The field of spatial omics and digital pathology is moving towards more efficient and accurate analysis of high-resolution data. Recent developments have focused on improving the computational efficiency and robustness of models for predicting spatial transcriptomics data from histology images. This includes the use of fully convolutional architectures and novel evaluation metrics. Additionally, there is a growing interest in developing controllable latent space augmentation methods for digital pathology, which can improve the performance of models in low-data regimes. Another area of research is the development of dynamic and morphology-guided binary-to-instance segmentation pipelines for renal pathology, which can enable more accurate morphometric analysis. Noteworthy papers include: Img2ST-Net, which proposes a novel histology-to-ST generation framework for efficient and parallel high-resolution ST prediction. Controllable Latent Space Augmentation for Digital Pathology, which introduces a fast and efficient generative model for controllable augmentations in the latent space. DyMorph-B2I, which presents a dynamic, morphology-guided binary-to-instance segmentation pipeline tailored for renal pathology.