FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI
Researchers have developed FlexiBrain, a novel framework for processing fMRI data that is agnostic to spatial and temporal resolution variations. This approach utilizes a Mamba-JEPA backbone and dynamic patch resizing to avoid destructive standardization, preserving subject-specific anatomical information. FlexiBrain has demonstrated superior performance across five neuroscience tasks, outperforming existing methods by up to 12 percentage points and significantly reducing preprocessing computational costs. AI
IMPACT Enables more robust and efficient development of foundation models for neuroscience by handling diverse fMRI data resolutions.