@inproceedings{wen-etal-2025-stop,
    title = "Stop Looking for ``Important Tokens'' in Multimodal Language Models: Duplication Matters More",
    author = "Wen, Zichen  and
      Gao, Yifeng  and
      Wang, Shaobo  and
      Zhang, Junyuan  and
      Zhang, Qintong  and
      Li, Weijia  and
      He, Conghui  and
      Zhang, Linfeng",
    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.505/",
    pages = "9972--9991",
    ISBN = "979-8-89176-332-6",
    abstract = "Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first defines an importance criterion for tokens and then prunes the unimportant vision tokens during inference. However, in this paper, we show that the importance is not an ideal indicator to decide whether a token should be pruned. Surprisingly, it usually results in inferior performance than random token pruning and leading to incompatibility to efficient attention computation operators. Instead, we propose DART (Duplication-Aware Reduction of Tokens), which prunes tokens based on its duplication with other tokens, leading to significant and training-free acceleration. Concretely, DART selects a small subset of pivot tokens and then retains the tokens with low duplication to the pivots, ensuring minimal information loss during token pruning. Experiments demonstrate that DART can prune 88.9{\%} vision tokens while maintaining comparable performance, leading to a 1.99$\times$ and 2.99$\times$ speed-up in total time and prefilling stage, respectively, with good compatibility to efficient attention operators."
}