The recent advancements in the research area demonstrate a significant shift towards leveraging advanced machine learning models, particularly Large Language Models (LLMs), to address complex natural language processing (NLP) and vision tasks. A notable trend is the focus on enhancing model robustness and generalizability across diverse datasets and tasks, as evidenced by studies evaluating LLMs on crisis-related microblogs and visual computing tasks. Additionally, there is a growing interest in developing specialized models for specific linguistic challenges, such as Chinese Named Entity Recognition (NER) and Chinese Spelling Check (CSC), which aim to improve accuracy and efficiency through innovative pretraining strategies and character relation modeling. Furthermore, the integration of contextualized prompts and multi-task learning frameworks is being explored to advance event extraction from literary content and visual tasks, respectively. The field also sees a rise in the creation and utilization of specialized datasets for tasks like conflict event classification and citizen report categorization, emphasizing the importance of domain-specific data in model training and evaluation. Overall, the research is moving towards more efficient, robust, and domain-specific solutions, with a strong emphasis on leveraging the strengths of LLMs and transformer-based architectures.