# VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding

arXiv: https://arxiv.org/abs/2601.05125 · HTML: https://mlsanity.com/paper/2601.05125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [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)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding](https://mlsanity.com/paper/2203.06947/) (2022)
- [All You May Need for VQA are Image Captions](https://mlsanity.com/paper/2205.01883/) (2022)
- [Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion](https://mlsanity.com/paper/2501.17887/) (2025)
- [SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion](https://mlsanity.com/paper/2503.11576/) (2025)
- [OCR-IDL: OCR Annotations for Industry Document Library Dataset](https://mlsanity.com/paper/2202.12985/) (2022)
- [Optimized Table Tokenization for Table Structure Recognition](https://mlsanity.com/paper/2305.03393/) (2023)
- [PDFVQA: A New Dataset for Real-World VQA on PDF Documents](https://mlsanity.com/paper/2304.06447/) (2023)
- [NNE: A Dataset for Nested Named Entity Recognition in English Newswire](https://mlsanity.com/paper/1906.01359/) (2019)

## Abstract (arXiv)

This work introduces VERSE, a methodology for analyzing and improving Vision-Language Models applied to Visually-rich Document Understanding by exploring their visual embedding space. VERSE enables the visualization of latent representations, supporting the assessment of model feasibility. It also facilitates the identification of problematic regions and guides the generation of synthetic data to enhance performance in those clusters. We validate the methodology by training on the synthetic MERIT Dataset and evaluating on its real-world counterpart, MERIT Secret. Results show that VERSE helps uncover the visual features associated with error-prone clusters, and that retraining with samples containing these features substantially boosts F1 performance without degrading generalization. Furthermore, we demonstrate that on-premise models such as Donut and Idefics2, when optimized with VERSE, match or even surpass the performance of SaaS solutions like GPT-4 and Pixtral.