@article{aligningaudiovisualjointrepresentations,
  title = {Aligning Audio-Visual Joint Representations with an Agentic Workflow},
  author = {Shentong Mo and Yibing Song},
  year = {2024},
  eprint = {2410.23230},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.23230v2},
}