@inproceedings{jiang-etal-2025-dcp,
    title = "{DCP}: Dual-Cue Pruning for Efficient Large Vision-Language Models",
    author = "Jiang, Lei  and
      Zhang, Zixun  and
      Zeng, Yuting  and
      Xie, Chunzhao  and
      Liu, Tongxuan  and
      Li, Zhen  and
      Cheng, Lechao  and
      Xu, Xiaohua",
    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.1074/",
    pages = "21202--21215",
    ISBN = "979-8-89176-332-6",
    abstract = "Large Vision-Language Models (LVLMs) achieve remarkable performance in multimodal tasks but suffer from high computational costs due to the large number of visual tokens. Existing pruning methods either apply after visual tokens enter the LLM or perform pre-pruning based solely on visual attention. Both fail to balance efficiency and semantic alignment, as post-pruning incurs redundant computation, while visual-only pre-pruning overlooks multimodal relevance.To address this limitation, we propose Dual-Cue Pruning (DCP), a novel cross-modal pruning framework that jointly considers textual semantics and visual self-attention. DCP consists of a text-aware computation module, which employs a gradient-weighted attention mechanism to enhance text-visual alignment, and an image-aware computation module, which utilizes deep-layer self-attention distributions to retain essential structural information. By integrating both cues, DCP adaptively selects the most informative visual tokens, achieving efficient inference acceleration while maintaining strong task performance. Experimental results show that DCP can retain only 25{\%} of the visual tokens, with a minimal performance degradation of only 0.063{\%} on LLaVA-1.5-13B, demonstrating its effectiveness in balancing efficiency and accuracy."
}