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~~
arXiv 2610.34797cs.LG
收藏

TimeWorld:面向时间序列预测的动作条件多模态世界模型

TimeWorld: Towards Action-Conditioned Multimodal World Models for Time Series Forecasting

The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

Hang Ni, Weijia Zhang, Hao Liu

AI总结:

针对现有时间序列世界模型的不足,提出插件框架TimeWorld,通过PLM和ACL模块适配预训练TSFM,在TSWM-Bench基准上验证了文本前缀适配可提升预测性能,为动作条件时间序列预测提供新方案。

摘要:

时间序列预测支持在线零售、网络管理等Web应用中的决策制定,其中计划执行的动作可重塑未来动态。世界模型为预测此类依赖动作的变化提供了自然范式,超越了仅外推历史模式的范畴。然而,现有时间序列世界模型(TSWM)通常依赖固定的、特定领域的协变量模式,限制了灵活的干预指定;而多模态预测器则主要将文本视为被动预测上下文。为探究这些差距,我们引入TSWM-Bench,这是一个面向多模态TSWM的跨领域基准,涵盖7个真实世界数据集,其中文本干预基于记录的动作-结果数据。我们的评估显示,尽管针对特定数据集进行了训练,传统多模态预测器的表现仍逊于仅使用历史数据的时间序列基础模型(TSFM),而简单的文本前缀适配可在所有评估的TSFM主干上提升预测性能。这些发现表明,预训练的TSFM编码了时间动态的隐式世界知识,为超越传统多模态融合的动作条件建模提供了坚实基础。基于这一见解,我们提出TimeWorld,这是一个插件框架,通过显式的动作-响应建模来适配预训练的TSFM。具体而言,原型引导的潜在调制(PLM)模块通过组合代表性响应原型,基于动作和历史模式调制未来表示,从而将文本动作与时间动态关联起来。动作对比学习(ACL)组件通过对比在相同历史下不同替代干预下的这些更新,强化了特定动作的响应建模,在区分动作类型的同时保留了相对强度关系。

英文摘要:

Time series forecasting supports decision-making in web applications such as online retail and network management, where planned actions can reshape future dynamics. World models provide a natural paradigm for predicting such action-dependent changes beyond extrapolating historical patterns. However, existing time series world models (TSWMs) typically rely on fixed, domain-specific covariate schemas that limit flexible intervention specification, while multimodal forecasters treat text primarily as passive predictive context. To investigate these gaps, we introduce TSWM-Bench, a cross-domain benchmark for multimodal TSWMs spanning seven real-world datasets, with textual interventions grounded in recorded action--outcome data. Our evaluation reveals that conventional multimodal forecasters underperform history-only time series foundation models (TSFMs) despite dataset-specific training, whereas simple text-prefix adaptations improve forecasting across all evaluated TSFM backbones. These findings suggest that pretrained TSFMs encode implicit world knowledge of temporal dynamics, offering a strong foundation for action-conditioned modeling beyond conventional multimodal fusion. Building on this insight, we propose TimeWorld, a plug-in framework that adapts pretrained TSFMs through explicit action-response modeling. Specifically, the Prototype-Guided Latent Modulation (PLM) module grounds textual actions in temporal dynamics by composing representative response prototypes to modulate future representations based on the action and historical patterns. The Action Contrastive Learning (ACL) component strengthens action-specific response modeling by contrasting these updates under alternative interventions sharing the same history, distinguishing action types while preserving relative intensity relationships.

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。

↑