Fluvo AI: A Multimodal Agent For Bidirectional Conversion BETWEEN Natural Language AND Flowcharts
DOI:
https://doi.org/10.62431/wqa96589Keywords:
Artificial Intelligence (AI), Multimodal, Flowchart Generation, Natural Language, Generative AI, Visual DiagramsAbstract
In recent times, we have found that lots of educational content that we have, in terms of text, videos, or images, is not structured and not easy to understand. As a human mind, our tendency is to remember more and learn more from visualization and diagrams. Many traditional diagramming tools need users to create things manually using specific formats. Also, they do not provide proper editing through the user interface. Many AI diagramming tools provide editing with the help of prompting, which is also not efficient, so this paper introduces Fluvo AI, an intelligent system that can translate between natural language and flowcharts in both directions, which means it lets users edit their diagrams, improve components, structure of the diagram and adjust the frames. The system uses multi-modal understanding, knowledge extraction, logical step analysis, and automatic diagram creation to turn messy information into clear visual steps. Besides making flowcharts, Fluvo AI also provides a summary for videos, audios and images, which helps them understand in a simpler way. It will also help users in exporting the diagrams and the summaries. By mixing multi-modal AI with interactive visuals, FluvoAI makes it easier to understand information, cut down on manual work, and provide better visual presentation.
References
S. Palaskar, J. Libovický, S. Gella, and F. Metze, “Multimodal abstractive summarization for How2 videos,” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, Jul. 2019, pp. 6587–6596.
L. Logeswaran, S. Sohn, Y. Jang, M. Lee, and H. Lee, “Unsupervised task graph generation from instructional video transcripts,” in Findings of the Association for Computational Linguistics: ACL 2023, Jul. 2023, pp. 3392–3406.
A. Khullar and U. Arora, “MAST: Multimodal abstractive summarization with trimodal hierarchical attention,” in Proceedings of the EMNLP Workshop on NLP Beyond Text, Nov. 2020.
M. Abdeen, R. El-Sahan, A. Ismaeil, S. El-Harouny, M. Shalaby, and M. C. E. Yagoub, “Direct automatic generation of mind maps from text with M2Gen,” in Proceedings of the IEEE Toronto International Conference on Science and Technology for Humanity (TIC-STH), Toronto, Canada, 2009.
S. Yao, H. Wang, J. Chen, J. Zhong, and X. Jiang, “FlowGraph2Text: Automatic flowchart-to-text description generation,” in Proceedings of the 30th International Conference on Computational Linguistics (COLING), Oct. 2024.
W. Huang, Z. Chen, X. Deng, and Z. Li, “Text-to-flowchart generation via program synthesis and semantic parsing,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Vaishali Dhawas , Riya Shedge, Vishakha Sable , Kiran Kushwaha
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author(s) hold complete right on the content of this article.
