STEM Education

STEM education research currently focuses on leveraging artificial intelligence, particularly large language models (LLMs) and multimodal models, to personalize learning, automate assessment (including multimodal answer sheets), and improve the dissemination of STEM content via social media. Key algorithmic approaches include gradient boosting, sentence-BERT, and various neural network architectures for tasks like stance detection and analogical reasoning. These advancements aim to enhance STEM learning experiences, address biases in educational resources, and improve access to quality STEM education, particularly in underserved regions.