12 papers
PGP-Clinical-TimeKAN: Prior-Guided Joint Probabilistic Forecasting of Clinical Trajectories
Weizhi Nie, Rihao Chang, Weijie Wang +1
Clinical deterioration unfolds through coupled, partially observed trajectories, not a single diagnostic label. We introduce PGP-Clinical-TimeKAN, a trajectory-first framework for…
Patient-Conditioned Dual Hypergraph Reasoning for Auditable Traditional Chinese Medicine Prescription Support
Weizhi Nie, Shaojin Bai, Weijie Wang +1
Traditional Chinese medicine (TCM) prescription support requires patient-specific reasoning from clinical narratives to syndromes, treatment principles, herbs, and doses. Direct la…
Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling
Weizhi Nie, Weijie Wang, Yuting Su
Multivariate time-series models for prognostics are often evaluated by point prediction accuracy, yet their internal states rarely expose a coherent degradation process. We study l…
Prototype Latent World Model Replay for Class-Incremental Learning
Weizhi Nie, Hui Wang, Weijie Wang +1
Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones. This is difficult when raw old samples are no longer available. We…
Hypergraph Normal World Models for Logical Visual Anomaly Detection
Weizhi Nie, Zibo Xu, Weijie Wang +1
Visual anomaly detection is often deployed with only normal training images. Most one-class detectors map test patches or features to a normal reference distribution. This works we…
Learning a Normal World Model for Few-Shot Boundary-Calibrated Abnormality Detection
Weizhi Nie, Weichao Liu, Weijie Wang +1
Abnormality detection in complex systems faces two practical barriers: abnormal labels are scarce, and binary labels do not quantify how far an event has departed from normal behav…
Phys-JEPA: Physics-Informed Latent World Models for Multivariate Time-Series Forecasting
Weizhi Nie, Weichao Liu, Honglin Guo +1
Multivariate forecasting in physical systems requires models that predict coupled temporal variables while preserving meaningful state evolution. Deep forecasters can fit temporal…
Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA
Zibo Xu, Qiang Li, Ke Lu +3
Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However, existing methods often overfit…
Unlabeled Cross-Center Automatic Analysis for TAAD: An Integrated Framework from Segmentation to Clinical Features
Mengdi Liu, Qiang Li, Weizhi Nie +2
Type A Aortic Dissection (TAAD) is a life-threatening cardiovascular emergency that demands rapid and precise preoperative evaluation. While key anatomical and pathological feature…
CIV-DG: Conditional Instrumental Variables for Domain Generalization in Medical Imaging
Shaojin Bai, Yuting Su, Weizhi Nie
Cross-site generalizability in medical AI is fundamentally compromised by selection bias, a structural mechanism where patient demographics (e.g., age, severity) non-randomly dicta…
Mask-Guided Attention Regulation for Anatomically Consistent Counterfactual CXR Synthesis
Zichun Zhang, Weizhi Nie, Honglin Guo +1
Counterfactual generation for chest X-rays (CXR) aims to simulate plausible pathological changes while preserving patient-specific anatomy. However, diffusion-based editing methods…
Learning to Trim: End-to-End Causal Graph Pruning with Dynamic Anatomical Feature Banks for Medical VQA
Zibo Xu, Qiang Li, Weizhi Nie +1
Medical Visual Question Answering (MedVQA) models often exhibit limited generalization due to reliance on dataset-specific correlations, such as recurring anatomical patterns or qu…