CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception

@misc{carvalho2025cropvlm,
  title = {CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception},
  author = {Miguel Carvalho and Hélder Dias and Bruno Martins},
  year = {2025},
  eprint = {2511.19820},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.19820},
}