Google 发布 TimesFM-3：零样本多变量时间序列预测基础模型
原标题：TimesFM-3: A zero-shot foundation model for multivariate forecasting
AI 摘要
Google Research 发布了 TimesFM-3，这是一个 3.3 亿参数的多变量时间序列基础模型，支持零样本预测，并在 Gift-Eval、FEV-Bench 和 Time 等基准测试中取得领先性能。该模型采用解码器 Transformer 架构和连续补丁掩码策略，可在单次前向传播中生成整个预测区间，并支持外部协变量。相比前代模型，TimesFM-3 显著提升了多变量场景下的预测准确性。
正文节选
August 31, 2026 Ayush Jain and Rajat Sen, Research Scientists, Google Research We introduce TimesFM-3, a state-of-the-art time series foundation model that enables highly accurate multivariate time series forecasting in a single forward pass, significantly outperforming other forecasting models across major benchmarks. Since the debut of TimesFM in 2024, we’ve seen the adoption of time-series foundation models for real-world time-series forecasting tasks across multiple domains, such as retail,