@article{audioenhancedvisionlanguagemodelingwith,
  title = {Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion},
  author = {Yu Sun and Yin Li and Ruixiao Sun and Chunhui Liu and Fangming Zhou and Ze Jin and Linjie Wang and Xiang Shen and Zhuolin Hao and Hongyu Xiong},
  year = {2025},
  eprint = {2503.17551},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.17551v1},
}