Selected work

Representative Papers

LSEAD: A Privacy-Preserving LLM-Based Speech Analysis Framework for Early Alzheimer's Disease Screening

Aug 07, 2026

This study addresses the critical gap in non-invasive, low-cost methods for early Alzheimer’s disease (AD) screening across diverse clinical settings. The authors propose a privacy-preserving approach that locally deploys open-source large language models to extract embeddings from automatically transcribed speech, followed by dimensionality reduction via principal component analysis (PCA) and machine learning–based classification—all without uploading sensitive patient data. This work represents the first integration of locally hosted large language models with transcribed speech for AD detection, achieving up to a 5% improvement in accuracy on the ADReSS20 and ADReSSo2021 datasets. Notably, the method demonstrates superior performance in the early stages of the disease and exhibits enhanced cross-dataset generalizability.

0 citationsRead paper

Can a small additional claim lower the premium? Credibility orders for collective risk models

Jul 28, 2026

This study addresses a critical flaw in the classical collective risk model used for experience rating: it may violate monotonicity by reducing premiums when small claims increase, thereby undermining fairness and incentive compatibility. The authors formally define a credibility ordering within the collective risk framework, integrating stochastic order theory, Bayesian prediction, and multidimensional claim history—encompassing both claim counts and severities—to derive tractable sufficient conditions that guarantee monotonicity of the predictive distribution. Theoretical analysis demonstrates that these conditions eliminate anomalous behavior, while numerical simulations and empirical validation on real-world insurance data confirm the method’s effectiveness and practical applicability.

0 citationsRead paper

An Automated Multimodal Glaucoma Detection Framework Using ViT and a Stacking-Based Ensemble

Jul 02, 2026

This study addresses the inefficiency and reliance on expert interpretation in early glaucoma screening by proposing a multimodal automatic detection framework that integrates fundus images with clinical data. The method leverages a Vision Transformer (ViT) to extract visual features and combines them with traditional machine learning models within a stacking ensemble architecture, enabling both sample-level and patient-level diagnosis. Evaluated on the PAPILA dataset, the model achieves 97.47% accuracy and 97.50% F1-score at the sample level, and 98.97% accuracy and F1-score at the patient level. By innovatively integrating ViT with a stacking ensemble strategy and deploying the system as an end-to-end web platform, this work significantly enhances the feasibility and precision of large-scale glaucoma screening.

0 citationsRead paper

Learner-based Concept Drift Detection: Analysis and Evaluation

Jun 18, 2026

This study addresses the performance degradation of machine learning models caused by concept drift in dynamic data streams. It systematically analyzes the characteristics of concept drift and theoretically investigates, alongside empirical evaluation, the behavior of multiple learner-based detection algorithms under diverse drift scenarios—including abrupt and gradual shifts. Through comprehensive experiments on both synthetic and real-world datasets, the work compares the behavioral patterns and applicability of various detection methods, thereby deepening the understanding of underlying drift mechanisms. The findings elucidate the relative strengths and limitations of different detectors across heterogeneous environments, offering robust empirical guidance for algorithm selection in practical applications.

0 citationsRead paper

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

Jun 07, 2026

Generative artificial intelligence is transforming academic search from traditional document retrieval toward intelligent, interactive paradigms, yet it faces significant challenges concerning transparency, trustworthiness, and support for higher-order cognitive tasks. This work addresses these issues by organizing the CHIIR 2026 workshop—the first initiative to systematically integrate perspectives from information retrieval and human-computer interaction. Centered on three core themes—foundational principles, application scenarios, and “search as learning”—the project explores the design and evaluation of generative academic search systems leveraging conversational interaction, literature summarization, recommendation, and knowledge synthesis. By fostering cross-disciplinary consensus and identifying critical research directions, this effort advances a human-centered paradigm for next-generation academic search and catalyzes sustained community collaboration and innovation.

