Skip to content

论文HF Daily Papers · arXiv 2611.1077115 天前

WorldFoundry开源具身世界模型评测基建,收录270模型与74基准 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:WorldFoundry: Towards Unified Infrastructure for World Intelligence(HF Daily Papers · arXiv 2611.10771)

核心内容 ​

针对当前视觉生成模型虽逼真但缺乏持久状态与因果动力学的痛点,研究团队提出世界模型应作为预测性动力系统的新定义,并正式发布开源基础设施WorldFoundry。该平台旨在解决异构系统间评测不可复现的难题,目前已收录270个模型条目、74个基准测试集及62项注册指标,覆盖视频生成、3D/4D重建、具身动作及交互式世界系统四大核心模态,为具身智能研究提供标准化的验证底座。

技术架构上,WorldFoundry统一了模型发现、运行时准备、执行编排及工件管理全流程,通过模态适配器保留原生输入输出语义与评估协议。系统采用显式清单与持久化工件契约,将执行就绪度与评估声明分离,确保每项评分均可追溯至具体支撑证据。该框架实现了跨模态的可控动力学对比,使研究者能在统一标准下验证模型的感知接地、状态保持及闭环交互能力,填补了世界智能量化评测的工程空白。

关键看点 ​

  • 资产规模:内置270个模型、74个基准及62项指标,覆盖视频、3D/4D及具身动作等关键模态
  • 架构机制:采用模态适配器保留原生语义,利用显式清单与工件契约实现执行与评估解耦
  • 评测范式:定义世界模型为预测性动力系统,确立包含感知接地与闭环交互的五维评估框架
  • 工程价值:支持异构系统间持久可控动力学的可复现比较,提供证据感知的评分追溯体系

工程与产业观察 ​

该设施标志着具身世界模型研究从“视频生成”转向“物理仿真验证”的工程化拐点。对于算法工程师,其标准化的Artifact契约与解耦评测流程,解决了Sora类模型在机器人Sim-to-Real中难以量化物理一致性的痛点;统一的Benchmark基建将加速具身大模型在状态保持与因果推理能力的迭代收敛。

英文摘要 (Abstract) ​

Visual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelling outputs may lack persistent state, physical dynamics, or causally consistent responses to interactions. We define a generative world model as a predictive dynamical system that maintains a persistent, history-conditioned representation of an environment, updates that representation in response to actions or interventions, and generates temporally coherent trajectories that reflect outcomes under observed and counterfactual interventions. From this definition, we derive an intelligence-oriented framework spanning perceptual grounding, persistent state modeling, controllable transformation, dynamics-aware prediction, and closed-loop interaction. We present WorldFoundry, open-source infrastructure for reproducible inference and evaluation across video, 3D and 4D, embodied action, and interactive world systems. WorldFoundry unifies model and benchmark discovery, runtime and asset preparation, execution orchestration, artifact management, and interactive visualization, while modality-specific adapters preserve native inputs, execution semantics, output representations, and evaluation protocols. Explicit manifests, durable artifact contracts, and evidence-aware scorecards separate execution readiness from evaluative claims, making each claim traceable to its supporting artifacts. The catalog contains 270 model entries, 74 benchmarks, and 62 registered metric entries, with readiness and execution evidence recorded separately. WorldFoundry enables reproducible comparison of persistent, controllable dynamics across heterogeneous systems, advancing the field from perceptual synthesis toward measurable world intelligence.

Hugging Face Daily Papers 热度:42 upvotes 作者:Juanxi Tian, Jiadong Hou, Baiang Li, Xin Lin, Zhengbo Jiao, Weijia Zhang, Yeying Jin, Truong Nguyen, Haitian Zheng, Zhifei Zhang, Jianfei Yang, Ming-Hsuan Yang, Felix Heide, Wei Xiong, Enze Xie, Wanhu…

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. HF Daily Papers · arXiv 2611.10771:WorldFoundry: Towards Unified Infrastructure for World Intelligence ↗访问 2026-11-10