BrainPFN is a Prior Data Fitted Network that predicts behavioral phenotypes from functional MRI data without needing per-score or per-cohort refitting. It is meta-trained on a domain-specific prior derived from about 7,000 real functional connectivity matrices, generating one billion synthetic training samples. In tests across four independent cohorts, BrainPFN outperforms Kernel Ridge Regression on small-sample predictions and rivals larger foundation models, all while using a modest, publicly available training pool.
By Carlo Alberto Barbano (MIND), Demian Wassermann (MIND)
arXiv:2606. 04010v1 Announce Type: cross Abstract: Brain foundation models (BFMs) are self-supervised Transformers pretrained on fMRI data.
By Giovanni Marraffini, Gabriel Mahuas, Trinidad Borrell, Victoria Shevchenko, Demian Wassermann
The study investigates how data volume, model size, and training duration affect the performance of fMRI foundation models. Using over 200 datasets and 10,000 GPU‑hours, the authors find that larger models benefit more from additional data, and that at a fixed compute budget, increasing data yields greater gains than enlarging the model. By selecting optimal combinations of data, size, and duration, they produce models that outperform existing fMRI foundation models on out‑of‑distribution tasks while requiring less pretraining compute.
By Wenhao Ye, Xuanye Pan, Junfeng Xia, Junxiang Zhang, Mo Wang, Quanying Liu
arXiv:2608.30418v1 Announce Type: cross
Abstract: Resting-state functional magnetic resonance imaging (rs-fMRI) functional connectivity (FC) matrices are widely used for individual-level prediction,...
By Ce Ju, Antoine Collas, Florent Bouchard, Bertrand Thirion
arXiv:2606.13315v2 Announce Type: replace
Abstract: MRI self-supervised learning (SSL) has largely emphasized segmentation and dense prediction, while controlled studies of how alternative pretrainin...
By Esra Erg\"un, Hersh Chandarana, Dan Sodickson, Gozde Unal
arXiv:2609.34167v2 Announce Type: replace
Abstract: Foundation models pre-trained on large-scale fMRI datasets have shown strong downstream performance, but at substantial data and computation cost....
By Juhyeon Park, Yeonwoo Kim, Peter Yongho Kim, Yansen Wang, Mingqing Xiao, Dongqi Han, Dongsheng Li, Taesup Moon
arXiv:2609.12834v1 Announce Type: new
Abstract: Modelling how a disease progresses over time requires longitudinal imaging cohorts, which are scarce and small, whereas cross-sectional data -- one ima...
By Ifeoma Veronica Nwabufo, Julius Gervelmeyer, Sarah M\"uller, Philipp Berens
The study evaluates self‑supervised pretraining for Prognostics and Health Management (PHM) across 47 public datasets, using a compact Transformer encoder trained with masked patch prediction. Transfer performance is highly task‑dependent: it dramatically improves fault‑classification on CWRU and HSG18 but offers no reliable benefit for remaining‑useful‑life estimation on CMAPSS. The authors also compare centralized versus simulated federated pretraining, finding that centralized training generally outperforms federated training under matched budgets, and that the intrinsic SSL loss does not reliably predict downstream performance.
By Jos\'e Sanz-Dur\'an, David Sol\'is-Mart\'in
The study investigates whether self‑supervised learning can produce useful representations from fMRI data alone. Using a joint embedding predictive architecture, participant‑specific encoders are trained without access to stimulus images or derived representations. The resulting embeddings perform competitively on brain captioning, image reconstruction, and cross‑participant generalization, and can be aligned unsupervised across participants, enabling a decoding head trained on one subject to work on another with minimal loss of performance.
By Serwan Jassim, Victoria Bosch, Daniel Anthes, Elia Bruni, Tim Kietzmann
arXiv:2607. 06629v1 Announce Type: new Abstract: Brain age -- the age inferred from a physiological recording -- is an emerging biomarker whose deviation from chronological age tracks neurological and psychiatric burden, and EEG is an attractive substrate for it because it is cheap, portable, and temporally rich.
By Roy Segal, Yoni Svechinsky, Tomer Fekete
Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We...
arXiv:2604. 04958v3 Announce Type: replace-cross Abstract: Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis.
By Xinhong Xu, Yimeng Zhang, Qichen Qian, Yuanlong Zhang