# Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing

arXiv: https://arxiv.org/abs/2602.11678 · HTML: https://mlsanity.com/paper/2602.11678/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 12 of 12)

- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models](https://mlsanity.com/paper/2406.14852/) (2024)
- [Do Vision-Language Models Really Understand Visual Language?](https://mlsanity.com/paper/2410.00193/) (2024)
- [Scaling Vision Pre-Training to 4K Resolution](https://mlsanity.com/paper/2503.19903/) (2025)
- [Systematic Visual Reasoning through Object-Centric Relational Abstraction](https://mlsanity.com/paper/2306.02500/) (2023)
- [HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models](https://mlsanity.com/paper/2407.08706/) (2024)
- [CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs](https://mlsanity.com/paper/2502.07980/) (2025)
- [The Power of Graph Signal Processing for Chip Placement Acceleration](https://mlsanity.com/paper/2502.17632/) (2025)

## Abstract (arXiv)

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.