Lotus：通过预测学习理解时间序列
原标题：Lotus: Learning to Understand Time-series by Learning to Forecast
AI 摘要
该论文提出了一种名为 Lotus 的时间序列语言模型，通过「预测性 grounding」预训练原则，要求语言对齐的时间序列表示在适配下游任务前仍能预测未来演化。Lotus 将每个时间序列通道划分为不重叠的 patch 并映射到 LLM 嵌入空间，同时提出结合原始 patch 与频谱表示的时频 patch 表示。在三种语言模型骨干和六个下游数据集上，Lotus 以极少可训练参数取得最佳平均性能，并在 TSRBench 上超越规模大 25–50 倍的模型。
正文节选
Lotus: Learning to Understand Time-series by Learning to Forecast Abstract Time-series language models typically align numerical signals with language using labels, captions, or question–answer pairs. Although such supervision encourages linguistic representations, it does not explicitly require them to preserve information about how the underlying time-series signal evolves. We introduce forecast grounding, a pretraining principle that requires language-aligned time-series representations to re