Zhiping Lin
YOU?
Author Swipe
View article: Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
Analytic Continual Test-Time Adaptation for Multi-Modality Corruption Open
View article: Critical attention scaling in long-context transformers
Critical attention scaling in long-context transformers Open
As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length $n$ increases, causing tokens to cluster excessively, a phenomenon known…
View article: One-step Multi-view Clustering With Adaptive Low-rank Anchor-graph Learning
One-step Multi-view Clustering With Adaptive Low-rank Anchor-graph Learning Open
In light of their capability to capture structural information while reducing computing complexity, anchor graph-based multi-view clustering (AGMC) methods have attracted considerable attention in large-scale clustering problems. Neverthel…
View article: Predicting chronic stenosis progression of stable coronary artery disease using peri-coronary fat attenuation index derived from coronary computed tomography angiography
Predicting chronic stenosis progression of stable coronary artery disease using peri-coronary fat attenuation index derived from coronary computed tomography angiography Open
Baseline peri-coronary FAI is valuable in predicting chronic coronary stenosis progression that occurs within a short period (within 1 year) in RCA, and, potentially, in LM + CX. Stenosis progression in LAD might be mainly driven by factor…
View article: The relationship between programmed cell death and vascular calcification
The relationship between programmed cell death and vascular calcification Open
Vascular calcification (VC) is a pathological condition closely associated with a range of cardiovascular diseases, including atherosclerosis (AS), hypertension, vascular injury, and diabetic angiopathy. Programmed cell death, encompassing…
View article: Towards Identifiability of Interventional Stochastic Differential Equations
Towards Identifiability of Interventional Stochastic Differential Equations Open
We study identifiability of stochastic differential equations (SDE) under multiple interventions. Our results give the first provable bounds for unique recovery of SDE parameters given samples from their stationary distributions. We give t…
View article: Accurate Diagnosis of Respiratory Viruses Using an Explainable Machine Learning with Mid-Infrared Biomolecular Fingerprinting of Nasopharyngeal Secretions
Accurate Diagnosis of Respiratory Viruses Using an Explainable Machine Learning with Mid-Infrared Biomolecular Fingerprinting of Nasopharyngeal Secretions Open
Accurate identification of respiratory viruses (RVs) is critical for outbreak control and public health. This study presents a diagnostic system that combines Attenuated Total Reflectance Fourier Transform Infrared Spectroscopy (ATR-FTIR) …
View article: Surface modification strategies for silicon based anodes coated with polymer-derived carbon source
Surface modification strategies for silicon based anodes coated with polymer-derived carbon source Open
View article: Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations Open
Modern high-throughput biological datasets with thousands of perturbations provide the opportunity for large-scale discovery of causal graphs that represent the regulatory interactions between genes. Differentiable causal graphical models …
View article: Real-Time Human Action Recognition With Dynamical Frame Processing via Modified ConvLSTM and BERT
Real-Time Human Action Recognition With Dynamical Frame Processing via Modified ConvLSTM and BERT Open
In this study, a human action recognition approach with dynamical frame processing is proposed to fulfill the need for action recognition in a real-time manner. A novel architecture with a modified convolutional long short-term memory (Mod…
View article: Penalized Learning
Penalized Learning Open
View article: Analytic Learning Methods for Pattern Recognition
Analytic Learning Methods for Pattern Recognition Open
View article: Decision Forest with Fast-Determined Optimal Parameter Intervals of Base Learners
Decision Forest with Fast-Determined Optimal Parameter Intervals of Base Learners Open
View article: Residual connections provably mitigate oversmoothing in graph neural networks
Residual connections provably mitigate oversmoothing in graph neural networks Open
Graph neural networks (GNNs) have achieved remarkable empirical success in processing and representing graph-structured data across various domains. However, a significant challenge known as "oversmoothing" persists, where vertex features …
View article: Introduction
Introduction Open
