[1]
“A Robust Two-Stage Retrieval-Augmented Vision-Language Framework for Knowledge-Intensive Multimodal Reasoning and Alignment”, CDIS, vol. 2, no. 2, pp. 42–52, Feb. 2026, Accessed: Feb. 22, 2026. [Online]. Available: https://pub.scientificirg.com/index.php/CDIS/article/view/40