@article{spatialviltenhancingvisualspatialreasoni,
  title = {Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning},
  author = {Chashi Mahiul Islam and Oteo Mamo and Samuel Jacob Chacko and Xiuwen Liu and Weikuan Yu},
  year = {2025},
  eprint = {2510.03441},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.03441},
}