Google开源了TimesFM-3，单次前向就能做多变量时间序列预测，比其他模型表现好多了。
Google Research发布了TimesFM-3，这是一个先进的时间序列基础模型。该模型仅需单次前向传播即可实现准确的多变量时间序列预测。TimesFM-3在多个主要基准测试中显著优于其他预测模型。模型已在GitHub和Hugging Face平台可用。
this is huge! fyi, TimesFM-3 is available on GitHub and Hugging Face - https://t.co/BMg45uy1lq - h...
this is huge! fyi, TimesFM-3 is available on GitHub and Hugging Face - github.com/google-researc… - huggingface.co/google/timesfm… Google Research @GoogleResearch Introducing TimesFM-3, a state-of-the-art time series foundation model that enables accurate multivariate time series forecasting in a single forward pass, significantly outperforming other forecasting models across major benchmarks. More on the blog → goo.gle/4x5WGpD 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 8 👀 709 📊 2 ⚡