@article{flashvlmtextguidedvisualtokenselectionfo,
  title = {FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models},
  author = {Kaitong Cai and Jusheng Zhang and Jing Yang and Yijia Fan and Pengtao Xie and Jian Wang and Keze Wang},
  year = {2025},
  eprint = {2512.20561},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.20561},
}