@article{beyondclipknowledgeenhancedmultimodaltra,
  title = {Beyond CLIP: Knowledge-Enhanced Multimodal Transformers for Cross-Modal Alignment in Diabetic Retinopathy Diagnosis},
  author = {Argha Kamal Samanta and Harshika Goyal and Vasudha Joshi and Tushar Mungle and Pabitra Mitra},
  year = {2025},
  eprint = {2512.19663},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.19663},
}