Fine-Tuning Pretrained Models with NVIB for Improved Generalisation

This repository is currently under release. For now please see https://github.com/idiap/nvib.

This repository contains the code developed for the paper Fine-Tuning Pretrained Models with NVIB for Improved Generalisation (ICLR 2025).

Please cite the original authors for their work in any publication(s) that uses this work:

@inproceedings{
    fehr2025finetuning,
    title={Fine-Tuning Pretrained Models with {NVIB} for Improved Generalisation},
    author={Fabio James Fehr and Alina Elena Baia and Xiaoguang Chang and Andrei Catalin Coman and Karl El Hajal and Dina El Zein and Shashi Kumar and Juan Pablo Zuluaga Gomez and Andrea Cavallaro and Damien Teney and James Henderson},
    booktitle={Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions},
    year={2025},
    url={https://openreview.net/forum?id=eX0VFgG4IS}
}

Contact

For questions or reporting issues to this software package, kindly contact the author_.

Author: [email protected]