Reproduce “Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hanning Guo, Hanwen Bi, Farah Abdellatif, Andrei Galbenus, Jon. N. Shah, Abigail Morrison, Jürgen Dammers
Brain-OF converts fMRI, EEG, and MEG recordings into shared representations, enabling one pretrained model to use single modalities or paired inputs. It reconstructs signals in temporal and frequency domains during self-supervised pretraining. In age prediction and age-group evaluations, fusion beats the stronger single-modality result in five of six settings, but not for the largest model on CamCAN.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.