From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting

TMLR Paper7185 Authors

Abstract: Recent progress in foundation models has enabled strong zero-shot performance for time series forecasting. In this work, we show that such capabilities can also emerge from tabular foundation models. We introduce TabPFN-TS, a simple method that treats forecasting as a tabular regression problem by combining lightweight temporal featurization with the pretrained TabPFN-v2. This formulation requires no time-series–specific pretraining and naturally supports both univariate and covariate-informed forecasting. Despite its compact size (11M parameters), TabPFN-TS achieves state-of-the-art performance on covariate-informed forecasting and competitive accuracy on univariate forecasting across the GIFT-Eval and fev-bench benchmarks. We further provide controlled analyses examining how the model interprets temporal structure, how featurization choices affect accuracy, and how forecasts change under alternative tabular backbones. Together, our results demonstrate that tabular foundation models—when paired with suitable temporal features—offer an efficient and versatile alternative for forecasting, bridging tabular and time-series learning within a unified framework.

Submission Type: Long submission (more than 12 pages of main content)

Changes Since Last Submission:

- Added comparison to classical tabular models (XGBoost, LightGBM, CatBoost) under identical temporal featurization (Section 5.4), isolating the contribution of the TabPFNv2 backbone from the feature design.
- Added Appendix A.10 discussing concrete inference optimization strategies, including patch-based sequence compression, series batching, and sparse attention, along with a note on the immediate practical workaround of data-parallel inference.
- Added full results tables (Table 2 and 3 in Appendix) to provide the exact numbers of all models across all GIFT-Eval tasks.
- Updated figures (minor, for aesthetics only).
- Fixed typo

Assigned Action Editor: ~Jacek_Cyranka1

Submission Number: 7185