Tag
This paper proposes UMMT, a token-level cross-modal transformer with contrastive multi-task learning for breast cancer subtype classification and survival prediction, achieving state-of-the-art results on METABRIC and TCGA-BRCA datasets.
SAGEAgent is an LLM-based clinical agent that sequentially decides which diagnostic modalities to acquire for cancer patients to balance predictive accuracy with clinical invasiveness, reducing acquisition burden by 55% while maintaining competitive survival prediction performance.
SHIFT is a missingness-aware survival model that uses masked self-attention to predict from incomplete genomic inputs without test-time imputation, showing strong generalization across cohorts in glioblastoma and lung squamous cell carcinoma.