# Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval

arXiv: https://arxiv.org/abs/2605.08421 · HTML: https://mlsanity.com/paper/2605.08421/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval](https://mlsanity.com/paper/2505.17166/) (2025)
- [Do Vision and Language Encoders Represent the World Similarly?](https://mlsanity.com/paper/2401.05224/) (2024)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)
- [Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model](https://mlsanity.com/paper/2507.05513/) (2025)
- [UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG](https://mlsanity.com/paper/2510.03663/) (2025)

## Abstract (arXiv)

Visual Document Retrieval (VDR) models mostly rely on late interaction architectures, in which documents are represented by a set of local patch embeddings and then matched against query tokens. While efficient, this architecture prioritizes local similarity over global layout structure of documents to estimate relevancy between documents and query. In practice, this leads to errors as relevance originates from layout structure of documents with heterogeneous layouts combining figures, tables, and text. We make document layout learnable without changing inference. We propose a multimodal encoder that augments local patch representations with a global layout embedding, trained via textual descriptions encoding document layout information. Across four ViDoRe-v2 datasets, our model improves over the strongest architecturally comparable ColPali/ColQwen baseline by +2.4 nDCG@5 and +2.3 MAP@5, with statistically significant per-dataset gains over ColQwen.