NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Torabi, Yasaman, Razmara, Parsa, Ajorlou, Hamed, Baraeinejad, Bardia
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913162187505664
author Torabi, Yasaman
Razmara, Parsa
Ajorlou, Hamed
Baraeinejad, Bardia
author_facet Torabi, Yasaman
Razmara, Parsa
Ajorlou, Hamed
Baraeinejad, Bardia
contents Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal domains. However, their integration with graph-based models of brain connectivity remains limited. In addition, most existing fMRI analysis methods rely on static Functional Connectivity (FC) representations, which obscure transient neural dynamics critical for neurodevelopmental disorders such as autism. Recent state-space approaches, including Mamba, model temporal structure efficiently, but are typically used as standalone feature extractors without explicit high-level reasoning. We propose NeuroMambaLLM, an end-to-end framework that integrates dynamic latent graph learning and selective state-space temporal modelling with LLMs. The proposed method learns the functional connectivity dynamically from raw Blood-Oxygen-Level-Dependent (BOLD) time series, replacing fixed correlation graphs with adaptive latent connectivity while suppressing motion-related artifacts and capturing long-range temporal dependencies. The resulting dynamic brain representations are projected into the embedding space of an LLM model, where the base language model remains frozen and lightweight low-rank adaptation (LoRA) modules are trained for parameter-efficient alignment. This design enables the LLM to perform both diagnostic classification and language-based reasoning, allowing it to analyze dynamic fMRI patterns and generate clinically meaningful textual reports.
format Preprint
id arxiv_https___arxiv_org_abs_2602_13770
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
Torabi, Yasaman
Razmara, Parsa
Ajorlou, Hamed
Baraeinejad, Bardia
Image and Video Processing
Machine Learning
Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal domains. However, their integration with graph-based models of brain connectivity remains limited. In addition, most existing fMRI analysis methods rely on static Functional Connectivity (FC) representations, which obscure transient neural dynamics critical for neurodevelopmental disorders such as autism. Recent state-space approaches, including Mamba, model temporal structure efficiently, but are typically used as standalone feature extractors without explicit high-level reasoning. We propose NeuroMambaLLM, an end-to-end framework that integrates dynamic latent graph learning and selective state-space temporal modelling with LLMs. The proposed method learns the functional connectivity dynamically from raw Blood-Oxygen-Level-Dependent (BOLD) time series, replacing fixed correlation graphs with adaptive latent connectivity while suppressing motion-related artifacts and capturing long-range temporal dependencies. The resulting dynamic brain representations are projected into the embedding space of an LLM model, where the base language model remains frozen and lightweight low-rank adaptation (LoRA) modules are trained for parameter-efficient alignment. This design enables the LLM to perform both diagnostic classification and language-based reasoning, allowing it to analyze dynamic fMRI patterns and generate clinically meaningful textual reports.
title NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2602.13770