互動元素，涵蓋更廣泛的動作（例如攻擊、射箭、施法與射擊），以及更豐富的文字驅動事件。(4) 我們率先在世界建模領域整合了智能體控制機制，其中領航智能體負責規劃與執行角色行為，而導演智能體則負責在場景進展中合成新穎的環境元素。此外，為促進共享體驗，我們開發了一套介面，允許多位玩家同時沉浸於此生動的世界模擬器中。我們將主要的14B模型與輕量級的1.3B模型配對，以支援在單一GPU上輕鬆部署。

English

We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. (1) Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. (2) Through distilling a real-time variant from the base model, our system guarantees rapid response time, sufficient to drive 720p video streams at 60 fps. (3) Compared to the previous version, this update introduces highly diverse interactive elements, comprising a broader spectrum of actions (e.g., attacking, archery, spell-casting, and shooting) alongside a richer variety of text-driven events. (4) We pioneer the integration of an agentic harness within the domain of world modeling, wherein a pilot agent is tasked with planning and executing character behaviors, while a director agent is responsible for synthesizing novel environmental elements as the scene progresses. Additionally, to facilitate a shared experience, we develop an interface that permits multiple players to simultaneously immerse themselves in this vivid world simulator. We pair our primary 14B model with a lightweight 1.3B counterpart, which supports effortless deployment on a single GPU.