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

Hugging Face Daily Papers Papers
interactive-world-model video-diffusion long-horizon autoregressive distillation open-source world-modeling

Summary

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.

Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly. It enable us to create customized, explorable, and continuously evolving virtual world from text, an image, or video. Realizing this vision requires four tightly coupled capabilities: interaction, persistent spatiotemporal consistency, stable long-horizon generation, and efficient response. We present AlayaWorld, an interactive long-horizon video world model that generates 24-fps video at 540p and 720p. Built on a 15B video diffusion transformer, AlayaWorld generates short latent chunks autoregressively under camera trajectories and switchable text prompts. Its bounded visual context combines a persistent sink frame, compressed temporal history, geometry-aligned spatial memory, and recent-frame conditioning. To reduce long-term drift, the model is trained with corrupted histories and prediction residuals collected from its own roll-outs. We further introduce a discrete autoregressive distillation formulation that combines distribution-matching distillation, self-forcing++, and consistency distillation, reducing inference from approximately 30 sampling steps to four steps per chunk. On iWorld-Bench, AlayaWorld achieves the best performance over long-horizon generation. Conceived as a full-stack, open-source, and long-term project, AlayaWorld is intended to provide an extensible foundation for future research on interactive video world models.
Original Article
View Cached Full Text

Cached at: 07/22/26, 06:41 AM

Paper page - AlayaWorld: Interactive Long-Horizon World Modeling – Full Technical Report

Source: https://huggingface.co/papers/2607.18367 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Unlikeconventionalvideogamedevelopment,whichreliesonlabor-intensivepipelinesforassetproduction,animation,physics,andprogramming,videoworldmodelsgenerateinteractiveenvironmentsfromuserinputsinstantly.Itenableustocreatecustomized,explorable,andcontinuouslyevolvingvirtualworldfromtext,animage,orvideo.Realizingthisvisionrequiresfourtightlycoupledcapabilities:interaction,persistentspatiotemporalconsistency,stablelong-horizongeneration,andefficientresponse.WepresentAlayaWorld,aninteractivelong-horizonvideoworldmodelthatgenerates24-fpsvideoat540pand720p.Builtona15Bvideodiffusiontransformer,AlayaWorldgeneratesshortlatentchunksautoregressivelyundercameratrajectoriesandswitchabletextprompts.Itsboundedvisualcontextcombinesapersistentsinkframe,compressedtemporalhistory,geometry-alignedspatialmemory,andrecent-frameconditioning.Toreducelong-termdrift,themodelistrainedwithcorruptedhistoriesandpredictionresidualscollectedfromitsownroll-outs.Wefurtherintroduceadiscreteautoregressivedistillationformulationthatcombinesdistribution-matchingdistillation,self-forcing++,andconsistencydistillation,reducinginferencefromapproximately30samplingstepstofourstepsperchunk.OniWorld-Bench,AlayaWorldachievesthebestperformanceoverlong-horizongeneration.Conceivedasafull-stack,open-source,andlong-termproject,AlayaWorldisintendedtoprovideanextensiblefoundationforfutureresearchoninteractivevideoworldmodels.

View arXiv pageView PDFProject pageGitHub556Add to collection

Get this paper in your agent:

hf papers read 2607\.18367

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/2607.18367 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.18367 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.18367 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: Long-Horizon and Playable Video World Generation

Hugging Face Daily Papers

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.

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.