@article{activatingvisualcontextandcommonsenserea,
  title = {Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs},
  author = {Jiaao Yu and Shenwei Li and Mingjie Han and Yifei Yin and Wenzheng Song and Chenghao Jia and Man Lan},
  year = {2025},
  eprint = {2510.21807},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.21807},
}