This paper proposes Prototypical Guidance SAM (ProtoSAM), a novel semi-supervised framework for 3D medical image segmentation. To address the limitations of existing methods in generalization under limited annotations and high model complexity, our framework introduces a Token Prototype Encoder that replaces parametric clustering with dynamic prototype optimization through fuzzy assignment and momentum update mechanisms. The Prototype-adaptive Decoder explicitly integrates multi-scale clustering features and employs morphological post-processing to refine boundary accuracy. Experiments show that ProtoSAM achieves Dice scores of 0.78 and 0.55, and HD95 scores of 3.33 and 17.97 on two large public datasets. By generating high-quality pseudo-labels through knowledge prototypes, our method maintains performance comparable to fully-supervised using merely 33% labeled data, significantly reducing dependency on complete annotations. Code is available at: https://github.com/yanliugroup.

In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment. Our framework comprises two primary components: 1) SocioMind: a meticulously crafted digital brain that models personalities with systematic few-shot exemplars, incorporates a reflection process based on psychology principles, and emulates autonomy by initiating dialogue topics; 2) MoMat-MoGen: a text-driven motion synthesis paradigm for controlling the character's digital body. It integrates motion matching, a proven industry technique to ensure motion quality, with cutting-edge advancements in motion generation for diversity. Extensive experiments demonstrate that each module achieves state-of-the-art performance in its respective domain. Collectively, they enable virtual characters to initiate and sustain dialogues autonomously, while evolving their socio-psychological states. Concurrently, these characters can perform contextually relevant bodily movements. Additionally, an extension of DLP enables a virtual character to recognize and appropriately respond to human players' actions.

Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets. To advance the diversity and annotation quality of human models, we introduce a new synthetic dataset, SynBody, with three appealing features: 1) a clothed parametric human model that can generate a diverse range of subjects; 2) the layered human representation that naturally offers high-quality 3D annotations to support multiple tasks; 3) a scalable system for producing realistic data to facilitate real-world tasks. The dataset comprises 1.2M images with corresponding accurate 3D annotations, covering 10,000 human body models, 1,187 actions, and various viewpoints. The dataset includes two subsets for human pose and shape estimation as well as human neural rendering. Extensive experiments on SynBody indicate that it substantially enhances both SMPL and SMPL-X estimation. Furthermore, the incorporation of layered annotations offers a valuable training resource for investigating the Human Neural Radiance Fields(NeRF).

Although the needle Electromyography (EMG) is an efficient means for Amyotrophic Lateral Sclerosis (ALS) diagnosis, the proper selection of muscles with high sensitivity is an important issue in clinical application. In this paper, we propose a new deep learning method called Wavelet-based Multi-branch Convolutional Neural Network (WM-CNN) for cross-individual ALS disease identification. The proposed method uses the multi-branch network as framework to learn the relationship among EMG samples of an EMG recording, in which each sub-network with three wavelet-based convolution layers (WCL) is used to extract features of the corresponding sample. Experiments show that the proposed method obtains better performance in cross-individual and cross-muscle experiments compared with other methods, which implies that the proposed method can extract general features of neurogenic injury and could be helpful to find proper muscles more sensitive for ALS disease identification.