@article{towardscalablevideonarrationatrainingfre,
  title = {Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models},
  author = {Tz-Ying Wu and Tahani Trigui and Sharath Nittur Sridhar and Anand Bodas and Subarna Tripathi},
  year = {2025},
  eprint = {2507.17050},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.17050},
}