MoDora: A Multimodal Document AI Assistant Harness
Summary: MoDora treats PDFs as editable, layout-aware multimodal component trees rather than flat chunks or images, enabling transparent structural inspection and refinement. Its QA agent provides cross-modal answers with bounding-box evidence grounding, achieving 71.1% AIC-Acc and >14% gains on MMDA. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yukai Wu (Shanghai Jiao Tong University)
- 2. Bangrui Xu (Shanghai Jiao Tong University)
- 3. Shaoli Yu (Shanghai Jiao Tong University)
- 4. Zirui Tang (Shanghai Jiao Tong University)
- 5. Xuanhe Zhou (Shanghai Jiao Tong University)
- 6. Yeye He (Microsoft)
- 7. Bin Wang (Shanghai AI Lab)
- 8. Conghui He (Shanghai AI Lab)
- 9. Guoliang Li (Tsinghua University)
- 10. Fan Wu (Shanghai Jiao Tong University)
BibTeX Citation
@article{wu_vldb26,
title = {{MoDora: A Multimodal Document AI Assistant Harness}},
author = {Wu, Yukai and Xu, Bangrui and Yu, Shaoli and Tang, Zirui and Zhou, Xuanhe and He, Yeye and Wang, Bin and He, Conghui and Li, Guoliang and Wu, Fan},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4794--4797},
doi = {10.14778/3827998.3828124},
url = {https://doi.org/10.14778/3827998.3828124},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 501 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB | 0.00017267905 |
| 9,066 | MoDora: Tree-Based Semi-Structured Document Analysis System | 2026 | SIGMOD | 5.2283159e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,406 | AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora | 2026 | SIGMOD |
| 2 | 10,791 | BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents | 2026 | VLDB |
| 3 | 11,529 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 4 | 10,804 | Document-to-Database: Extraction Meets Relational Semantics | 2026 | VLDB |
| 5 | 683 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB |
| 6 | 6,869 | Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents | 2025 | VLDB |
| 7 | 8,632 | DocDB: A Database for Unstructured Document Analysis | 2025 | VLDB |
| 8 | 6,886 | Multi-Objective Agentic Rewrites for Unstructured Data Processing | 2026 | VLDB |
| 9 | 7,318 | An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models | 2024 | VLDB |
| 10 | 9,066 | MoDora: Tree-Based Semi-Structured Document Analysis System | 2026 | SIGMOD |