@article{videollmknowswhentospeakenhancingtime,
  title = {VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format},
  author = {Yueqian Wang and Xiaojun Meng and Yuxuan Wang and Jianxin Liang and Jiansheng Wei and Huishuai Zhang and Dongyan Zhao},
  year = {2024},
  eprint = {2411.17991},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.17991v1},
}