The field of pathology image analysis is moving towards more interpretable and reliable models. Recent developments have focused on improving the accuracy and robustness of survival analysis and anomaly detection in pathology images. Models that incorporate prior knowledge and uncertainty awareness are becoming increasingly popular, as they can provide more accurate and trustworthy results. Noteworthy papers include: IPGPhormer, which proposes a novel framework for survival analysis that provides interpretability at both tissue and cellular levels. Uncertainty-Aware Learning Policy, which addresses the issue of diagnostic uncertainty in medical AI. DictAS, which enables a unified model to detect visual anomalies in unseen object categories without any retraining on the target data. A Robust BERT-Based Deep Learning Model, which achieves state-of-the-art results in automated cancer type extraction from unstructured pathology reports. Normal and Abnormal Pathology Knowledge-Augmented Vision-Language Model, which enhances accuracy and robustness to variability in pathology images and provides interpretability through image-text associations.