@article{chainofvisualthoughtteachingvlmstoseeand,
  title = {Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens},
  author = {Yiming Qin and Bomin Wei and Jiaxin Ge and Konstantinos Kallidromitis and Stephanie Fu and Trevor Darrell and XuDong Wang},
  year = {2025},
  eprint = {2511.19418},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.19418},
}