Toto 2.0：时间序列预测进入规模化时代

Toto 2.0: Time Series Forecasting Enters the Scaling Era

May 19, 2026

作者: Emaad Khwaja, Chris Lettieri, Gerald Woo, Eden Belouadah, Marc Cenac, Guillaume Jarry, Enguerrand Paquin, Xunyi Zhao, Viktoriya Zhukov, Othmane Abou-Amal, Chenghao Liu, Ameet Talwalkar, David Asker

cs.AI

摘要

我们证明时间序列基础模型具有可扩展性：单个训练方案可产生从400万到25亿参数可靠的预测质量提升。我们发布了Toto 2.0，这是一个在此训练方案下训练的五款开源权重预测模型系列。Toto 2.0系列在三个预测基准上创造了新的最优水平：BOOM（我们的可观测性基准）、GIFT-Eval（标准通用基准）以及近期提出的抗污染TIME基准。本报告描述了我们的实验结果，并详细说明Toto 2.0背后的设计决策：其架构与训练方案、训练数据以及u-muP超参数迁移管线。所有五个基础检查点均根据Apache 2.0许可证发布。

English

We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters. We release Toto 2.0, a family of five open-weights forecasting models trained under this recipe. The Toto 2.0 family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. This report describes our experimental results and details the design decisions behind Toto 2.0: its architecture and training recipe, training data, and the u-muP hyperparameter transfer pipeline. All five base checkpoints are released under Apache 2.0.