@article{unifyingvisionlanguagelatentsforzerolabe,
  title = {Unifying Vision-Language Latents for Zero-label Image Caption Enhancement},
  author = {Sanghyun Byun and Jung Ick Guack and Mohanad Odema and Baisub Lee and Jacob Song and Woo Seong Chung},
  year = {2025},
  eprint = {2510.12931},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.12931},
}