SOURCE-LINKED INTELLIGENCE

$t_0$: A Time-Series Foundation Model for Forecasting with Context

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

We present $t_0$, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: $\texttt{t0-alpha}$ and $\texttt{t0-beta}$, respectively 102M and 256M parameters. Both condition their forecasts on target history, past covariates, and known-future covariates, without task-specific retraining. Their transformer layers alternate attention along time and across variates. They produce probabilistic forecasts through quantile predictions. Pretraining combines curated public data with synthetic generator families constructed to contain covaria

Read original source ↗ Open in workspace

recordType

paper

region

Global