Sun, Jiangfeng, SiHao He, Zhonghong Ou, and Meina Song. “Structures Meet Semantics: Multimodal Fusion via Graph Contrastive Learning”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 30 (March 14, 2026): 25691–25699. Accessed May 15, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/39766.