The field of neural networks and uncertainty quantification is rapidly advancing, with a focus on developing innovative methods for capturing and propagating uncertainty in complex systems. Recent research has explored the use of neural ordinary differential equations, multidimensional distributional neural networks, and distance-informed neural processes to improve uncertainty estimation and calibration. These advances have the potential to enhance the reliability and performance of neural networks in a wide range of applications, from scientific modeling to image processing. Notable papers in this area include: Uncertainty Propagation Networks for Neural Ordinary Differential Equations, which introduces a novel family of neural differential equations that incorporate uncertainty quantification into continuous-time modeling. Distance-informed Neural Processes, which proposes a novel variant of Neural Processes that improves uncertainty estimation by combining global and distance-aware local latent structures. Multidimensional Distributional Neural Network Output Demonstrated in Super-Resolution of Surface Wind Speed, which presents a framework for training neural networks with a multidimensional Gaussian loss, generating closed-form predictive distributions over outputs with non-identically distributed and heteroscedastic structure.