International Journal of New Developments in Education, 2026, 8(2); doi: 10.25236/IJNDE.2026.080207.
Huanhuan Feng1, Lingli Wang1, Yuting Wu2
1School of Foreign Languages, Jingdezhen Vocational University of Art, Jingdezhen, Jiangxi, China
2School of Finance, Economics and Law, Jingdezhen Vocational University of Art, Jingdezhen, Jiangxi, China
The convergence of artificial intelligence, educational digitalization, and cultural-industrial transformation is reshaping talent cultivation in vocational higher education. Under these conditions, vocational undergraduate foreign language education can no longer remain confined to general language instruction or discrete skills training; it must respond more directly to regional industrial upgrading, cultural internationalization, and students’ future professional adaptability. Focusing on Jingdezhen’s ceramic cultural industry, this paper develops a conceptual framework for embedding multimodal large language models (MLLMs) into collaborative education. Drawing on sociocultural mediation, situated learning, multimodality, collaborative governance, and vocational education scholarship, the paper argues that MLLMs should be understood not merely as instructional tools or writing assistants, but as mediating infrastructures that connect curriculum, pedagogy, authentic industrial scenarios, multimodal resources, and the global communication of local culture. The paper proposes a four-dimensional model composed of value orientation, capability architecture, collaborative mechanism, and implementation pathways. It further explains how these dimensions interact through curriculum reconstruction, scenario-based pedagogy, localized resource development, dual-competence faculty construction, performance-oriented assessment, and ethics-based governance. The study contributes to current discussions on the educational implications of MLLMs, the reform of vocational undergraduate foreign language education, and the role of education in supporting culturally distinctive regional industries.
multimodal large language models; vocational undergraduate education; foreign language education; ceramic cultural industry; collaborative education
Huanhuan Feng, Lingli Wang, Yuting Wu. Multimodal LLM-Driven Collaborative Education between Vocational Undergraduate Foreign Language Education and the Ceramic Culture Industry. International Journal of New Developments in Education (2026), Vol. 8, Issue 2: 47-55. https://doi.org/10.25236/IJNDE.2026.080207.
[1] Zapata, G. C., Kalantzis, M., & Cope, B. (2023). Multiliteracies in international educational contexts. Taylor & Francis.
[2] Xinhua. (2025, October 21). Xinhua headlines: From clay to codes, AI transforms China’s porcelain capital. https://english.news.cn/20251021/672b39015a954ddb9a1580073e55d2f2/c.html
[3] Picca, D. (2025). Not Minds, but Signs: Reframing LLMs through Semiotics. arXiv preprint arXiv:2505.17080.
[4] Shahzad, T., Mazhar, T., Tariq, M. U., Ahmad, W., Ouahada, K., & Hamam, H. (2025). A comprehensive review of large language models: issues and solutions in learning environments. Discover Sustainability, 6(1), 27.
[5] Billett, S. (2022). Vocational education. In Oxford research encyclopedia of education.
[6] UNESCO Creative Cities Network. (2022). Jingdezhen monitoring report 2022. https://www.unesco. org/sites/default/files/medias/fichiers/2025/01/Jingdezhen_Monitoring_Report_2022.pdf
[7] Nielsen, W., & Yeo, J. (2022). Introduction to the special issue: Multimodal meaning-making in science. Research in Science Education, 52(3), 751-754.
[8] Alkhudiry, R. (2022). The Contribution of Vygotsky's Sociocultural Theory in Mediating L2 Knowledge Co-Construction. Theory & Practice in Language Studies (TPLS), 12(10).
[9] Cong-Lem, N. (2022). Vygotsky’s, Leontiev’s and Engeström’s cultural-historical (activity) theories: Overview, clarifications and implications. Integrative Psychological and Behavioral Science, 56(4), 1091-1112.
[10] Wenger, E. (2022). Jean Lave and Etienne Wenger. Understanding and using educational theories, 257.
[11] Jewitt, C., Bezemer, J., & O'Halloran, K. (2025). Introducing multimodality. Routledge.
[12] Ou Yang, L., Liu, J., Guo, Y., & Ling, J. (2024, June). Integrating collaborative learning into youth art education: Preservation and innovation of Guangzhou’s Polo Birth culture. In International Conference on Human-Computer Interaction (pp. 192-202). Cham: Springer Nature Switzerland.
[13] Lodge, J., Howard, S., Bearman, M. L., & Dawson, P. (2023). Assessment reform for the age of artificial intelligence.
[14] Gu, J. (2024). A Survey on Responsible Generative AI: What to Generate and What Not. arXiv preprint arXiv:2404.05783.