Metraipolis › archive › dc_cf28cf4f5daf
ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs — arXiv:2609.34558
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34558
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:52:15.563Z
- SHA-256 of the archived text
00038c8e1b7d135c2bd0c1116e1e342c935ed017e8f949d97d5d98471c113cfd- Stable URL of this page
https://metraipolis.com/documento/dc_cf28cf4f5daf
How to cite
ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs — arXiv:2609.34558 — arXiv (en), https://arxiv.org/abs/2609.34558 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf28cf4f5daf (Metraipolis archive dc_cf28cf4f5daf, sha256 00038c8e1b7d135c2bd0c1116e1e342c935ed017e8f949d97d5d98471c113cfd)
BibTeX
@misc{dccf28cf4f5daf,
title = {ACPruner: Visual Token Pruning as Biased Attention Coverage Maximization in LVLMs — arXiv:2609.34558},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34558},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf28cf4f5daf; sha256 00038c8e1b7d135c2bd0c1116e1e342c935ed017e8f949d97d5d98471c113cfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34558. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Vision-Language Models (LVLMs) face significant computational inefficiencies caused by the large number of visual tokens. Existing visual token pruning methods mainly focus on either retaining individually important tokens or selecting mutually diverse ones. In this work, we revisit visual token pruning from a coverage perspective and formulate it as a biased attention coverage maximization problem. The key idea is to select a compact token subset whose encoder-side outgoing attention can jointly cover the image while assigning higher coverage priority to more informative regions. From this perspective, we propose ACPruner, a training-free visual token pruning framework for efficient LVLM inference. ACPruner first estimates token importance by combining intra-modal saliency and inter-modal relevance, then derives token-wise coverage from attention patterns within the vision encoder, and finally performs greedy selection to maximize the proposed coverage objective. Extensive experiments across multiple LVLM backbones, including LLaVA-1.5-7B/13B, LLaVA-NeXT-7B/13B, Qwen2.5-VL-7B, and LLaVA-OneVision-7B, show that ACPruner consistently achieves strong performance retention while delivering substantial end-to-end inference speedups. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.34558 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T23:29:27.394Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).