@inproceedings{yan-etal-2026-sculpting,
    title = "Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework",
    author = "Yan, Yibo  and
      Ou, Mingdong  and
      Cao, Yi  and
      Zou, Xin  and
      Huo, Jiahao  and
      Liu, Shuliang  and
      Kwok, James  and
      Hu, Xuming",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1247/",
    pages = "24883--24925",
    ISBN = "979-8-89176-395-1",
    abstract = "Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in performance but suffers from prohibitive overhead, a problem that current efficiency methods like pruning and merging address imperfectly, creating a difficult trade-off between compression rate and feature fidelity. To overcome this dilemma, we introduce **Prune-then-Merge**, a novel two-stage framework that synergizes these complementary approaches. Our method first employs an adaptive pruning stage to filter out low-information patches, creating a refined, high-signal set of embeddings. Subsequently, a hierarchical merging stage compresses this pre-filtered set, effectively summarizing semantic content without the noise-induced feature dilution seen in single-stage methods. **Extensive experiments on 29 VDR datasets demonstrate that our framework consistently outperforms existing methods, significantly extending the near-lossless compression range and providing robust performance at high compression ratios.**"
}