UnEBOLT: A Unified Model for EEG-to-BOLD Translation and Functional Connectivity Reconstruction

Yamin Li, Ange Lou, Chang Li, Shiyu Wang, Haatef Pourmotabbed, Ziyuan Xu, SHENGCHAO ZHANG, Dario J. Englot, Soheil Kolouri, Daniel Moyer, Roza G Bayrak, Catie Chang

Keywords: fMRI, EEG, EEG-to-fMRI Synthesis

Abstract: Functional magnetic resonance imaging (fMRI) provides high-resolution, whole-brain dynamic information, but is costly and immobile, limiting its utility in low-resource settings. EEG-to-fMRI translation via deep learning offers a promising alternative, enabling access to deep brain activity from scalp EEG signals in naturalistic settings. However, current state-of-the-art methods for EEG-to-fMRI translation require training separate models for each brain region, limiting efficiency and scalability. Here, we introduce UnEBOLT, a United model for EEG-to-BOLD Translation. UnEBOLT is an end-to-end framework that predicts whole-brain fMRI time series from EEG by adaptive multi-region decoding within a single model. This approach enables efficient and comprehensive inference while also reconstructing subject-specific functional connectivity matrices, a representation that provides insight into neuronal interactions and which has been successfully utilized for clinical biomarkers. Our results show that UnEBOLT achieves comparable performance to dedicated ROI-specific models while scaling to multi-region prediction. Additionally, the reconstructed fMRI time series enable functional connectivity estimation, which may have broad applications in neuroscience.

Primary Subject Area: Application: Neuroimaging

Secondary Subject Area: Image Synthesis

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Replace NNN with your OpenReview submission ID., Includes \documentclass{midl}, \jmlryear{2026}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package., Did not use the times package., Use the correct spelling and format, avoid Unicode characters, and use LaTeX equivalents instead., Any math in the title and abstract must be enclosed within $...$., Did not override the bibliography style defined in midl.cls and did not use \begin{thebibliography} directly to insert references., Avoid using \scalebox; use \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., No separate supplementary PDF uploads., Acknowledgements, references, and appendix must start after the main content.

Submission Number: 194