Preprint · 2026 · Open access
DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation
Research Square · Published 20 February 2026 · DOI 10.21203/rs.3.rs-8917857/v1
In brief
“DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation” is a 2026 preprint by Tingwen Zhang and 3 co-authors, published in Research Square. OpenAlex counts 1 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.
- Citations
- 1
- Most cited in
- 2026 (1)
- References
- 9
- Authors
- 4
Abstract
Recent advances in autonomous “AI scientist” systems have demonstrated the ability to automatically write scientific manuscripts and codes with execution. However, producing a publication-grade scientific diagram (e.g., teaser figure) is still a major bottleneck in the “end-to-end” paper generation process. For example, a teaser figure acts as a strategic visual interface and serves a different purpose than derivative data plots. It demands conceptual synthesis and planning to translate complex logic workflow into a compelling graphic that guides intuition and sparks curiosity. Existing AI scientist systems usually omit this component or fall back to an inferior alternative. To bridge this gap, we present DiagramBank, a largescale dataset consisting of 89,422 schematic diagrams curated from existing top-tier scientific publications, designed for multimodal retrieval and exemplar-driven scientific figure generation. DiagramBank is developed through our automated curation pipeline that extracts figures and corresponding in-text references, and uses a CLIP-based filter to differentiate schematic diagrams from standard plots or natural images. Each instance is paired with rich context from abstract, caption, to figure-reference pairs, enabling information retrieval under different query granularities. We release DiagramBank in a ready-to-index format and provide a retrieval-augmented generation codebase to demonstrate exemplar-conditioned synthesis of teaser figures. DiagramBank is publicly available at https:// huggingface.co/datasets/zhangt20/DiagramBank with code at https: //github.com/csml-rpi/DiagramBank.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhang, T., Yue, L., Xu, Z., & Pan, S. (2026). DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation. Research Square. https://doi.org/10.21203/rs.3.rs-8917857/v1
MLA 9
Zhang, Tingwen, et al. “DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-8917857/v1.
Chicago
Zhang, Tingwen, Ling Yue, Zhen Xu, and Shaowu Pan. 2026. “DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation.” Research Square. https://doi.org/10.21203/rs.3.rs-8917857/v1.
Harvard
Zhang, T. et al. (2026) ‘DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation’, Research Square. doi:10.21203/rs.3.rs-8917857/v1.
IEEE
T. Zhang, L. Yue, Z. Xu, and S. Pan, “DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation,” Research Square, 2026, doi: 10.21203/rs.3.rs-8917857/v1.
BibTeX
@misc{zhang2026diagrambank,
title = {{DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation}},
author = {Zhang, Tingwen and Yue, Ling and Xu, Zhen and Pan, Shaowu},
howpublished = {Research Square},
year = {2026},
doi = {10.21203/rs.3.rs-8917857/v1},
url = {https://doi.org/10.21203/rs.3.rs-8917857/v1}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- schematic diagrams
- retrieval-augmented generation
- multimodal retrieval
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Zhang, T., Yue, L., Xu, Z., & Pan, S. (2026). DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation. Research Square. https://doi.org/10.21203/rs.3.rs-8917857/v1
How many times has this paper been cited?
1 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Research Square.
Who wrote this paper?
Tingwen Zhang, Ling Yue, Zhen Xu, Shaowu Pan.
What is the DOI of this paper?
10.21203/rs.3.rs-8917857/v1. The permanent link is https://doi.org/10.21203/rs.3.rs-8917857/v1.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.