A Large Language Model Powered Integrated Circuit Footprint Geometry Understanding

2025-07-29

AI Summary

Automated geometric annotation of PCB footprint pads in IC mechanical drawings remains challenging due to complex, domain-specific layout conventions and limited annotated data. Method: This paper proposes LLM4-IC8K—the first framework leveraging large language models (LLMs) for IC packaging geometry parsing. It introduces a stepwise geometric reasoning mechanism, constructs ICGeo8K—the first multimodal dataset dedicated to IC packaging—and adopts a two-stage training strategy: synthetic-data pretraining followed by fine-tuning on real-world drawings, enabling end-to-end structured recognition of pin count, centroid coordinates, and pad dimensions. Contribution/Results: Experiments on a custom benchmark demonstrate significant improvements over existing state-of-the-art multimodal models, achieving breakthroughs in both accuracy and engineering robustness. LLM4-IC8K establishes a novel, interpretable, and scalable paradigm for geometric understanding in electronic design automation (EDA), bridging high-level semantic reasoning with low-level geometric perception.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• Automated parsing of unstructured IC footprint drawings
• Accurate modeling of PCB footprint geometry
• Enhancing LMMs' geometric perception for IC labeling

Innovation

• Leverages LLMs for structured IC geometry interpretation
• Two-stage training with synthetic and real-world data
• Introduces ICGeo8K multimodal dataset for enhanced accuracy