@article{bridgingearsandeyesanalyzingaudioand,
  title = {Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation},
  author = {Xilin Jiang and Junkai Wu and Vishal Choudhari and Nima Mesgarani},
  year = {2025},
  eprint = {2505.06803},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.06803v1},
}