arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08971cs.CVcs.RO
收藏

WorldArena: 一个用于评估具身世界模型感知与功能效用的统一基准

WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

Tsinghua University, Beijing, China（清华大学）；Shanghai Jiao Tong University, Shanghai, China（上海交通大学）；The University of Hong Kong, Hong Kong SAR, China（香港大学）；Princeton University, Princeton, NJ, USA（普林斯顿大学）；Chinese Academy of Sciences, Beijing, China（中国科学院）；University of Science（科学技术大学）；Peking University, Beijing, China（北京大学）；National University of Singapore, Singapore（新加坡国立大学）
Yu Shang, Zhuohang Li, Yiding Ma, Weikang Su, Xin Jin, Ziyou Wang, Lei Jin, Xin Zhang, Yinzhou Tang, Haisheng Su, Chen Gao, Wei Wu, Xihui Liu, Dhruv Shah, Zhaox… 展开作者

Yu Shang, Zhuohang Li, Yiding Ma, Weikang Su, Xin Jin, Ziyou Wang, Lei Jin, Xin Zhang, Yinzhou Tang, Haisheng Su, Chen Gao, Wei Wu, Xihui Liu, Dhruv Shah, Zhaoxiang Zhang, Zhibo Chen, Jun Zhu, Yonghong Tian, Tat-Seng Chua, Wenwu Zhu, Yong Li

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

WorldArena是一个统一的基准，用于评估具身世界模型的感知和功能效用，揭示高视觉质量与强具身任务能力之间的差距。

摘要：

尽管世界模型已成为具身智能的核心，通过行动条件预测使代理能够推理环境动态，但其评估仍碎片化。当前对具身世界模型的评估大多集中在感知保真度（例如视频生成质量），忽视了这些模型在下游决策任务中的功能效用。在本工作中，我们引入WorldArena，一个统一的基准，旨在系统地评估具身世界模型的感知和功能维度。WorldArena通过三个维度评估模型：视频感知质量，通过六个子维度的16项指标测量；具身任务功能，评估世界模型作为数据引擎、策略评估器和行动规划器的整合能力，并结合主观人类评估。此外，我们提出了EWMScore，一个整合多维表现的综合指标。通过在14个代表性模型上的广泛实验，我们揭示了显著的感知-功能差距，表明高视觉质量并不一定转化为强的具身任务能力。WorldArena基准及其公开排行榜已发布在https://world-arena.ai，为跟踪真正功能世界模型在具身AI中的进展提供了框架。

英文摘要：

While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their evaluation remains fragmented. Current evaluation of embodied world models has largely focused on perceptual fidelity (e.g., video generation quality), overlooking the functional utility of these models in downstream decision-making tasks. In this work, we introduce WorldArena, a unified benchmark designed to systematically evaluate embodied world models across both perceptual and functional dimensions. WorldArena assesses models through three dimensions: video perception quality, measured with 16 metrics across six sub-dimensions; embodied task functionality, which evaluates world models as data engines, policy evaluators, and action planners integrating with subjective human evaluation. Furthermore, we propose EWMScore, a holistic metric integrating multi-dimensional performance into a single interpretable index. Through extensive experiments on 14 representative models, we reveal a significant perception-functionality gap, showing that high visual quality does not necessarily translate into strong embodied task capability. WorldArena benchmark with the public leaderboard is released at https://world-arena.ai, providing a framework for tracking progress toward truly functional world models in embodied AI.

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。

↑