Metraipolis › archive › dc_3db73e384a1f
RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models — arXiv:2611.06047
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06047
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:29:53.836Z
- SHA-256 of the archived text
55629ab01b465374cb0f9b2e5c41c41323cd78e885cc8c9d5f70fc13b74b152a- Stable URL of this page
https://metraipolis.com/documento/dc_3db73e384a1f
How to cite
RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models — arXiv:2611.06047 — arXiv (en), https://arxiv.org/abs/2611.06047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3db73e384a1f (Metraipolis archive dc_3db73e384a1f, sha256 55629ab01b465374cb0f9b2e5c41c41323cd78e885cc8c9d5f70fc13b74b152a)
BibTeX
@misc{dc3db73e384a1f,
title = {RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models — arXiv:2611.06047},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06047},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3db73e384a1f; sha256 55629ab01b465374cb0f9b2e5c41c41323cd78e885cc8c9d5f70fc13b74b152a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large vision-language models (LVLMs) have recently been extended to handle multiple input images, but this extension dramatically increases the visual token budget, making visual-token pruning not merely an efficiency option but a practical necessity. Existing visual-token pruning methods, primarily designed for the single-image setting, rely on attention-derived saliency signals to estimate per-token importance. However, this attention-centric design transfers poorly to the multi-image regime: it causes substantial performance degradation on multi-image benchmarks, suffers from strong positional bias, and loses discriminative attention signals as the number of input images increases. To test whether attention-selected tokens are truly important for multi-image reasoning, we conduct two complementary causal probes Leave-One-In and Leave-One-Deletion, which measure token importance by restoring individual tokens to a zeroed visual sequence or removing them from the full sequence. Attention-based pruners provide only marginal gains over random selection, showing that attention is a weak proxy for visual-token importance in multi-image reasoning. Motivated by this gap, we propose Relation and Information Aware Pruning (RI-Prune), a training-free, attention-free pre-decoder selector for multi-image visual token pruning. RI-Prune scores each visual token using a z-normalized combination of three signals computed from projector outputs: query relevance, cross-image correspondence with compact per-image prototypes, and intra image representativeness. By integrating these signals, RI-Prune performs balanced per-image Top-K selection to preserve information across input images. Across multiple multi-image benchmarks and three LVLM backbones, RI-Prune achieves a stronger trade-off between token reduction and task performance than prior pruning methods, particularly under aggressive token budgets. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.06047 — 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 2026-11-05T18:19:49.049Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).