Saved in:
Bibliographic Details
Main Authors: Ma, Chengwei, Tian, Zhen, Zhou, Zhou, Xu, Zhixian, Zhu, Xiaowei, Hua, Xia, Shi, Si, Yu, F. Richard
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.11678
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914324656685056
author Ma, Chengwei
Tian, Zhen
Zhou, Zhou
Xu, Zhixian
Zhu, Xiaowei
Hua, Xia
Shi, Si
Yu, F. Richard
author_facet Ma, Chengwei
Tian, Zhen
Zhou, Zhou
Xu, Zhixian
Zhu, Xiaowei
Hua, Xia
Shi, Si
Yu, F. Richard
contents Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit.
format Preprint
id arxiv_https___arxiv_org_abs_2602_11678
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing
Ma, Chengwei
Tian, Zhen
Zhou, Zhou
Xu, Zhixian
Zhu, Xiaowei
Hua, Xia
Shi, Si
Yu, F. Richard
Artificial Intelligence
Computer Vision and Pattern Recognition
Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit.
title Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing
topic Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.11678