@article{readingnotthinkingunderstandingandbridgi,
  title = {Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs},
  author = {Kaiser Sun and Xiaochuang Yuan and Hongjun Liu and Chen Zhao and Cheng Zhang and Mark Dredze and Fan Bai},
  year = {2026},
  eprint = {2603.09095},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.09095},
}