Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.20701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916997615321088 |
|---|---|
| author | Chu, Zhendong Xie, Jian Wang, Shen Wang, Zichao Wen, Qingsong |
| author_facet | Chu, Zhendong Xie, Jian Wang, Shen Wang, Zichao Wen, Qingsong |
| contents | 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 unified solution that excels across multiple educational tasks while maintaining strong generalization capabilities. Its adaptability makes it well-suited for real-world deployment in diverse learning environments. Furthermore, UniEDU is optimized for industry-scale deployment by significantly reducing computational overhead-achieving approximately a 300\% increase in efficiency-while maintaining competitive performance with minimal degradation compared to fully fine-tuned models. This work represents a significant step toward creating versatile AI systems tailored to the evolving demands of education. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniEDU: A Unified Language and Vision Assistant for Education Applications Chu, Zhendong Xie, Jian Wang, Shen Wang, Zichao Wen, Qingsong Computation and Language 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 unified solution that excels across multiple educational tasks while maintaining strong generalization capabilities. Its adaptability makes it well-suited for real-world deployment in diverse learning environments. Furthermore, UniEDU is optimized for industry-scale deployment by significantly reducing computational overhead-achieving approximately a 300\% increase in efficiency-while maintaining competitive performance with minimal degradation compared to fully fine-tuned models. This work represents a significant step toward creating versatile AI systems tailored to the evolving demands of education. |
| title | UniEDU: A Unified Language and Vision Assistant for Education Applications |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.20701 |