arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

从生成到模拟:世界模型距离真正的模拟器还有多远?

From Generation to Simulation: How Far Are World Models from Being True Simulators?

Tong Wang, Huan Deng, Mucheng Yang, Yang He, Xiaohui Kuang, Gang Zhao

arXiv 2608.23070首次发表:更新:

发表机构

Institute of Systems Engineering, Academy of Military Sciences(军事科学院系统工程研究院)

机构由 AI 辅助整理,请以论文原文为准。

AI 中文总结

本研究通过系统评估200篇相关成果,分析了潜在动力学等3条技术路线的世界模型在传统模拟器8项能力上的表现,指出其在状态反馈等方面的缺陷并提出6个研究方向。

AI 中文摘要

随着扩散模型和大规模视频生成的快速发展,生成式世界模型愈发被期待能替代传统模拟器,包括物理引擎、游戏引擎和强化学习环境。然而,从生成到模拟的差距尚未得到系统评估。我们采用外部标尺开展基于能力的研究,该标尺涵盖传统模拟器的8项能力:资产构建、物理引擎、交互性、可控性、稳定性、状态反馈、多样性以及评估指标。我们梳理了3条主要技术路线——潜在动力学、视频生成和联合嵌入预测,并将2018年至2026年6月间发表的200篇代表性成果精准映射到这些能力维度。分析显示,世界模型已在特定场景下实现了交互性和可控性的功能替代,但在物理定律的形式化保证、结构化状态反馈以及可复现的长时序演化方面仍不及传统模拟器。状态反馈是所有路线中最被忽视的共性缺陷:163篇实现类论文中仅有6篇公开了用于查询实体状态或物理参数的运行时接口。我们确定了6个未来研究方向:形式化物理、统一动作接口、一级状态反馈、长时序稳定性、下游效用评估以及跨路线融合。项目页面:this https URL

英文摘要

With the rapid progress of diffusion models and large-scale video generation, generative world models are increasingly expected to replace traditional simulators, including physics engines, game engines, and reinforcement-learning environments. Yet the remaining distance from generation to simulation lacks a systematic assessment. We present a capability-based study using an external yardstick: eight capabilities of a traditional simulator, namely asset construction, physics engine, interaction, controllability, stability, state feedback, diversity, and evaluation metrics. We trace three main technical routes--latent dynamics, video generation, and joint-embedding prediction--and map exactly 200 representative works published from 2018 to June 2026 onto these capabilities. Our analysis shows that world models have achieved functional substitution in interaction and controllability for specific scenarios, but remain short of traditional simulators in formal guarantees of physical laws, structured state feedback, and reproducible long-horizon evolution. State feedback is the most neglected cross-route shortcoming: only 6 of 163 implementation papers expose a runtime interface for querying entity states or physical parameters. We identify six research directions: formalized physics, a unified action interface, first-class state feedback, long-horizon stability, downstream-utility evaluation, and cross-route hybridization. Project page: https://github.com/AtongWang/world-model-simulators

Comments42 pages, 23 figures, 2 tables. Project page: https://github.com/AtongWang/world-model-simulators

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