AlayaWorld: Long-Horizon and Playable Video World Generation

Hugging Face Daily Papers Papers

Summary

AlayaWorld is an open-source framework for building interactive generative worlds that enables real-time user interaction and supports diverse actions. It unifies the complete development pipeline from data preparation to deployment.

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.
Original Article
View Cached Full Text

Cached at: 07/08/26, 02:47 AM

Paper page - AlayaWorld: Long-Horizon and Playable Video World Generation

Source: https://huggingface.co/papers/2607.06291 Published on Jul 7

#1 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

AlayaWorld is an open-source framework for creating interactive generative worlds that enables real-time user interaction and supports diverse actions within a modular architecture.

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 invideo world modelsoffer 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 interactivegenerative worlds. AlayaWorld enables open-endedreal-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 releasereproducible pipelines,reference implementations,evaluation tools, and comprehensive documentation, establishing a practical foundation for future research and real-time applications of generative world models.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.06291

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.06291 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.06291 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.06291 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

Hugging Face Daily Papers

AlayaWorld is a 15B-parameter interactive video world model that generates 24-fps video at 540p and 720p, using autoregressive latent chunk generation with bounded visual context and distillation to reduce inference steps. It achieves state-of-the-art performance on the iWorld-Bench for long-horizon generation.

Generative World Renderer at the Speed of Play

Hugging Face Daily Papers

This paper introduces AlayaRenderer-Flash, a real-time generative world renderer that accelerates rendering from 0.56 FPS to 31.54 FPS using a few-step autoregressive streaming model and lightweight distilled codecs, enabling interactive play with a physics engine.

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Hugging Face Daily Papers

Evoke is an interactive world model with external persistent memory and a redesigned long-horizon teacher, enabling open-ended video generation with bounded context and low latency. It achieves state-of-the-art performance on WBench while staying competitive on VBench-Long and VBench-2.0.