Recent advancements in educational AI are focusing on enhancing personalized learning experiences and improving instructional content generation. A notable trend is the development of frameworks that simulate student artifacts, enabling teachers to practice diagnostic reasoning without violating privacy regulations. This approach addresses data scarcity in teacher training and supports professional development. Concurrently, large language models are being integrated into multi-agent systems for generating high-quality instructional videos, significantly reducing production costs while ensuring pedagogical coherence. Additionally, personalized learning systems are evolving through adaptive frameworks that identify skill gaps and recommend tailored resources, fostering a continuous feedback loop for students. The field is also exploring the calibration of AI grading systems to ensure reliability and accuracy, particularly in high-stakes assessments. Overall, educational AI is moving towards more integrated, scalable solutions that prioritize both educator support and student engagement, addressing critical challenges in modern educational environments.
Developing expertise in diagnostic reasoning requires practice with diverse student artifacts, yet privacy regulations prohibit sharing authentic student work for teacher professional development (PD)...
GenAI Units In Digital Design Education (GUIDE) is an open courseware repository with runnable Google Colab labs and other materials. We describe the repository's architecture and educational approach...
Personalized learning systems have emerged as a promising approach to enhance student outcomes by tailoring educational content, pacing, and feedback to individual needs. However, most existing system...
Learning Path Recommendation (LPR) aims to generate personalized sequences of learning items that maximize long-term learning effect while respecting pedagogical principles and operational constraints...
Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in scenarios that require strict logical rigor and prec...
Digital educational environments are expanding toward complex AI and human discourse, providing researchers with an abundance of data that offers deep insights into learning and instructional processe...
Recognizing and localizing student confusion from video is an important yet challenging problem in educational AI. Existing confusion datasets suffer from noisy labels, coarse temporal annotations, an...
In educational applications, LLMs exhibit several fundamental pedagogical limitations, such as their tendency to reveal solutions rather than support dialogic learning. We introduce ConvoLearn (https:...
Arithmetic puzzle games provide a controlled setting for studying difficulty in mathematical reasoning tasks, a core challenge in adaptive learning systems. We investigate the structural determinants ...
The rapid emergence of Large Language Models (LLMs) presents both opportunities and challenges for programming education. While students increasingly use generative AI tools, direct access often hinde...