@article{cliptextconditionedcontrastivelearningfo,
  title = {$β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment},
  author = {Fatimah Zohra and Chen Zhao and Hani Itani and Bernard Ghanem},
  year = {2025},
  eprint = {2512.12678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.12678},
}