[1] Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https://arxiv.org/abs/2103.00020

[2] Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks (2019). https://arxiv.org/abs/1908.02265

[3] Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: a simple and performant baseline for vision and language (2019). https://arxiv.org/abs/1908.03557

[4] Chu, M., Chen, Y., Gui, H., Yu, S., Wang, Y., Jia, J.: Travellama: facilitating multi-modal large language models to understand urban scenes and provide travel assistance (2025). https://arxiv.org/abs/2504.16505

[5] Nguyen, D.Q., Nguyen, A.T.: Phobert: pre-trained language models for Vietnamese (2020). https://arxiv.org/abs/2003.00744

[6] Nguyen, Q.H., Nguyen, M.V.T., Van Nguyen, K.: New benchmark dataset and fine-grained cross-modal fusion framework for Vietnamese multimodal aspect-category sentiment analysis. Multimedia Syst. 31(1) (2024). ISSN 1432–1882. https://doi.org/10.1007/s00530-024-01558-8

[7] Van Nguyen, Q., et al.: Vitextvqa: a large-scale visual question answering dataset for evaluating Vietnamese text comprehension in images (2025). https://arxiv.org/abs/2404.10652

[8] Nha, N.V., Huan, P.T., Tuan, L.M., Son, L.H.: Enhancing visual question answering in Vietnamese using large language models combined with OCR systems. In: Nghia, P.T., Thai, V.D., Thuy, N.T., Huynh, V.-N., Huan, N.V. (eds.) Advances in Information and Communication Technology, pp. 300–310. Springer, Cham (2025). DOI: https://doi.org/10.1007/978-3-031-80943-9_34. ISBN 978-3-031-80943-9