MAMBAxBrain: A Multi-task Neural Framework Linking Brain Functional Dynamics to Individual Fingerprints, Cognitive and Disease States

Abstract

Functional magnetic resonance imaging (fMRI) contains rich individual, cognitive, and pathological information, yet no universal model exists for multi-task modeling of these dimensions. Here, we introduce MAMBAxBrain, a multitask neural framework that integrates Mamba architecture with functional connectivity analysis to jointly model the temporal dynamics and spatial coordination of neural activity. MAMBAxBrain achieves high accuracy across four distinct fMRI objectives, including brain fingerprinting, cognitive task decoding, reaction time prediction, and schizophrenia classification, consistently outperforming state-of-the-art methods with robust cross-session generalization. Interpretability analyses show that each task engages distinct, biologically plausible circuitry: from higher-order association cortex for identity to subcortical-motor loops for reaction time and disrupted control-sensory connectivity for schizophrenia. These findings inform a longstanding debate: rather than operating through wholly separate or entirely shared systems, the brain preferentially recruits task-specific circuits while retaining common representational structure across functions.