11 papers
MPFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease
Lujia Zhong, Shuo Huang, Jianwei Zhang +2
While various multimodal methods combining imaging and tabular data for Alzheimer's disease (AD) diagnosis were proposed, they are often limited in generalization across cohorts. I…
When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction
Lujia Zhong, Xinkai Wang, Shuo Huang +1
Longitudinal prediction of Alzheimer's disease biomarkers increasingly informs clinical decisions, and a forecast is only useful if it also reports how much to trust it. Conformal…
TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings
Jingxiang Zhang, Lujia Zhong, Zijie Zhu +2
Few-shot multimodal classification commonly attaches a lightweight head, such as -nearest neighbors, logistic regression, or a linear SVM, to a frozen pretrained encoder. Althou…
Dimension expansion for simulation-efficient nanophotonic neural networks
Shuo Huang, Mahsa Torfeh, Lujia Zhong +3
Inverse design of nanophotonic structures is challenging due to the large design space, nonlinear structure-response relationships, and the high computational cost of iterative ele…
A Surface-based Multimodal Framework for Multitask Analysis in Alzheimer's Disease
Shuo Huang, Jianwei Zhang, Lujia Zhong +4
Alzheimer's Disease (AD) is a progressive neurodegenerative disorder, and longitudinal analysis is critical for early detection and effective intervention. Developing models capabl…
PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis
Lujia Zhong, Yihao Xia, Shuo Huang +2
Deep learning models in medical imaging typically operate as parametric memory, diagnosing patients by recalling fixed knowledge learned during training. This contrasts sharply wit…
NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research
Lujia Zhong, Yihao Xia, Jianwei Zhang +4
Multimodal neuroimaging analysis often involves complex, modality-specific preprocessing workflows that require careful configuration, quality control, and coordination across hete…
Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotion
Jingxiang Zhang, Lujia Zhong
Large Language Models (LLMs) are increasingly expected to navigate the nuances of human emotion. While research confirms that LLMs can simulate emotional intelligence, their intern…
ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation
Lujia Zhong, Shuo Huang, Yonggang Shi
Recently, deep learning has made remarkable strides, especially with generative modeling, such as large language models and probabilistic diffusion models. However, training these…
Diffusion Model-based FOD Restoration from High Distortion in dMRI
Shuo Huang, Lujia Zhong, Yonggang Shi
Fiber orientation distributions (FODs) is a popular model to represent the diffusion MRI (dMRI) data. However, imaging artifacts such as susceptibility-induced distortion in dMRI c…
Tau Anomaly Detection in PET Imaging via Bilateral-Guided Deterministic Diffusion Model
Lujia Zhong, Shuo Huang, Jiaxin Yue +4
The emergence of tau PET imaging over the last decade has enabled Alzheimer's disease (AD) researchers to examine tau pathology in vivo and more effectively characterize the diseas…