Preprint · 2024 · Open access
Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
arXiv (Cornell University) · Published 22 May 2024 · DOI 10.48550/arxiv.2405.13872
In brief
“Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models” is a 2024 preprint by Qiji Zhou and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 87 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 87
- Most cited in
- 2026 (42)
- References
- 38
- Authors
- 6
Abstract
Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Large Language Models (MLLMs), enhancing their capability to tackle complex multimodal reasoning problems is a crucial frontier. However, incorporating multimodal rationales in CoT has yet to be thoroughly investigated. We propose the Image-of-Thought (IoT) prompting method, which helps MLLMs to extract visual rationales step-by-step. Specifically, IoT prompting can automatically design critical visual information extraction operations based on the input images and questions. Each step of visual information refinement identifies specific visual rationales that support answers to complex visual reasoning questions. Beyond the textual CoT, IoT simultaneously utilizes visual and textual rationales to help MLLMs understand complex multimodal information. IoT prompting has improved zero-shot visual reasoning performance across various visual understanding tasks in different MLLMs. Moreover, the step-by-step visual feature explanations generated by IoT prompting elucidate the visual reasoning process, aiding in analyzing the cognitive processes of large multimodal models
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhou, Q., Zhou, R., Hu, Z., Lu, P., Siyang, G., & Zhang, Y. (2024). Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.13872
MLA 9
Zhou, Qiji, et al. “Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2405.13872.
Chicago
Zhou, Qiji, Ruochen Zhou, Zike Hu, Panzhong Lu, Gao, Siyang, and Yue Zhang. 2024. “Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.13872.
Harvard
Zhou, Q. et al. (2024) ‘Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models’, arXiv (Cornell University). doi:10.48550/arxiv.2405.13872.
IEEE
Q. Zhou, R. Zhou, Z. Hu, P. Lu, G. Siyang, and Y. Zhang, “Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2405.13872.
BibTeX
@misc{zhou2024image,
title = {{Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models}},
author = {Zhou, Qiji and Zhou, Ruochen and Hu, Zike and Lu, Panzhong and Siyang, Gao, and Zhang, Yue},
howpublished = {arXiv (Cornell University)},
year = {2024},
doi = {10.48550/arxiv.2405.13872},
url = {https://doi.org/10.48550/arxiv.2405.13872}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 5 | |
| 2025 | 40 | |
| 2026 | 42 |
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- multimodal large language models
- chain-of-thought
- visual reasoning
- visual information extraction
- step-by-step reasoning
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?
Zhou, Q., Zhou, R., Hu, Z., Lu, P., Siyang, G., & Zhang, Y. (2024). Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2405.13872
How many times has this paper been cited?
87 times, according to OpenAlex on 19 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 at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Qiji Zhou, Ruochen Zhou, Zike Hu, Panzhong Lu, Gao, Siyang, Yue Zhang.
What is the DOI of this paper?
10.48550/arxiv.2405.13872, permanently at https://doi.org/10.48550/arxiv.2405.13872. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.