@article{latentvisualstatesforefficientmultimodal,
  title = {Latent Visual States for Efficient Multimodal Reasoning},
  author = {Xiuwei Chen and Wentao Hu and Yongxin Wang and Zisheng Chen and Likui Zhang and Kun Xiang and Jianhua Han and Hui-Ling Zhen and Jingyuan Zou and Hang Xu and Xiaodan Liang},
  year = {2026},
  eprint = {2606.24233},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.24233},
}