WorldRuler提出可配置规则驱动的交互式世界模型框架
WorldRuler: Interactive World Modeling under Configurable Rules
搞世界模型或游戏生成的可以看看这篇:WorldRuler用3D规则图把规则执行和视频生成接成闭环,存档读档不丢状态,规则还能作用到还没出现的物体上。数据集是用GTA-V和Habitat自动标注出来的,复现路径比较清晰。
一篇新论文提出WorldRuler,一种让生成式世界模型遵循用户自定义规则的框架,解决两个核心难题:Rule-State Persistence(存档与读档时保留规则定义、依赖关系和世界状态)和 Rule-to-Visual Realization(把规则引发的变化准确呈现在指定对象上,包括尚未出现的对象)。
技术机制上,WorldRuler用可执行的3D规则图组织规则定义、依赖与对象状态,把规则执行、视频生成和感知反馈串成闭环。动态对象绑定将规则指定的实体锚定到视觉实例,并在对象首次出现时就用已存状态约束生成;对象属性状态替换与反事实重建训练则实现准确的属性控制,同时限制对无关内容的干扰。
数据方面,作者基于GTA-V和Habitat搭建自动采集标注流水线,构建了RuleVerse数据集,包含带详细状态与事件标注的规则驱动交互,涵盖规则在受影响对象可见之前就已生效的场景。实验显示该框架在存档读档的规则-状态一致性和规则结果落点上均有提升。
WorldRuler: Interactive World Modeling under Configurable Rules
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.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:WorldRuler、世界模型、视频生成、RuleVerse,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Mingliang Zhai, Chuanhao Li, Jiaming Tan, Zhen Li, Yuwei Wu, Yunde Jia, Zian Meng, Yuanyang Yin, Kaipeng Zhang),经 AITOP 多维评分管线结构化提炼。