0 citationsRead paper

Recent publications

Latest Papers

LSEAD: A Privacy-Preserving LLM-Based Speech Analysis Framework for Early Alzheimer's Disease Screening

Aug 07, 2026

This study addresses the critical gap in non-invasive, low-cost methods for early Alzheimer’s disease (AD) screening across diverse clinical settings. The authors propose a privacy-preserving approach that locally deploys open-source large language models to extract embeddings from automatically transcribed speech, followed by dimensionality reduction via principal component analysis (PCA) and machine learning–based classification—all without uploading sensitive patient data. This work represents the first integration of locally hosted large language models with transcribed speech for AD detection, achieving up to a 5% improvement in accuracy on the ADReSS20 and ADReSSo2021 datasets. Notably, the method demonstrates superior performance in the early stages of the disease and exhibits enhanced cross-dataset generalizability.

0 citationsRead paper

Can a small additional claim lower the premium? Credibility orders for collective risk models

Jul 28, 2026

This study addresses a critical flaw in the classical collective risk model used for experience rating: it may violate monotonicity by reducing premiums when small claims increase, thereby undermining fairness and incentive compatibility. The authors formally define a credibility ordering within the collective risk framework, integrating stochastic order theory, Bayesian prediction, and multidimensional claim history—encompassing both claim counts and severities—to derive tractable sufficient conditions that guarantee monotonicity of the predictive distribution. Theoretical analysis demonstrates that these conditions eliminate anomalous behavior, while numerical simulations and empirical validation on real-world insurance data confirm the method’s effectiveness and practical applicability.

0 citationsRead paper

An Automated Multimodal Glaucoma Detection Framework Using ViT and a Stacking-Based Ensemble

Jul 02, 2026

This study addresses the inefficiency and reliance on expert interpretation in early glaucoma screening by proposing a multimodal automatic detection framework that integrates fundus images with clinical data. The method leverages a Vision Transformer (ViT) to extract visual features and combines them with traditional machine learning models within a stacking ensemble architecture, enabling both sample-level and patient-level diagnosis. Evaluated on the PAPILA dataset, the model achieves 97.47% accuracy and 97.50% F1-score at the sample level, and 98.97% accuracy and F1-score at the patient level. By innovatively integrating ViT with a stacking ensemble strategy and deploying the system as an end-to-end web platform, this work significantly enhances the feasibility and precision of large-scale glaucoma screening.

0 citationsRead paper

Learner-based Concept Drift Detection: Analysis and Evaluation

Jun 18, 2026

This study addresses the performance degradation of machine learning models caused by concept drift in dynamic data streams. It systematically analyzes the characteristics of concept drift and theoretically investigates, alongside empirical evaluation, the behavior of multiple learner-based detection algorithms under diverse drift scenarios—including abrupt and gradual shifts. Through comprehensive experiments on both synthetic and real-world datasets, the work compares the behavioral patterns and applicability of various detection methods, thereby deepening the understanding of underlying drift mechanisms. The findings elucidate the relative strengths and limitations of different detectors across heterogeneous environments, offering robust empirical guidance for algorithm selection in practical applications.

0 citationsRead paper

Report on CHIIR 2026 Workshop on Generative AI and Academic Search (GAI&AS)

Jun 07, 2026

Generative artificial intelligence is transforming academic search from traditional document retrieval toward intelligent, interactive paradigms, yet it faces significant challenges concerning transparency, trustworthiness, and support for higher-order cognitive tasks. This work addresses these issues by organizing the CHIIR 2026 workshop—the first initiative to systematically integrate perspectives from information retrieval and human-computer interaction. Centered on three core themes—foundational principles, application scenarios, and “search as learning”—the project explores the design and evaluation of generative academic search systems leveraging conversational interaction, literature summarization, recommendation, and knowledge synthesis. By fostering cross-disciplinary consensus and identifying critical research directions, this effort advances a human-centered paradigm for next-generation academic search and catalyzes sustained community collaboration and innovation.

0 citationsRead paper