UniEDU: A Unified Language and Vision Assistant for Education Applications

UniEDU is a unified large multimodal model designed for K-12 educational applications including knowledge recommendation, knowledge tracing, time cost prediction, and user answer prediction, processing both text and images from educational materials. The model achieves approximately 3× computational efficiency improvement while maintaining competitive performance across multiple educational tasks.

Education materials for K-12 students often consist of multiple modalities, such as text and images, posing challenges for models to fully understand nuanced information in these materials. In this paper, we propose a unified language and vision assistant UniEDU designed for various educational applications, including knowledge recommendation, knowledge tracing, time cost prediction, and user answer prediction, all within a single model. Unlike conventional task-specific models, UniEDU offers a

Source

Framework Categories

Tool Types

Tags