@article{scalablevisionlanguagemodeltrainingvia,
  title = {Scalable Vision Language Model Training via High Quality Data Curation},
  author = {Hongyuan Dong and Zijian Kang and Weijie Yin and Xiao Liang and Chao Feng and Jiao Ran},
  year = {2025},
  eprint = {2501.05952},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.05952v1},
}