The field of computational microscopy is moving towards the development of more accurate and robust image reconstruction methods. Recent research has focused on addressing the challenges of unknown probes, low-signal conditions, and artifact removal in various microscopy techniques. Innovative approaches, such as the use of neural networks and mathematical optimization, are being explored to improve image quality and fidelity. These advances have the potential to significantly impact the field of materials science, biology, and nanotechnology. Noteworthy papers include: Learning neural representations for X-ray ptychography reconstruction with unknown probes, which introduces a self-supervised framework for simultaneous object and probe recovery. Fidelity-preserving enhancement of ptychography with foundational text-to-image models, which proposes a plug-and-play framework for integrating physics model-based phase retrieval with text-guided image editing. High-Quality Tomographic Image Reconstruction Integrating Neural Networks and Mathematical Optimization, which develops a novel technique for reconstructing images from projection-based nano- and microtomography. Neutron Reflectometry by Gradient Descent, which proposes a novel approach for optimizing reflectivity data analysis by performing gradient descent on the forward reflection model itself.