@article{aligningforestandtreesinimageslongcaptio,
  title = {Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding},
  author = {Byeongju Woo and Zilin Wang and Byeonghyun Pak and Sangwoo Mo and Stella X. Yu},
  year = {2026},
  eprint = {2602.02977},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.02977},
}