Trustworthy Multimodal AI: Unifying Vision–Language Models with Verifiable Safety Constraints. International Journal of Engineering & Extended Technologies Research (IJEETR), [S. l.], v. 4, n. 6, p. 5681–5688, 2022. DOI: 10.15662/IJEETR.2022.0406009. Disponível em: https://ijeetr.com/index.php/ijeetr/article/view/137. Acesso em: 5 dec. 2025.