The field of medical image segmentation is moving towards leveraging semi-supervised learning techniques to overcome the challenges of limited annotated data and domain shift. Recent developments have focused on designing novel frameworks that can effectively utilize unlabeled data to improve model performance and adaptability across different domains. Notable advancements include the use of pseudo-labeling methods, momentum encoders, and diverse teaching strategies to generate reliable pseudo-labels and enhance model robustness. These innovations have led to state-of-the-art performance in various medical image segmentation tasks, including semi-supervised medical image segmentation, unsupervised medical domain adaptation, and universal lesion detection. Noteworthy papers include: Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning, which proposes a novel pseudo-labeling method for medical image segmentation. MoSSDA: A Semi-Supervised Domain Adaptation Framework for Multivariate Time-Series Classification using Momentum Encoder achieves state-of-the-art performance for multivariate time-series classification. Boosting Generic Semi-Supervised Medical Image Segmentation via Diverse Teaching and Label Propagation develops a generic framework that masters semi-supervised medical image segmentation, semi-supervised medical domain generalization, and unsupervised medical domain adaptation. Unified and Semantically Grounded Domain Adaptation for Medical Image Segmentation introduces a unified framework that supports both source-accessible and source-free adaptation. Uncertainty-aware Cross-training for Semi-supervised Medical Image Segmentation proposes an uncertainty-aware cross-training framework that incorporates two distinct subnets to mitigate cognitive biases within the model. COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets establishes a universal framework for multi-heterogeneous ultrasound datasets.