Selected work

Representative Papers

Coupled Graph--Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity

Aug 10, 2026

This work addresses medication safety risks faced by older adults with multimorbidity during non-clinical periods due to missed critical health information. It proposes ATLAS, a framework that constructs a medication safety knowledge graph and dynamically generates personalized drug interaction graphs based on patient states. ATLAS incorporates a risk-prioritized multi-agent strategy to perform contraindication screening, risk assessment, and alternative recommendation. The framework innovatively introduces a coupled graph-policy distillation mechanism to translate clinical guideline evidence into individualized decisions and establishes GeriMedBench—the first interactive benchmark for evaluating systems’ evidence-based decision-making capabilities. Experiments demonstrate that ATLAS significantly outperforms existing methods across multiple international benchmarks: on the European non-interactive multimorbidity test, it achieves a 53.73-point gain in Strict Success Rate and a 14.63-point improvement in OSRS over the strongest closed-source LLM baseline, with zero unsafe recommendations in automated evaluation and superior performance across all metrics in clinical double-blind assessment.

0 citationsRead paper

BRIGHT: A Collaborative Generalist-Specialist Foundation Model for Breast Pathology

Mar 03, 2026

This work addresses the limited performance of existing general-purpose foundation models in comprehensive clinical tasks within a single organ system—such as the breast—due to insufficient large-scale validation and organ-specific training. To overcome this, we propose BRIGHT, the first breast-specialized foundation model, trained on 210 million tissue patches and 51,000 whole-slide images of breast specimens. BRIGHT employs a generalist–specialist collaborative training framework that integrates both universal and organ-specific pathological features, enabling support for 24 diverse tasks spanning diagnosis, biomarker prediction, treatment response assessment, and survival analysis. The model achieves state-of-the-art performance across 21 internal and 5 external evaluation tasks, significantly outperforming general-purpose counterparts, and establishes the largest multicenter validation cohort to date, offering a scalable paradigm for organ-specific pathology foundation models.

0 citationsRead paper

Recent publications

Latest Papers

Coupled Graph--Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity

Aug 10, 2026

This work addresses medication safety risks faced by older adults with multimorbidity during non-clinical periods due to missed critical health information. It proposes ATLAS, a framework that constructs a medication safety knowledge graph and dynamically generates personalized drug interaction graphs based on patient states. ATLAS incorporates a risk-prioritized multi-agent strategy to perform contraindication screening, risk assessment, and alternative recommendation. The framework innovatively introduces a coupled graph-policy distillation mechanism to translate clinical guideline evidence into individualized decisions and establishes GeriMedBench—the first interactive benchmark for evaluating systems’ evidence-based decision-making capabilities. Experiments demonstrate that ATLAS significantly outperforms existing methods across multiple international benchmarks: on the European non-interactive multimorbidity test, it achieves a 53.73-point gain in Strict Success Rate and a 14.63-point improvement in OSRS over the strongest closed-source LLM baseline, with zero unsafe recommendations in automated evaluation and superior performance across all metrics in clinical double-blind assessment.

0 citationsRead paper

BRIGHT: A Collaborative Generalist-Specialist Foundation Model for Breast Pathology

Mar 03, 2026

This work addresses the limited performance of existing general-purpose foundation models in comprehensive clinical tasks within a single organ system—such as the breast—due to insufficient large-scale validation and organ-specific training. To overcome this, we propose BRIGHT, the first breast-specialized foundation model, trained on 210 million tissue patches and 51,000 whole-slide images of breast specimens. BRIGHT employs a generalist–specialist collaborative training framework that integrates both universal and organ-specific pathological features, enabling support for 24 diverse tasks spanning diagnosis, biomarker prediction, treatment response assessment, and survival analysis. The model achieves state-of-the-art performance across 21 internal and 5 external evaluation tasks, significantly outperforming general-purpose counterparts, and establishes the largest multicenter validation cohort to date, offering a scalable paradigm for organ-specific pathology foundation models.

0 citationsRead paper