Machine learningTime-series forecasting
Sundial:生成式时间序列基础模型
Sundial 是由清华大学的 Yong Liu 及其同事(ICML 2025)提出的一系列生成式时间序列基础模型。Sundial 在大规模、多样化的时间序列语料库上进行了预训练,采用了一种基于分解的架构,并配以生成式预测头,以产生概率性的多步预测。它代表了向通用、零样本能力模型在真实世界时间预测任务中的转变。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Liu, Y., Qin, G., Shi, X., Hu, T., Wang, J., & Long, M. (2025). Sundial: A family of highly capable time series foundation models. ICML. link ↗
如何引用本页
ScholarGate. (2026, June 2). Sundial (Generative Time-Series Foundation Models). ScholarGate. https://scholargate.app/zh/deep-learning/sundial
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Chronos:一种用于时间序列预测的标记化基础模型深度学习↔ compare
- Moirai:通用时间序列预测Transformer深度学习↔ compare
- TimesFM:面向时间序列预测的仅解码器基础模型深度学习↔ compare