@article{instructionaugmentedmultimodalalignment,
  title = {Instruction-augmented Multimodal Alignment for Image-Text and Element Matching},
  author = {Xinli Yue and Jianhui Sun and Junda Lu and Liangchao Yao and Fan Xia and Tianyi Wang and Fengyun Rao and Jing Lyu and Yuetang Deng},
  year = {2025},
  eprint = {2504.12018},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.12018v1},
}