AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding
Xiao Wang, Qingyi Si, Shiyu Zhu, Jianlong Wu, Li Cao, Liqiang Nie
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.
BibTeX
@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://aclanthology.org/2025.findings-acl.283/",
doi = "10.18653/v1/2025.findings-acl.283",
pages = "5417--5432",
ISBN = "979-8-89176-256-5"
}