Selected work

Representative Papers

Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work

Aug 15, 2026

This study addresses the fragmentation of scientific knowledge systems and challenges in cross-user collaboration by proposing a hierarchical knowledge state and service governance framework. Replacing flat knowledge graphs with a five-layer FREG model, the approach integrates a router-contract-workflow microkernel architecture with LLM agents to enable unified encapsulation, secure exchange, and auditable recombination of research knowledge. Experimental validation in antibody design review demonstrates that this framework significantly enhances knowledge ingestion efficiency, cross-member integration capabilities, and support for scientific writing. Consequently, this work establishes a novel structured governance paradigm for open science ecosystems, effectively mitigating systemic fragmentation while facilitating secure and traceable collaborative research processes across diverse user groups.

0 citationsRead paper

A Fine Evaluation Method for Cube Copying Test for Early Detection of Alzheimer's Disease

Dec 01, 2025

The Cube Copying Test (CCT) in the Montreal Cognitive Assessment (MoCA) employs a binary pass/fail scoring scheme, leading to floor effects—particularly among low-education older adults—and introducing significant bias in visuospatial cognitive assessment. Method: We propose a fine-grained CCT scoring framework based on dynamic handwriting features: trajectories are captured via Cogni-CareV3.0 during cube copying; spatiotemporal motor and geometric spatial features are extracted; an unequal-dimension feature normalization strategy is designed; and a BiLSTM-Attention fusion model is developed for early mild cognitive impairment (MCI) detection. Contribution/Results: Our approach overcomes the limitations of binary evaluation by establishing an age-negative- and education-positive-correlated continuous scoring scale. It achieves 86.69% classification accuracy—substantially outperforming prior methods—and uncovers systematic distribution patterns of cube-drawing ability in MCI identification, thereby enhancing screening objectivity and enabling personalized intervention.

0 citationsRead paper

Recent publications

Latest Papers

Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work

Aug 15, 2026

This study addresses the fragmentation of scientific knowledge systems and challenges in cross-user collaboration by proposing a hierarchical knowledge state and service governance framework. Replacing flat knowledge graphs with a five-layer FREG model, the approach integrates a router-contract-workflow microkernel architecture with LLM agents to enable unified encapsulation, secure exchange, and auditable recombination of research knowledge. Experimental validation in antibody design review demonstrates that this framework significantly enhances knowledge ingestion efficiency, cross-member integration capabilities, and support for scientific writing. Consequently, this work establishes a novel structured governance paradigm for open science ecosystems, effectively mitigating systemic fragmentation while facilitating secure and traceable collaborative research processes across diverse user groups.

0 citationsRead paper

A Fine Evaluation Method for Cube Copying Test for Early Detection of Alzheimer's Disease

Dec 01, 2025

The Cube Copying Test (CCT) in the Montreal Cognitive Assessment (MoCA) employs a binary pass/fail scoring scheme, leading to floor effects—particularly among low-education older adults—and introducing significant bias in visuospatial cognitive assessment. Method: We propose a fine-grained CCT scoring framework based on dynamic handwriting features: trajectories are captured via Cogni-CareV3.0 during cube copying; spatiotemporal motor and geometric spatial features are extracted; an unequal-dimension feature normalization strategy is designed; and a BiLSTM-Attention fusion model is developed for early mild cognitive impairment (MCI) detection. Contribution/Results: Our approach overcomes the limitations of binary evaluation by establishing an age-negative- and education-positive-correlated continuous scoring scale. It achieves 86.69% classification accuracy—substantially outperforming prior methods—and uncovers systematic distribution patterns of cube-drawing ability in MCI identification, thereby enhancing screening objectivity and enabling personalized intervention.

0 citationsRead paper