NeuroMambaLLM learns dynamic brain graphs from fMRI with a Mamba model and a frozen LLaMA-3-8B with LoRA, reaching 72.12% accuracy on ABIDE I.
Physics-informed deep learning model selection for robust segmen- tation of multi-center stress perfusion datasets: results from the scmr registry
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
NeuroMambaLLM learns dynamic brain graphs from fMRI with a Mamba model and a frozen LLaMA-3-8B with LoRA, reaching 72.12% accuracy on ABIDE I.