Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperforming on challenging benchmarks. This paper presents TempoPFN, a univariate time series foundation model based on linear Recurrent Neural Networks (RNNs) pre-trained exclusively on synthetic data. The model uses a GatedDeltaProduct architecture with state-weaving for fully parallelizable training across sequence lengths, eliminating the need for windowing or summarization techniques while maintaining robust temporal state-tracking. Our comprehensive synthetic data pipeline unifies diverse generators, including stochastic differential equations, Gaussian processes, and audio synthesis, with novel augmentations. In zero-shot evaluations on the Gift-Eval, fev-bench and Chronos-ZS benchmarks, TempoPFN achieves top-tier competitive performance, outperforming all existing synthetic-only approaches and surpassing the majority of models trained on real-world data, while being more efficient than existing baselines by leveraging fully parallelizable training and inference. We open-source our complete data generation pipeline and training code, providing a reproducible foundation for future research.

翻译：零样本时间序列预测的基础模型在高效长时程预测和可复现性方面面临挑战，现有纯合成数据方法在具有挑战性的基准测试中表现不佳。本文提出了TempoPFN，一种基于线性循环神经网络（RNN）的单变量时间序列基础模型，完全通过合成数据进行预训练。该模型采用带有状态编织机制的GatedDeltaProduct架构，实现了跨序列长度的完全并行化训练，无需使用窗口化或摘要技术，同时保持了稳健的时间状态跟踪能力。我们全面的合成数据流水线统一了多种生成器，包括随机微分方程、高斯过程和音频合成方法，并引入了新颖的数据增强策略。在Gift-Eval、fev-bench和Chronos-ZS基准测试的零样本评估中，TempoPFN取得了顶尖的竞争性能，超越了所有现有的纯合成数据方法，并优于大多数基于真实世界数据训练的模型，同时通过完全并行化的训练和推理机制，比现有基线模型更为高效。我们开源了完整的数据生成流水线和训练代码，为未来研究提供了可复现的基础框架。