Skip to content

TabPFN-TS

Home / Concepts / TabPFN-TS

TabPFN-TS

Auto-generated stub. Edit this file to add more details.

A Transformer-based foundation model for tabular and time series data that treats forecasting as an in-context regression problem.

Why It Matters

The paper identifies it as a distinct model class for covariate-target relationship modeling in TSFMs compared to autoregressive foundations.

Evidence

TabPFN-TS captures these relationships more effectively than Chronos-2, especially for short horizons

Metadata & Links