CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation
为解决冠状动脉造影解读一致性问题，开发了CARDEA模型，通过视觉特征对齐、自蒸馏和强化学习方法提供可审计的推理过程。
0 citationsRead paper
Selected work
Representative Papers
DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis
To address factual hallucinations and opaque reasoning in multimodal models for gastrointestinal (GI) pathology image diagnosis, this work introduces the first large-scale GI pathology dataset annotated with explicit clinical reasoning chains. We propose a “prompt-argumentation” strategy that jointly optimizes lesion classification and anatomical localization, and design a Grouped Relative Policy Optimization (GRPO) framework integrating vision-language modeling with structured prompt engineering. Built upon supervised fine-tuning, GRPO enhances reasoning auditability via intra-group consistency optimization. Experiments on real-world pathology report generation demonstrate that our method achieves a 18.7% improvement in clinical relevance, a 32.4% increase in structural completeness, and a 41.2% reduction in diagnostic error rate over state-of-the-art baselines—significantly advancing model accuracy, trustworthiness, and clinical utility.
0 citationsRead paper
Recent publications
Latest Papers
CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation
为解决冠状动脉造影解读一致性问题，开发了CARDEA模型，通过视觉特征对齐、自蒸馏和强化学习方法提供可审计的推理过程。
0 citationsRead paper
DiagR1: A Vision-Language Model Trained via Reinforcement Learning for Digestive Pathology Diagnosis
To address factual hallucinations and opaque reasoning in multimodal models for gastrointestinal (GI) pathology image diagnosis, this work introduces the first large-scale GI pathology dataset annotated with explicit clinical reasoning chains. We propose a “prompt-argumentation” strategy that jointly optimizes lesion classification and anatomical localization, and design a Grouped Relative Policy Optimization (GRPO) framework integrating vision-language modeling with structured prompt engineering. Built upon supervised fine-tuning, GRPO enhances reasoning auditability via intra-group consistency optimization. Experiments on real-world pathology report generation demonstrate that our method achieves a 18.7% improvement in clinical relevance, a 32.4% increase in structural completeness, and a 41.2% reduction in diagnostic error rate over state-of-the-art baselines—significantly advancing model accuracy, trustworthiness, and clinical utility.
0 citationsRead paper