Skip to content
Live
Hugging Face Daily Papers·· yesterday65

WorldRuler: Interactive World Modeling under Configurable Rules

WorldRuler: Interactive World Modeling under Configurable Rules

Brief overview

WorldRuler organizes rule definitions, dependencies, and object states through executable 3D rule graphs, achieving persistent saving and loading of rule states, and accurately implementing rule-induced visual changes on specified objects and attributes. The model supports dynamic object binding and counterfactual reconstruction training, and has built the RuleVerse dataset, which includes detailed state and event annotations. Experiments have validated its effectiveness in preserving rule consistency and accurately implementing rule results.

Article

Published on Nov 18

Authors:

,

,

,

,

,

Abstract

A rule-graph-based generative world model preserves user-defined rules and world states across saving and loading while accurately realizing rule-induced visual changes on designated objects and attributes.

Rules govern how player actions change interactive worlds. Different rules create distinct gameplay experiences within similar scenes and action spaces. For customizable gameplay, generative world models must follow user-defined rules beyond real-world behaviors. However, realizing user-defined rules presents two challenges: Rule-State Persistence and Rule-to-Visual Realization. The former requires preserving rule definitions, dependencies, and world states across saving and loading, so that restored worlds follow the established rules. The latter requires accurately realizing rule-induced changes on designated objects and attributes, particularly when affected objects are unseen. In this paper, we propose WorldRuler, which organizes rule definitions, dependencies, and object states in an executable 3D rule graph and connects rule execution, video generation, and perceptual feedback in a closed loop. The graph supports joint saving and restoration of rules and world states, while dynamic object binding grounds rule-specified entities in visual instances and uses stored states to constrain generation from their first appearance. We further introduce object attribute state replacement and counterfactual reconstruction training, enabling accurate attribute control and compatible appearance and motion changes while limiting interference with unrelated content. We develop an automated data collection and annotation pipeline using GTA-V and Habitat to construct RuleVerse, a dataset of rule-driven interactions with detailed state and event annotations, including cases where rules take effect before affected objects become visible. Extensive experiments demonstrate the effectiveness of WorldRuler in preserving rule-state consistency across saving and loading and accurately realizing rule outcomes on designated objects and attributes.

View arXiv page View PDF Project page GitHub 7 Add to collection

Get this paper in your agent:

hf papers read 2611.24869

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.24869 in a model README.md to link it from this page.

Datasets citing this paper 1

AlayaLab/RuleVerse

Preview •

Updated 44 minutes ago

•

98

•

1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.24869 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Source: Hugging Face Daily Papers · huggingface.co