The field of human digitization and recognition is experiencing significant growth, with a focus on improving the accuracy and robustness of 3D human reconstruction, pose estimation, and recognition systems. Researchers are exploring novel approaches to address the challenges associated with geometric inconsistencies, scale variations, and background noise interference. Notably, the development of unified models and frameworks that integrate multiple tasks, such as human generation and reconstruction, is becoming increasingly popular. These models have shown promising results in achieving state-of-the-art performance on various benchmarks and datasets. Furthermore, the creation of large-scale datasets and the application of advanced techniques, such as Gaussian restoration and hypergraph-based modeling, are contributing to the advancement of the field. Noteworthy papers include: HumanDreamer-X, which introduces a novel framework for photorealistic single-image human avatars reconstruction. SapiensID, which proposes a unified model for human recognition that achieves robust performance across diverse settings. RCCFormer, which presents a robust Transformer-based crowd counting network that surpasses traditional baselines. HGMamba, which develops a Hyper-GCN-Mamba network for enhancing 3D human pose estimation. SIGMAN, which proposes a latent space generation paradigm for 3D human digitization that produces high-quality 3D human Gaussians.