The field of 3D object detection is moving towards leveraging radar-camera fusion to achieve robust and accurate detection in various environmental conditions. Recent developments have focused on designing novel architectures that exploit the advantages of radar point clouds, such as accurate distance estimation and speed information. These advancements have led to significant improvements in detection accuracy and inference speed, making them suitable for real-time deployment in autonomous driving applications. Noteworthy papers in this area include PAN, which introduced a pillars-attention-based network for 3D object detection, and RadarGaussianDet3D, which proposed a Gaussian-based 3D detector with improved feature extraction and optimization techniques. MLF-4DRCNet is also notable for its multi-level fusion approach, achieving state-of-the-art performance on several datasets.