---
license: other
license_name: tsicl-v1-license-v1.0
license_link: LICENSE
model_id: ts-icl
tags:
- time series
- foundation model
- time series imputation
- timeseries forecasting
pipeline_tag: time-series-forecasting
paper: https://arxiv.org/abs/2606.05878
library_name: tsicl
---

# TS-ICL: A Flexible Time-Index Foundation Model for Time Series via In-Context Learning

## Installation
```bash
pip install tsicl
```

Source code available at [GitHub - EDF-Lab/ts-icl](https://github.com/EDF-Lab/ts-icl).

Example notebooks can be found at [GitHub - EDF-Lab/ts-icl/notebooks](https://github.com/EDF-Lab/ts-icl/tree/main/notebooks).

Check also the doc [here](https://edf-lab.github.io/ts-icl/).

## License

TS-ICL weights and code are released under a non-commercial license, see [LICENSE](LICENSE).

## Citation

If you use TS-ICL for research purposes, please consider citing the associated **[TS-ICL](https://arxiv.org/abs/2606.05878) paper**:

```bibtex
@article{lenaour2026tsicl,
  title={TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning},
  author={Le Naour, Etienne and Nabil, Tahar and Petralia, Adrien},
  journal={arXiv preprint arXiv:2606.05878},
  year={2026}
}
```