@article{visionfoundryteachingvlmsvisualperceptio,
  title = {VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images},
  author = {Guanyu Zhou and Yida Yin and Wenhao Chai and Shengbang Tong and Xingyu Fu and Zhuang Liu},
  year = {2026},
  eprint = {2604.09531},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.09531},
}