Zobrazit v EDS

VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization.

Uloženo v:
Podrobná bibliografie
Název: VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization.
Autoři: Biswas A, Turton TL, Ranasinghe NR, Jones S, Love B, Jones W, Hagberg A, Shen HW, DeBardeleben N, Lawrence E
Zdroj: IEEE transactions on visualization and computer graphics [IEEE Trans Vis Comput Graph] 2025 Dec 05; Vol. PP. Date of Electronic Publication: 2025 Dec 05.
Publication Model: Ahead of Print
Způsob vydávání: Journal Article
Jazyk: English
Informace o časopise: Publisher: IEEE Computer Society Country of Publication: United States NLM ID: 9891704 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1941-0506 (Electronic) Linking ISSN: 10772626 NLM ISO Abbreviation: IEEE Trans Vis Comput Graph Subsets: MEDLINE
Imprint Name(s): Original Publication: New York, NY : IEEE Computer Society, c1995-
Abstrakt: We present VizGenie, a self-improving, agentic framework that advances scientific visualization through large language model (LLM) by orchestrating of a collection of domain-specific and dynamically generated modules. Users initially access core functionalities-such as threshold-based filtering, slice extraction, and statistical analysis-through pre-existing tools. For tasks beyond this baseline, VizGenie autonomously employs LLMs to generate new visualization scripts (e.g., VTK Python code), expanding its capabilities on-demand. Each generated script undergoes automated backend validation and is seamlessly integrated upon successful testing, continuously enhancing the system's adaptability and robustness. A distinctive feature of VizGenie is its intuitive natural language interface, allowing users to issue high-level feature-based queries (e.g., "visualize the skull" or "highlight tissue boundaries"). The system leverages image-based analysis and visual question answering (VQA) via fine-tuned vision models to interpret these queries precisely, bridging domain expertise and technical implementation. Additionally, users can interactively query generated visualizations through VQA, facilitating deeper exploration. Reliability and reproducibility are further strengthened by Retrieval-Augmented Generation (RAG), providing context-driven responses while maintaining comprehensive provenance records. Evaluations on complex volumetric datasets demonstrate significant reductions in cognitive overhead for iterative visualization tasks. By integrating curated domain-specific tools with LLM-driven flexibility, VizGenie not only accelerates insight generation but also establishes a sustainable, continuously evolving visualization practice. The resulting platform dynamically learns from user interactions, consistently enhancing support for feature-centric exploration and reproducible research in scientific visualization.
Entry Date(s): Date Created: 20251205 Latest Revision: 20251205
Update Code: 20251206
DOI: 10.1109/TVCG.2025.3634655
PMID: 41348775
Databáze: MEDLINE
Popis
Abstrakt:We present VizGenie, a self-improving, agentic framework that advances scientific visualization through large language model (LLM) by orchestrating of a collection of domain-specific and dynamically generated modules. Users initially access core functionalities-such as threshold-based filtering, slice extraction, and statistical analysis-through pre-existing tools. For tasks beyond this baseline, VizGenie autonomously employs LLMs to generate new visualization scripts (e.g., VTK Python code), expanding its capabilities on-demand. Each generated script undergoes automated backend validation and is seamlessly integrated upon successful testing, continuously enhancing the system's adaptability and robustness. A distinctive feature of VizGenie is its intuitive natural language interface, allowing users to issue high-level feature-based queries (e.g., "visualize the skull" or "highlight tissue boundaries"). The system leverages image-based analysis and visual question answering (VQA) via fine-tuned vision models to interpret these queries precisely, bridging domain expertise and technical implementation. Additionally, users can interactively query generated visualizations through VQA, facilitating deeper exploration. Reliability and reproducibility are further strengthened by Retrieval-Augmented Generation (RAG), providing context-driven responses while maintaining comprehensive provenance records. Evaluations on complex volumetric datasets demonstrate significant reductions in cognitive overhead for iterative visualization tasks. By integrating curated domain-specific tools with LLM-driven flexibility, VizGenie not only accelerates insight generation but also establishes a sustainable, continuously evolving visualization practice. The resulting platform dynamically learns from user interactions, consistently enhancing support for feature-centric exploration and reproducible research in scientific visualization.
ISSN:1941-0506
DOI:10.1109/TVCG.2025.3634655