Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.13299 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909995328602112 |
|---|---|
| author | Seefried, Ethan Movva, Prahitha Marupaka, Naga Harshita Kasturi, Tilak Ghosal, Tirthankar |
| author_facet | Seefried, Ethan Movva, Prahitha Marupaka, Naga Harshita Kasturi, Tilak Ghosal, Tirthankar |
| contents | We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By capturing hierarchical component relationships, connections, and semantic elements across diverse engineering domains, our proposed dataset would enable multimodal large language models to address critical downstream tasks including structured diagram parsing, cross-modal information retrieval, and AI-assisted engineering simulation. Enginuity would be transformative for AI for Scientific Discovery by enabling artificial intelligence systems to comprehend and manipulate the visual-structural knowledge embedded in engineering diagrams, breaking down a fundamental barrier that currently prevents AI from fully participating in scientific workflows where diagram interpretation, technical drawing analysis, and visual reasoning are essential for hypothesis generation, experimental design, and discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13299 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams Seefried, Ethan Movva, Prahitha Marupaka, Naga Harshita Kasturi, Tilak Ghosal, Tirthankar Computer Vision and Pattern Recognition We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By capturing hierarchical component relationships, connections, and semantic elements across diverse engineering domains, our proposed dataset would enable multimodal large language models to address critical downstream tasks including structured diagram parsing, cross-modal information retrieval, and AI-assisted engineering simulation. Enginuity would be transformative for AI for Scientific Discovery by enabling artificial intelligence systems to comprehend and manipulate the visual-structural knowledge embedded in engineering diagrams, breaking down a fundamental barrier that currently prevents AI from fully participating in scientific workflows where diagram interpretation, technical drawing analysis, and visual reasoning are essential for hypothesis generation, experimental design, and discovery. |
| title | Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.13299 |