View article: Applications
Applications Open
View article: Graph-Driven Models for Gas Mixture Identification and Concentration Estimation on Heterogeneous Sensor Array Signals
Graph-Driven Models for Gas Mixture Identification and Concentration Estimation on Heterogeneous Sensor Array Signals Open
Accurately identifying gas mixtures and estimating their concentrations are crucial across various industrial applications using gas sensor arrays. However, existing models face challenges in generalizing across heterogeneous datasets, whi…
View article: Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
Analytic Continual Test-Time Adaptation for Multi-Modality Corruption Open
Test-Time Adaptation (TTA) enables pre-trained models to bridge the gap between source and target datasets using unlabeled test data, addressing domain shifts caused by corruptions like weather changes, noise, or sensor malfunctions in tes…
View article: On-Site Precise Screening of SARS-CoV-2 Systems Using a Channel-Wise Attention-Based PLS-1D-CNN Model with Limited Infrared Signatures
On-Site Precise Screening of SARS-CoV-2 Systems Using a Channel-Wise Attention-Based PLS-1D-CNN Model with Limited Infrared Signatures Open
During the early stages of respiratory virus outbreaks, such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the efficient utilize of limited nasopharyngeal swabs for rapid and accurate screening is crucial for public heal…
View article: Unsupervised Attention-Based Multi-Source Domain Adaptation Framework for Drift Compensation in Electronic Nose Systems
Unsupervised Attention-Based Multi-Source Domain Adaptation Framework for Drift Compensation in Electronic Nose Systems Open
Continuous, long-term monitoring of hazardous, noxious, explosive, and flammable gases in industrial environments using electronic nose (E-nose) systems faces the significant challenge of reduced gas identification accuracy due to time-var…
View article: FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking
FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking Open
Multiple object tracking (MOT) involves identifying multiple targets and assigning them corresponding IDs within a video sequence, where occlusions are often encountered. Recent methods address occlusions using appearance cues through onli…
View article: DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning Open
Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that reta…
View article: DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning Open
Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that reta…
View article: A novel hybrid machine learning model for auxiliary diagnosing myocardial ischemia
A novel hybrid machine learning model for auxiliary diagnosing myocardial ischemia Open
Introduction Accurate identification of the myocardial texture features of fat around the coronary artery on coronary computed tomography angiography (CCTA) images are crucial to improve clinical diagnostic efficiency of myocardial ischemi…
View article: Robust Semi-Supervised Community Detection Based on Symmetric Nonnegative Matrix Factorization
Robust Semi-Supervised Community Detection Based on Symmetric Nonnegative Matrix Factorization Open
View article: Imaging Presentation and Molecular Biomarkers in Identifying Stage CT1N0M0 Lung Adenocarcinoma
Imaging Presentation and Molecular Biomarkers in Identifying Stage CT1N0M0 Lung Adenocarcinoma Open
View article: Advances in Fiber-Based Wearable Sensors with Machine Learning
Advances in Fiber-Based Wearable Sensors with Machine Learning Open
Fiber sensors, with their high sensitivity and flexibility, have contributed to the integration of wearable technologies into everyday clothing, enabling both comfortability and efficient data collection. Meanwhile, the rapid advancements …
View article: Reducing Reliance on Expensive Annotations in Medical Image Segmentation Via Diffusion Models and Segment Anything Model
Reducing Reliance on Expensive Annotations in Medical Image Segmentation Via Diffusion Models and Segment Anything Model Open
View article: Deterministic bridge regression for compressive classification
Deterministic bridge regression for compressive classification Open
View article: TCF-Trans: Temporal Context Fusion Transformer for Anomaly Detection in Time Series
TCF-Trans: Temporal Context Fusion Transformer for Anomaly Detection in Time Series Open
Anomaly detection tasks involving time-series signal processing have been important research topics for decades. In many real-world anomaly detection applications, no specific distributions fit the data, and the characteristics of anomalie…