ADERINOKUN, Aderinsola. Unified Multimodal Transformers: Improving Vision-Language Models with Knowledge-Guided Attention Mechanisms. MZ Journal of Artificial Intelligence, [S. l.], v. 1, n. 2, 2024. Disponível em: http://mzresearch.com/index.php/MZJAI/article/view/272. Acesso em: 18 jul. 2025.