@article{frompixelstopromptsvisionlanguagemodels,
  title = {From Pixels to Prompts: Vision-Language Models},
  author = {Khang Hoang Nhat Vo},
  year = {2026},
  eprint = {2605.07544},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.07544},
}