@article{llavaspenhancingvisualrepresentationwith,
  title = {LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs},
  author = {Haoran Lou and Chunxiao Fan and Ziyan Liu and Yuexin Wu and Xinxiang Wang},
  year = {2025},
  eprint = {2507.00505},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.00505v1},
}