@article{scaffoldingcoordinatestopromotevision,
  title = {Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models},
  author = {Xuanyu Lei and Zonghan Yang and Xinrui Chen and Peng Li and Yang Liu},
  year = {2024},
  eprint = {2402.12058},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.12058v1},
}