@article{letsrollabiftabirefinementforfinegrained,
  title = {Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models},
  author = {Yuhao Sun and Chengyi Cai and Jiacheng Zhang and Zesheng Ye and Xingliang Yuan and Feng Liu},
  year = {2026},
  eprint = {2601.20419},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.20419},
}