9 papers
Imaging the Topology of Dynamic Brain Connectivity
Peilin He, Tananun Songdechakraiwut
Functional brain connectivity changes dynamically over time, making its representation challenging for learning on non-Euclidean data. We present a framework that encodes dynamic f…
Bayesian Topological Analysis of Functional Brain Networks
Xukun Zhu, Michael W Lutz, Tananun Songdechakraiwut
Subtle alterations in brain network topology often evade detection by traditional statistical methods. To address this limitation, we introduce a Bayesian inference framework for t…
Leveraging LLMs for Early Alzheimer's Prediction
Tananun Songdechakraiwut
We present a connectome-informed LLM framework that encodes dynamic fMRI connectivity as temporal sequences, applies robust normalization, and maps these data into a representation…
Language Models for Longitudinal Clinical Prediction
Tananun Songdechakraiwut, Michael Lutz
We explore a lightweight framework that adapts frozen large language models to analyze longitudinal clinical data. The approach integrates patient history and context within the la…
Connectome-Guided Automatic Learning Rates for Deep Networks
Peilin He, Tananun Songdechakraiwut
The human brain is highly adaptive: its functional connectivity reconfigures on multiple timescales during cognition and learning, enabling flexible information processing. By cont…
Augmenting Bias Detection in LLMs Using Topological Data Analysis
Keshav Varadarajan, Tananun Songdechakraiwut
Recently, many bias detection methods have been proposed to determine the level of bias a large language model captures. However, tests to identify which parts of a large language…