Song, Lingran, et al. “Sim4Seg: Boosting Multimodal Multi-Disease Medical Diagnosis Segmentation With Region-Aware Vision-Language Similarity Masks”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 11, Mar. 2026, pp. 9079-87, doi:10.1609/aaai.v40i11.37864.