README.md

---
language:
- en
library_name: timee-ts
license: apache-2.0
pipeline_tag: other
tags:
- time-series
- classification
- in-context-learning
- transformer
---

# TIMEE: Time Series Classification via In-Context Learning

TIMEE is a pretrained transformer for time series classification, introduced in [TimEE: End-to-end Time Series Classification via In-Context Learning](https://huggingface.co/papers/2607.07500).

It classifies test series in a **single forward pass** given labeled training examples — no per-dataset training or fine-tuning required.

[![arXiv](https://img.shields.io/badge/arXiv-2607.07500-b31b1b.svg)](https://arxiv.org/abs/2607.07500)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)

Official GitHub Repository: https://github.com/automl/timee

## Usage

```bash
pip install timee-ts
```

```python
from timee import TimeeClassifier
import numpy as np

# Downloads weights automatically on first use
clf = TimeeClassifier.from_pretrained()

# X: (n_samples, n_channels, seq_len) float32
X_train = np.random.randn(20, 1, 256).astype(np.float32)
y_train = np.array([0, 1] * 10)
X_test  = np.random.randn(5,  1, 256).astype(np.float32)

predictions, probabilities = clf.predict(X_train, y_train, X_test)
```

Labels can be any type (`int`, `str`, etc.).
Datasets with more than 10 classes are handled automatically via one-vs-rest.

## UCR Benchmark Results

| Dataset            | Classes | Accuracy | ROC AUC |
|--------------------|---------|----------|---------|
| ArrowHead          | 3       | 76.6 %   | 0.964   |
| ECG5000            | 5       | 95.0 %   | 0.952   |
| GunPoint           | 2       | 98.7 %   | 0.997   |
| ItalyPowerDemand   | 2       | 96.0 %   | 0.993   |
| TwoPatterns        | 4       | 99.8 %   | 1.000   |

Results use the default 4-member ensemble (interpolate × {256, 512} × {raw, first-difference}).

## Model Details

- **Parameters:** 4,557,322
- **Input:** univariate or multivariate time series, any length
- **Output:** class probabilities over up to 10 classes (OvR for more)
- **Inference:** single forward pass; no dataset-specific adaptation

## Citation

```bibtex
@misc{küken2026timeeendtoendtimeseries,
      title={TimEE: End-to-end Time Series Classification via In-Context Learning},
      author={Jaris Küken and Shi Bin Hoo and Martin Mráz and Frank Hutter and Lennart Purucker},
      year={2026},
      eprint={2607.07500},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2607.07500},
}
```