A Large Language Model Powered Integrated Circuit Footprint Geometry Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918115679404032 |
|---|---|
| author | Wang, Yida Lu, Taiting Liu, Runze Yang, Lanqing Yang, Yifan Chen, Zhe Wang, Yuehai Liu, Yixin Lin, Kaiyuan Chen, Xiaomeng Ding, Dian Li, Yijie Chen, Yi-Chao Jin, Yincheng Gowda, Mahanth |
| author_facet | Wang, Yida Lu, Taiting Liu, Runze Yang, Lanqing Yang, Yifan Chen, Zhe Wang, Yuehai Liu, Yixin Lin, Kaiyuan Chen, Xiaomeng Ding, Dian Li, Yijie Chen, Yi-Chao Jin, Yincheng Gowda, Mahanth |
| contents | Printed-Circuit-board (PCB) footprint geometry labeling of integrated circuits (IC) is essential in defining the physical interface between components and the PCB layout, requiring exceptional visual perception proficiency. However, due to the unstructured footprint drawing and abstract diagram annotations, automated parsing and accurate footprint geometry modeling remain highly challenging. Despite its importance, no methods currently exist for automated package geometry labeling directly from IC mechanical drawings. In this paper, we first investigate the visual perception performance of Large Multimodal Models (LMMs) when solving IC footprint geometry understanding. Our findings reveal that current LMMs severely suffer from inaccurate geometric perception, which hinders their performance in solving the footprint geometry labeling problem. To address these limitations, we propose LLM4-IC8K, a novel framework that treats IC mechanical drawings as images and leverages LLMs for structured geometric interpretation. To mimic the step-by-step reasoning approach used by human engineers, LLM4-IC8K addresses three sub-tasks: perceiving the number of pins, computing the center coordinates of each pin, and estimating the dimensions of individual pins. We present a two-stage framework that first trains LMMs on synthetically generated IC footprint diagrams to learn fundamental geometric reasoning and then fine-tunes them on real-world datasheet drawings to enhance robustness and accuracy in practical scenarios. To support this, we introduce ICGeo8K, a multi-modal dataset with 8,608 labeled samples, including 4138 hand-crafted IC footprint samples and 4470 synthetically generated samples. Extensive experiments demonstrate that our model outperforms state-of-the-art LMMs on the proposed benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Large Language Model Powered Integrated Circuit Footprint Geometry Understanding Wang, Yida Lu, Taiting Liu, Runze Yang, Lanqing Yang, Yifan Chen, Zhe Wang, Yuehai Liu, Yixin Lin, Kaiyuan Chen, Xiaomeng Ding, Dian Li, Yijie Chen, Yi-Chao Jin, Yincheng Gowda, Mahanth Computer Vision and Pattern Recognition Printed-Circuit-board (PCB) footprint geometry labeling of integrated circuits (IC) is essential in defining the physical interface between components and the PCB layout, requiring exceptional visual perception proficiency. However, due to the unstructured footprint drawing and abstract diagram annotations, automated parsing and accurate footprint geometry modeling remain highly challenging. Despite its importance, no methods currently exist for automated package geometry labeling directly from IC mechanical drawings. In this paper, we first investigate the visual perception performance of Large Multimodal Models (LMMs) when solving IC footprint geometry understanding. Our findings reveal that current LMMs severely suffer from inaccurate geometric perception, which hinders their performance in solving the footprint geometry labeling problem. To address these limitations, we propose LLM4-IC8K, a novel framework that treats IC mechanical drawings as images and leverages LLMs for structured geometric interpretation. To mimic the step-by-step reasoning approach used by human engineers, LLM4-IC8K addresses three sub-tasks: perceiving the number of pins, computing the center coordinates of each pin, and estimating the dimensions of individual pins. We present a two-stage framework that first trains LMMs on synthetically generated IC footprint diagrams to learn fundamental geometric reasoning and then fine-tunes them on real-world datasheet drawings to enhance robustness and accuracy in practical scenarios. To support this, we introduce ICGeo8K, a multi-modal dataset with 8,608 labeled samples, including 4138 hand-crafted IC footprint samples and 4470 synthetically generated samples. Extensive experiments demonstrate that our model outperforms state-of-the-art LMMs on the proposed benchmark. |
| title | A Large Language Model Powered Integrated Circuit Footprint Geometry Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.03725 |