# Investigating the effects of the patch size in Time Series Foundation Models

**Authors:** Jad Yehya, Andrei-Tiberiu Pantea, Aymeric Dieuleveut, Matthieu Kowalski, Thomas Moreau  
**Lab:** École Polytechnique · **Published:** 2 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.02750) · [PDF](https://arxiv.org/pdf/2611.02750) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.02750.html)

## Key numbers

- **97**: Across 97 GIFT-Eval tasks

## Abstract

Patch size is a central design choice in patch-based time-series foundation models, controlling temporal resolution, sequence length, and computational cost. We study how this choice interacts with transformer architecture through a controlled comparison of encoder-only and decoder-only forecasting models trained with the same data mixture and optimization budget. Across 97 GIFT-Eval tasks, encoder-only models consistently benefit from smaller patches, whereas decoder-only performance follows a U-shaped trend, with an intermediate patch size performing best in aggregate. Dataset-level results further show that the preferred decoder patch size increases with the forecasting horizon. For encoder-only models, increasing context length improves performance across patch sizes, although the gains diminish beyond a context length of 2048. Finally, training-compute and CPU-latency Pareto analyses reveal complementary regimes: decoder-only models provide efficient low-cost alternatives, while encoder-only models attain the highest overall accuracy. These results show that the choice of patch size and architecture should be made depending on the forecasting horizon and deployment constraints.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.