AlayaWorld：長程且可遊玩的影片世界生成

摘要

傳統遊戲世界通常透過高勞動密集的生產流程構建，導致開發成本高昂、難以客製化，且部署後修改不易。近期影片世界模型的進展提供了截然不同的典範：這類模型無需逐一明確設計虛擬環境中的所有元件，而是根據當前的世界狀態與使用者互動，以自回歸方式合成未來的觀察結果，從而實現即時生成可遊玩的世界。這些模型同時以遊戲錄影與真實世界影片進行訓練，能夠捕捉多樣的視覺表徵與物理動態，為超越遊戲範疇的互動式應用（包括具身智慧）開創了新的可能性。本文提出 AlayaWorld——一套用於建構互動式生成世界的全端開源框架。AlayaWorld 支援開放式的即時互動，允許使用者自由探索並執行戰鬥、施法、召喚怪物等多樣化的動作。該框架將完整的開發流程——從資料準備、模型架構、模型訓練、推理加速到部署——統一在一個模組化且可擴充的架構中。伴隨框架的釋出，我們同時公開了可重現的流程、參考實作、評估工具與完整的文件，為生成式世界模型的未來研究與即時應用奠定了實務基礎。

English

Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and expensive to modify after deployment. Recent advances in video world models offer a fundamentally different paradigm. Rather than explicitly authoring every component of a virtual environment, these models autoregressively synthesize future observations conditioned on the current world state and user interactions, enabling playable worlds to be generated online. Trained on both gameplay recordings and real-world videos, they can capture diverse visual appearances and physical dynamics, opening new opportunities for interactive applications beyond gaming, including embodied intelligence. In this paper, we present AlayaWorld, a full-stack open-source framework for building interactive generative worlds. AlayaWorld enables open-ended real-time interaction, allowing users to freely navigate and perform diverse actions such as combat, spell casting, and monster summoning. The framework unifies the complete development-from data preparation model architecture, model training, inference acceleration, and deployment-within a modular and extensible architecture. Alongside the framework, we release reproducible pipelines, reference implementations, evaluation tools, and comprehensive documentation, establishing a practical foundation for future research and real-time applications of generative world models.