Machine learningTime-series forecasting
TiRex：基于 xLSTM 的零样本时间序列预测模型
TiRex 是由 NX-AI xLSTM 团队（Auer et al.）于 2025 年推出的一种预训练零样本时间序列预测模型。TiRex 基于扩展长短期记忆（xLSTM）架构构建，在多样化的时间序列语料库上进行了大规模训练，无需任何微调即可预测未见过的数据集。其核心思想是利用增强的上下文学习（in-context learning）：模型将所有可用的历史数据作为上下文进行读取，并直接从该上下文中生成短期和长期预测。
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
- Auer, A., Podest, P., Klotz, D., Böck, S., Klambauer, G., & Hochreiter, S. (2025). TiRex: Zero-shot forecasting across long and short horizons with enhanced in-context learning. arXiv preprint. link ↗
如何引用本页
ScholarGate. (2026, June 2). TiRex (xLSTM-based Zero-Shot Forecasting Model). ScholarGate. https://scholargate.app/zh/deep-learning/tirex
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.
Compare side by side →