The Year in AI Papers
The year/Independent research

Paper 2607.06291

AlayaWorld: Long-Horizon and Playable Video World Generation

AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, et al.

Published
Jul 2026
Research lab
Independent
Citations
1
GitHub
Not linked

01 In brief

Summary

AlayaWorld is a full-stack, open-source framework for building interactive generative worlds, fine-tuned from LTX-2.3.

It addresses four key challenges: control, consistency, stability, and runtime.

For control, it combines a 3D cache rendered along the camera trajectory with AdaLN-style camera modulation, and supports prompt-driven actions via a prompt-switching mechanism at chunk boundaries.

For consistency, it merges spatial memory (3D cache) with temporal memory (compressed history) to handle leave-and-return scenarios.

For stability, it uses an error bank and training on drifted histories to prevent error accumulation in long-horizon generation.

For runtime, it employs DMD-based distillation and small temporal chunks to achieve real-time generation with low latency.

Qualitative results show precise camera control, open-ended actions, consistent revisits, long-horizon stability, and diverse styles.

The framework includes reproducible pipelines, reference implementations, and evaluation tools, with full code release planned for mid-July.

02 From the paper

Abstract

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 \textbf{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.