arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.23152cs.AI
收藏

一致性三元组作为一般世界模型的定义原则

The Trinity of Consistency as a Defining Principle for General World Models

Jingxuan Wei, Siyuan Li, Yuhang Xu, Zheng Sun, Junjie Jiang, Hexuan Jin, Caijun Jia, Honghao He, Xinglong Xu, Xi bai, Chang Yu, Yumou Liu, Junnan Zhu, Xuanhe Zh… 展开作者

Jingxuan Wei, Siyuan Li, Yuhang Xu, Zheng Sun, Junjie Jiang, Hexuan Jin, Caijun Jia, Honghao He, Xinglong Xu, Xi bai, Chang Yu, Yumou Liu, Junnan Zhu, Xuanhe Zhou, Jintao Chen, Xiaobin Hu, Shancheng Pang, Bihui Yu, Ran He, Zhen Lei, Stan Z. Li, Conghui He, Shuicheng Yan, Cheng Tan

AI总结:

本文提出一致性三元组作为定义通用世界模型的原则,通过系统回顾多模态学习的演变,引入CoW-Bench基准测试,明确未来发展方向。

摘要:

构建能够学习、模拟和推理客观物理定律的世界模型,构成了追求人工通用智能的基础挑战。最近以Sora为代表的视频生成模型的进步展示了数据驱动的扩展定律在近似物理动态方面的潜力,而新兴的统一多模态模型(UMM)提供了一种有前途的架构范式,用于整合感知、语言和推理。尽管有这些进展,该领域仍然缺乏一个原理性的理论框架,该框架定义了通用世界模型所必需的本质属性。在本文中,我们提出世界模型必须建立在一致性三元组的基础上:模态一致性作为语义接口,空间一致性作为几何基础,时间一致性作为因果引擎。通过这种三重视角,我们系统地回顾了多模态学习的演变,揭示了从松散耦合的专业模块向统一架构演进的轨迹,后者能够促进内部世界模拟器的协同涌现。为了补充这一概念框架,我们引入了CoW-Bench,一个专注于多帧推理和生成场景的基准测试。CoW-Bench在统一的评估协议下评估视频生成模型和UMM。我们的工作建立了一条通往通用世界模型的原理性路径,既明确了当前系统的局限性,也指明了未来进步的架构要求。

英文摘要:

The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial General Intelligence. Recent advancements represented by video generation models like Sora have demonstrated the potential of data-driven scaling laws to approximate physical dynamics, while the emerging Unified Multimodal Model (UMM) offers a promising architectural paradigm for integrating perception, language, and reasoning. Despite these advances, the field still lacks a principled theoretical framework that defines the essential properties requisite for a General World Model. In this paper, we propose that a World Model must be grounded in the Trinity of Consistency: Modal Consistency as the semantic interface, Spatial Consistency as the geometric basis, and Temporal Consistency as the causal engine. Through this tripartite lens, we systematically review the evolution of multimodal learning, revealing a trajectory from loosely coupled specialized modules toward unified architectures that enable the synergistic emergence of internal world simulators. To complement this conceptual framework, we introduce CoW-Bench, a benchmark centered on multi-frame reasoning and generation scenarios. CoW-Bench evaluates both video generation models and UMMs under a unified evaluation protocol. Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