@misc{pottanigari2026textpixels,
  title = {{Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA}},
  author = {Pottanigari, Nikhil Reddy and Kharaghani, Sepideh and Vadacchino, Saverio and Posada, Alejandro and Zhang, Ying},
  year = {2026},
  month = sep,
  eprint = {2609.22628},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2609.22628}
}