Artificial Intelligence Medical Compendium

Severe pneumonia-induced septic shock is one of the most representative complex syndromes in pulmonary critical care medicine. Its pathophysiology results from the combined effects of alveolar-capillary barrier injury, infection-associated vasodilati... read more 

Severe pneumonia, characterized by rapid progression and high heterogeneity, is a leading cause of patient mortality. Early identification of high-risk patients is crucial for improving outcomes. Traditional risk stratification tools, such as CURB-65... read more 

Severe pneumonia is the most common cause of acute respiratory distress syndrome (ARDS), and precise and individualized assessment is a prerequisite for improving therapeutic outcomes. Of all bedside assessment tools, respiratory physiological indica... read more 

Self-supervised polysomnography foundation models (PSG FMs) aim to capture clinically useful information beyond sleep staging, yet are rarely compared with sleep-staging encoders pretrained at comparable scale and modality coverage. Using a common wh... read more 

Fréchet Distributional (FD) objectives provide an effective distribution-level signal for post-training generative models. For latent generative models, however, existing FD-based post-training methods optimize only the latent generator while keeping... read more 

DNA methylation is a critical epigenetic modification that regulates gene expression and genome stability, primarily catalyzed by the DNA methyltransferase 3 (DNMT3) family of enzymes. Distinguishing precise sequence-specific flanking preferences bet... read more 

Retrieval-Augmented Generation (RAG) systems are increasingly used for biomedical Question Answering (QA). However, evaluating their effectiveness remains challenging due to the lack of reliable reference resources and the frequent misalignment betwe... read more 

Autonomous driving (AD) relies on multi-sensor perception to interpret the surrounding environment. However, the robustness of camera--radar fusion under adversarial conditions remains largely unexplored. This paper presents a systematic measurement ... read more 

Reliable scene understanding requires deciding which predictions to trust, retain, or inspect. In semantic segmentation, component failure predictors support these decisions, but their predictive performance does not fully describe the value of the r... read more 

Heterogeneous medical image data motivate domain-specialized diffusion experts, but expert specialization alone does not determine how their predictions should be combined during sampling. Learning a global router is particularly challenging when the... read more