TopPaper
15 February 2026
Today's Paper

Uni-Hema: Unified Model for Digital Hematopathology

Abdul Rehman, Iqra Rasool, Ayisha Imran, Mohsen Ali, Waqas Sultani • arXiv

This groundbreaking paper introduces Uni-Hema, the first unified, multi-task, multi-modal vision-language model specifically designed for digital hematopathology. It addresses the fragmentation in current AI approaches by enabling a single model to handle multiple tasks such as object detection (locating individual blood cells), classification (identifying cell types and diseases), semantic segmentation (outlining cells at pixel level), morphology prediction (describing detailed shape and feature abnormalities, e.g., irregular nuclei or vacuoles), masked language modeling, and visual question answering (VQA) across a wide range of hematological conditions. These include malignant diseases like leukemia, infectious ones like malaria, and non-malignant disorders such as sickle cell disease, anemia, and thalassemia.

View Full Abstract View Full Paper DOI: 10.48550/arXiv.2511.13889 Share