Towards Federated Learning Across Biobanks: Prototype Software from the 2026 Carnegie Mellon University–NVIDIA Hackathon

Download paper here

This preprint presents prototype federated learning software developed during the 2026 Carnegie Mellon University–NVIDIA Federated Learning Hackathon for Biomedical Applications. The work demonstrates federated frameworks across a range of biomedical tasks, including disease subtyping, genetic association studies, histopathology harmonization, rare disease stratification, cancer subtyping, polygenic risk score aggregation, and multimodal clinical prediction.

Citation: Mu, J., et al., 2026. Towards Federated Learning Across Biobanks: Prototype Software from the 2026 Carnegie Mellon University–NVIDIA Hackathon. BioHackrXiv. https://doi.org/10.37044/osf.io/5psfj_v1.

Citation: Mu, J., et al., 2026. Towards Federated Learning Across Biobanks: Prototype Software from the 2026 Carnegie Mellon University–NVIDIA Hackathon. BioHackrXiv. https://doi.org/10.37044/osf.io/5psfj_v1.
Download Paper