# Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding

arXiv: https://arxiv.org/abs/2503.14140 · HTML: https://mlsanity.com/paper/2503.14140/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 74 of its 98 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 74)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [DVQA: Understanding Data Visualizations via Question Answering](https://mlsanity.com/paper/1801.08163/) (2018)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [CogVLM2: Visual Language Models for Image and Video Understanding](https://mlsanity.com/paper/2408.16500/) (2024)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)

## Built on by (most cited first, 20 of 20)

- [A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends](https://mlsanity.com/paper/2507.09861/) (2025)
- [DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting](https://mlsanity.com/paper/2602.15958/) (2026)
- [LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?](https://mlsanity.com/paper/2505.12307/) (2025)
- [DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarios](https://mlsanity.com/paper/2508.00311/) (2025)
- [CodePercept: Code-Grounded Visual STEM Perception for MLLMs](https://mlsanity.com/paper/2603.10757/) (2026)
- [DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents](https://mlsanity.com/paper/2606.26122/) (2026)
- [DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding](https://mlsanity.com/paper/2511.11313/) (2025)
- [Hierarchical Evidence-Driven Reasoning for Long Document Understanding](https://mlsanity.com/paper/2607.04625/) (2026)
- [Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models](https://mlsanity.com/paper/2604.00161/) (2026)
- [InstructTable: Improving Table Structure Recognition Through Instructions](https://mlsanity.com/paper/2604.02880/) (2026)
- [MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems](https://mlsanity.com/paper/2605.19307/) (2026)
- [LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement](https://mlsanity.com/paper/2606.23539/) (2026)
- [UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation](https://mlsanity.com/paper/2606.24333/) (2026)
- [ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering](https://mlsanity.com/paper/2606.24602/) (2026)
- [Automatic Fine-grained Segmentation-assisted Report Generation](https://mlsanity.com/paper/2507.16623/) (2025)
- [HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents](https://mlsanity.com/paper/2603.26784/) (2026)
- [FlowTrain: Flow-Based Decoupled Training for Industrial-Grade Vision-Language Models](https://mlsanity.com/paper/2606.23087/) (2026)
- [Group Preference Collapse in Personalized Multimodal Large Language Models](https://mlsanity.com/paper/2607.22603/) (2026)
- [Question-Guided Evidence Acquisition for Multimodal Visual Question Answering](https://mlsanity.com/paper/2608.19739/) (2026)
- [Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction](https://mlsanity.com/paper/2609.15706/) (2026)

## Abstract (arXiv)

Multi-modal Large Language Models (MLLMs) have introduced a novel dimension to document understanding, i.e., they endow large language models with visual comprehension capabilities; however, how to design a suitable image-text pre-training task for bridging the visual and language modality in document-level MLLMs remains underexplored. In this study, we introduce a novel visual-language alignment method that casts the key issue as a Visual Question Answering with Mask generation (VQAMask) task, optimizing two tasks simultaneously: VQA-based text parsing and mask generation. The former allows the model to implicitly align images and text at the semantic level. The latter introduces an additional mask generator (discarded during inference) to explicitly ensure alignment between visual texts within images and their corresponding image regions at a spatially-aware level. Together, they can prevent model hallucinations when parsing visual text and effectively promote spatially-aware feature representation learning. To support the proposed VQAMask task, we construct a comprehensive image-mask generation pipeline and provide a large-scale dataset with 6M data (MTMask6M). Subsequently, we demonstrate that introducing the proposed mask generation task yields competitive document-level understanding performance. Leveraging the proposed VQAMask, we introduce Marten, a training-efficient MLLM tailored for document-level understanding. Extensive experiments show that our Marten consistently achieves significant improvements among 8B-MLLMs in document-centric tasks. Code and datasets are available at https://github.com/PriNing/Marten.