Cover Image

Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ding, Yihao, Sun, Qiang, Wu, Puzhen, Li, Sirui, Luo, Siwen, Liu, Wei
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends
by: Ding, Yihao, et al.
Published: (2025)

DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral
by: Sun, Qiang, et al.
Published: (2025)

DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
by: Yan, Hao, et al.
Published: (2026)

VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding
by: Ding, Yihao, et al.
Published: (2025)

CircuitSynth: Reliable Synthetic Data Generation
by: Cheng, Zehua, et al.
Published: (2026)

Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
by: Sun, Qiang, et al.
Published: (2024)

SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding
by: Ding, Chuanghao, et al.
Published: (2024)

CasualSynth: Generating Structurally Sound Synthetic Data
by: Cheng, Zehua, et al.
Published: (2026)

DistilDoc: Knowledge Distillation for Visually-Rich Document Applications
by: Van Landeghem, Jordy, et al.
Published: (2024)

SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement
by: Jain, Chelsi, et al.
Published: (2025)

ScaleDoc: Scaling LLM-based Predicates over Large Document Collections
by: Zhang, Hengrui, et al.
Published: (2025)

DocReLM: Mastering Document Retrieval with Language Model
by: Wei, Gengchen, et al.
Published: (2024)

FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models
by: Dua, Karan, et al.
Published: (2025)

Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning
by: Mo, Ye, et al.
Published: (2025)

SynthRAR: Ring Artifacts Reduction in CT with Unrolled Network and Synthetic Data Training
by: Yang, Hongxu, et al.
Published: (2026)

VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding
by: de Rodrigo, Ignacio, et al.
Published: (2026)

PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding
by: Huang, Kui, et al.
Published: (2025)

DocTER: Evaluating Document-based Knowledge Editing
by: Wu, Suhang, et al.
Published: (2023)

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data
by: Chanin, David, et al.
Published: (2026)

Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs
by: Zhu, Fengbin, et al.
Published: (2023)

STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
by: Zhang, Wenxiao, et al.
Published: (2026)

Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation
by: Guo, Jiaxin, et al.
Published: (2025)

DocOS: Towards Proactive Document-Guided Actions in GUI Agents
by: Liu, Jingjing, et al.
Published: (2026)

Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources
by: Lupidi, Alisia, et al.
Published: (2024)

DermaSynth: Rich Synthetic Image-Text Pairs Using Open Access Dermatology Datasets
by: Yilmaz, Abdurrahim, et al.
Published: (2025)

SynthTools: A Framework for Scaling Synthetic Tools for Agent Development
by: Castellani, Tommaso, et al.
Published: (2025)

Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
by: Sharifzadeh, Sahand, et al.
Published: (2024)

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
by: Zhang, Xinyu, et al.
Published: (2025)

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

Multimodal Commonsense Knowledge Distillation for Visual Question Answering
by: Yang, Shuo, et al.
Published: (2024)

MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data
by: Poliakov, Mykhailo, et al.
Published: (2025)

LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding
by: Wu, Mingrui, et al.
Published: (2024)

VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction
by: Tran, Khai Phan, et al.
Published: (2024)

SynthAgent: Adapting Web Agents with Synthetic Supervision
by: Wang, Zhaoyang, et al.
Published: (2025)

Improving Vietnamese Legal Document Retrieval using Synthetic Data
by: Tien, Son Pham, et al.
Published: (2024)

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
by: Lin, Teng, et al.
Published: (2026)

DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding
by: Feng, Hao, et al.
Published: (2023)

SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task
by: Zhong, Ziije, et al.
Published: (2024)

DocReward: A Document Reward Model for Structuring and Stylizing
by: Liu, Junpeng, et al.
Published: (2025)

DocMEdit: Towards Document-Level Model Editing
by: Zeng, Li, et al.
Published: (2025)