The field of 3D scene representation and rendering is moving towards more efficient and scalable methods. Recent developments have focused on improving the performance of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS) techniques, which are critical for applications such as autonomy testing, medical imaging, and scientific visualization. Notable advancements include the use of sparse local fields, hybrid neural and tensorial representations, and adaptive time-step training strategies. These innovations have led to significant improvements in training and rendering times, as well as enhanced capabilities for handling complex scenes and multi-sensor simulations. Noteworthy papers include: SaLF, which presents a novel volumetric representation that supports rasterization and raytracing, achieving fast training and rendering capabilities. NerT-CA, which proposes a hybrid approach for accelerated 4D reconstructions with sparse-view X-ray coronary angiography, outperforming previous works in training time and reconstruction accuracy.