Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient. We introduce FlowState, a novel TSFM architecture that achieves sampling-rate-equivariant forecasting through a unified design that pairs a state space model (SSM) encoder with a functional basis decoder (FBD). This design enables continuous-time modeling and dynamic time-scale adjustment, allowing FlowState to inherently generalize across all possible temporal resolutions, and dynamically adjust the forecasting horizons without retraining. We further propose an efficient pretraining strategy that improves robustness and accelerates training. Despite being one of the smallest TSFMs, FlowState achieves state-of-the-art results on the widely used GIFT-Eval benchmark, while demonstrating superior adaptability to unseen sampling rates. Our detailed analyses confirm the effectiveness of its components, and we demonstrate its unique ability to adapt to varying input sampling rates.

翻译：现有基于Transformer变体的时间序列基础模型缺乏对不同采样率的适应性，难以泛化至不同上下文长度与目标长度，且计算效率低下。我们提出FlowState，一种新颖的时间序列基础模型架构，通过将状态空间模型编码器与函数基解码器相结合的统一设计实现采样率等变预测。该架构支持连续时间建模与动态时间尺度调整，使FlowState能够天然泛化至所有可能的时域分辨率，并无需重新训练即可动态调整预测视界。我们进一步提出高效预训练策略，以提升鲁棒性并加速训练。尽管FlowState是尺寸最小的基础模型之一，它在广泛使用的GIFT-Eval基准上取得了最先进的结果，同时展现出对未见采样率的卓越适应性。详细分析验证了其各组成部分的有效性，并展示了其适应不同输入采样率的独特能力。