@inproceedings{wang-etal-2025-adaretake,
    title = "{A}da{R}e{T}a{K}e: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding",
    author = "Wang, Xiao  and
      Si, Qingyi  and
      Zhu, Shiyu  and
      Wu, Jianlong  and
      Cao, Li  and
      Nie, Liqiang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.283/",
    pages = "5417--5432",
    ISBN = "979-8-89176-256-5",
    abstract = "Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding promising results. Nevertheless, our quantitative analysis shows that redundancy varies significantly across time and model layers, necessitating a more flexible compression strategy. We propose **AdaReTaKe**, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees. Integrated into state-of-the-art MLLMs, AdaReTaKe improves processing capacity from 256 to 2048 frames while preserving critical information. Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that AdaReTaKe outperforms existing methods by 2.3{\%} and 2.8{\%} for 7B and 72B models, respectively, with even greater improvements of 5.9{\%} and 6.0{\%} on the longest LVBench."
}