@misc{wang2025audiovisualworldmodelsmultisensory,
      title={Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound}, 
      author={Jiahua Wang and Shannan Yan and Leqi Zheng and Jialong Wu and Yaoxin Mao},
      year={2025},
      eprint={2512.00883},
      archivePrefix={arXiv},
      primaryClass={cs.MM},
      url={https://arxiv.org/abs/2512.00883}, 
}