The field of physics-informed neural networks (PINNs) is rapidly advancing, with a focus on improving the accuracy and stability of these models for solving partial differential equations (PDEs). Recent developments have centered on addressing the challenges of loss weight selection, model complexity, and the incorporation of external solvers. Notably, researchers are exploring innovative methods to balance loss function components during training, such as adaptive loss weighting mechanisms. Additionally, there is a growing interest in combining PINNs with other numerical methods, like isogeometric analysis and algebraic multigrid methods, to tackle complex engineering problems. These advancements have the potential to significantly improve the precision and robustness of PINNs in solving PDEs. Some noteworthy papers in this area include: The paper on Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics, which proposes a two-dimensional analysis-based weighting scheme to improve stability and accuracy. The paper on Gated X-TFC, which introduces a novel framework for soft domain decomposition, achieving superior accuracy and computational efficiency for sharp-gradient PDEs.