---
title: TimEE In-Context Time Series Classification
emoji: 📈
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 6.20.0
app_file: app.py
short_description: Classify time series in-context with TimEE foundation model
python_version: "3.12"
startup_duration_timeout: 30m
---

# TimEE: End-to-end Time Series Classification via In-Context Learning

TimEE is a 4.5M-parameter foundation model for time series classification that works
via in-context learning — it classifies test series in a single forward pass given labeled
training examples, with no per-dataset training or fine-tuning required.

This demo lets you provide labeled support time series and unlabeled query series in CSV
format, and shows the model's predictions with class probability distributions.

- 📄 Paper: https://arxiv.org/abs/2607.07500
- 🐙 GitHub: https://github.com/automl/timee
- 🤗 Model: https://huggingface.co/liamsbhoo/timee