HE, Fengjiang. Generative and Discriminative Models in Multimodal AI: An Analysis of Vision-Language Tasks. Transactions on Computer Science and Intelligent Systems Research, [S. l.], v. 10, p. 152–160, 2025. DOI: 10.62051/hdjsgp39. Disponível em: https://wepub.org/index.php/TCSISR/article/view/5704. Acesso em: 19 apr. 2026.