3 papers
cs.CL2026
A Monosemantic Attribution Framework for Stable Interpretability in Clinical Neuroscience Transformer-Based Language Models
Michail Mamalakis, Tiago Azevedo, Cristian Cosentino +5
Interpretability remains a key challenge for deploying language models (LM) in clinical settings such as progression diagnosis of Alzheimer disease, where early and trustworthy pre…
q-bio.NC2025
Geometry-Guided Generative Representation for Functional Brain Graphs
Subati Abulikemu, Tiago Azevedo, Michail Mamalakis +1
In network neuroscience, functional brain systems are often characterized using separate yet related graph-theoretic or spectral descriptors, overlooking how these properties covar…
q-bio.NC2025
Association-sensory spatiotemporal hierarchy and functional gradient-regularised recurrent neural network with implications for schizophrenia
Subati Abulikemu, Puria Radmard, Michail Mamalakis +1
The human neocortex is functionally organised at its highest level along a continuous sensory-to-association (AS) hierarchy. This study characterises the AS hierarchy of patients w…