Paper page - Generative World Simulation with DAO and JING

Source: https://huggingface.co/papers/2610.19726 Published on Oct 14

·

Submitted byhttps://huggingface.co/kinpzz

Paulon Oct 15

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

A generative framework couples a persistent shared world state with continuous first-person audiovisual generation to enable sustained interactive experiences that evolve through user actions.

We present aGenerative World Simulationframework that couples persistentshared world statewith continuousfirst-person audiovisual generation. The framework integrates DAO, a computable world engine, and JING, anEgocentric Interactive Experience Model, to support sustained interaction for humans and agents. DAO maintains the states of characters, objects, and spaces and their relationships, advancing the world according to interaction rules and world time while preserving the consequences of past actions. From this evolving state, DAO derives observer-specific conditions for JING, which combines these conditions with character, object, and scene references, observation history, and current actions to generate each observer’s audiovisual experience. Users can explore environments, manipulate objects, and communicate with characters through viewpoint control and text instructions, with their actions shaping both the shared state and subsequent experiences. By connecting world-state evolution with experience generation in acontinuous interaction loop, the framework offers an approach to building interactive worlds that retain their history, evolve through action, and persist beyond any individual observer.

View arXiv pageView PDFProject pageGitHub285Add to collection

Get this paper in your agent:

hf papers read 2610\.19726

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

Models citing this paper1

#### XGENlabs/XGEN-JING Image-Text-to-Video• Updatedabout 8 hours ago • 2 • 185

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.19726 in a dataset README.md to link it from this page.

Spaces citing this paper4

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.