@inproceedings{wang-etal-2025-prolongvid,
    title = "{P}ro{L}ong{V}id: A Simple but Strong Baseline for Long-context Video Instruction Tuning",
    author = "Wang, Rui  and
      Li, Bohao  and
      Dai, Xiyang  and
      Yang, Jianwei  and
      Chen, Yi-Ling  and
      Xing, Zhen  and
      Yang, Yifan  and
      Chen, Dongdong  and
      Qiu, Xipeng  and
      Wu, Zuxuan  and
      Jiang, Yu-Gang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1570/",
    pages = "30824--30837",
    ISBN = "979-8-89176-332-6",
    abstract = "Video understanding is essential for multimodal large language models (MLLMs) to interact effectively with users and the real world. However, analyzing long videos remains a major challenge due to the lack of high-quality video instruction data and effective training strategies. In this paper, we introduce a simple yet effective baseline for long-context video understanding, including dataset construction and training recipes. We curate a large-scale video instruction dataset with over 1M samples, encompassing videos from a few seconds to several minutes across diverse sources, without any human annotations. Additionally, we propose a progressive video instruction tuning strategy that incrementally increases input context length, enabling better utilization of videos of varying durations. Comprehensive experiments demonstrate that our dataset significantly outperforms existing video instruction datasets for fine-tuning MLLMs. Furthermore, our training approach establishes a strong video MLLM baseline, surpassing previous open-source models on video benchmarks and outperforming proprietary models like GPT-4V and GPT-4o-mini on VideoMME, even with a compact 7B model."
}