MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval

• URL: http://arxiv.org/abs/2603.13349v1
• Date: Sat, 07 Mar 2026 15:17:22 GMT
• Title: MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval
• Abstract summary: Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure.<n>Existing VDR models struggle to balance effectiveness and efficiency when processing high-resolution documents.<n>We propose a new X-VisEmb paradigm that progresses from multi-resolution sampling and encoding, through cross-granularity feature fusion, to adaptive representation distillation.
• Score: 111.99106496142474
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure to ensure retrieval efficacy while maintaining computational efficiency. Existing VDR models struggle to balance effectiveness and efficiency when processing high-resolution documents: they often either lose fine-grained information or generate an excessive number of visual tokens, resulting in significant indexing overhead and high retrieval latency. In this work, we rethink the visual encoding mechanism and propose a new X-VisEmb paradigm that progresses from multi-resolution sampling and encoding, through cross-granularity feature fusion, to adaptive representation distillation. A preliminary study validates its feasibility and effectiveness in capturing complementary visual cues at varying scales. Building on the insights, we develop MURE, a novel framework that employs VLMs as a hierarchical multi-resolution encoder, integrates resolution-level Matryoshka representation learning (RMRL) for effective feature fusion, and applies a semantic-aware hierarchical clustering mechanism for visual token compression. Experiments on two widely used VDR benchmarks show that our MURE framework consistently beats strong baselines. Furthermore, it significantly outperforms ColPali with only 50% of its visual token budget.

Related papers

• RADIO1D: Elastic Representations for Condensed Vision Modeling [69.84453279129937]
  This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.<n>We introduce RADIO1D, which compresses images into a compact, variable-length 1D token sequence using multi-teacher knowledge distillation and an autoencoder design.<n>The resulting representations exhibit strong hierarchical summarization, enabling accurate scene understanding - even with a single token - and support improved composition-aware image retrieval.
  arXiv  Detail & Related papers  (2026-07-03T22:58:54Z)
• Latent Visual States for Efficient Multimodal Reasoning [58.350643620457]
  EVA (LatEnt Visual StAtes) is a novel framework that generates continuous latent visual representations.<n>These internal representations manifest as an adaptive sequence of Latent_slot tokens.<n> EVA achieves significant performance gains while enhancing inference efficiency.
  arXiv  Detail & Related papers  (2026-06-23T07:22:22Z)
• Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification [80.62512020268626]
  UniAR is a unified autoregressive framework where a single visual tokenizer serves as the key bridge between understanding and generation.<n>UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme.<n>A diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images.
  arXiv  Detail & Related papers  (2026-06-16T17:59:22Z)
• VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions [51.41587958253802]
  We introduce VISion On Request (VISOR), a method that reduces inference cost without discarding visual information.<n>VISOR improves efficiency by sparsifying the interaction between image and text tokens.<n>Experiments show that VISOR drastically reduces computational cost while matching or exceeding state-of-the-art results.
  arXiv  Detail & Related papers  (2026-03-24T17:58:17Z)
• CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding [71.88471147281406]
  We propose an auto-regressive generation approach, CausalEmbed, for constructing multi-vector embeddings.<n>By incorporating iterative margin loss during contrastive training, CausalEmbed encourages embedding models to learn compact and well-structured representations.<n>Our method enables efficient VDR tasks using only dozens of visual tokens, achieving a 30-155x reduction in token count.
  arXiv  Detail & Related papers  (2026-01-29T04:47:27Z)
• ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning [8.933549837045932]
  Large Vision-Language Models incur high computational costs due to significant redundancy in their visual tokens.<n>We propose a Visual and Textual Semantic Collaborative Pruning framework (ViTCoP) that combines redundancy filtering in the vision encoder with step-wise co-pruning within the Large Language Models.
  arXiv  Detail & Related papers  (2026-01-25T12:47:30Z)
• Infusing fine-grained visual knowledge to Vision-Language Models [5.487134463783365]
  Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs)<n>We propose a fine-tuning method explicitly designed to achieve optimal balance between fine-grained domain adaptation and retention of the pretrained VLM's broad multimodal knowledge.<n>Our approach consistently achieves strong results, notably retaining the visual-text alignment without utilizing any text data or the original text encoder during fine-tuning.
  arXiv  Detail & Related papers  (2025-08-16T19:12:09Z)
• A Multi-Granularity Retrieval Framework for Visually-Rich Documents [4.804551482123172]
  We propose a unified multi-granularity multimodal retrieval framework tailored for two benchmark tasks: MMDocIR and M2KR.<n>Our approach integrates hierarchical encoding strategies, modality-aware retrieval mechanisms, and vision-language model (VLM)-based candidate filtering.<n>Our framework demonstrates robust performance without the need for task-specific fine-tuning.
  arXiv  Detail & Related papers  (2025-05-01T02:40:30Z)
• DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs [124.52164183968145]
  We present DyMU, an efficient, training-free framework that reduces the computational burden of vision-language models (VLMs)<n>Our approach comprises two key components. First, Dynamic Token Merging (DToMe) reduces the number of visual token embeddings by merging similar tokens based on image complexity.<n>Second, Virtual Token Unmerging (VTU) simulates the expected token sequence for large language models (LLMs) by efficiently reconstructing the attention dynamics of a full sequence.
  arXiv  Detail & Related papers  (2025-04-23T18:38:18Z)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models [50.98559225639266]
  We investigate the contributions of visual features from different encoder layers using 18 benchmarks spanning 6 task categories.<n>Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.<n>We propose the instruction-guided vision aggregator, a module that dynamically integrates multi-layer visual features based on textual instructions.
  arXiv  Detail & Related papers  (2024-12-26T05:41:31Z)
• FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression [45.37530855889661]
  High-resolution images lead to a quadratic increase in the number of visual tokens input into Multi-modal Large Language Models. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.
  arXiv  Detail & Related papers  (2024-11-21T15:37:52Z)
• Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models [56.76307866160105]
  We propose a contrastive learning framework, termed Document Object COntrastive learning (DoCo) DoCo leverages an auxiliary multimodal encoder to obtain the features of document objects and align them to the visual features generated by the vision encoder of Large Visual-Language Models (LVLMs) We demonstrate that the proposed DoCo serves as a plug-and-play pre-training method, which can be employed in the pre-training of various LVLMs without inducing any increase in computational complexity during the inference process.
  arXiv  Detail & Related papers  (2024-02-29T10:17:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.