@inproceedings{chang-etal-2026-circuitpile,
title = "{C}ircuit{P}ile: A Data Synthesis Framework for Enhancing Multimodal {LLM}s' Perception on Circuit Schematics",
author = "Chang, Hongyu and
Li, Xinyue and
Liu, Huanyong and
Zhang, Feng and
Yin, Yuhui",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.226/",
pages = "5062--5094",
ISBN = "979-8-89176-439-2",
abstract = "In recent years, multimodal large language models have achieved substantial progress, yet their performance remains limited in specialized domains such as circuit diagram understanding. A key bottleneck lies in the lack of diverse and large-scale training data tailored to the structural characteristics of circuit diagrams, together with the high cost of expert annotation. To address this challenge, we propose CircuitPile, a systematic data synthesis framework for circuit visual-language modeling. CircuitPile integrates heterogeneous circuit resources from multiple sources and constructs standardized label spaces and multi-granularity visual representations. Based on this framework, we build 738K domain-specific pre-training samples and 100K task-oriented instruction-tuning samples for the pre-training and supervised fine-tuning stages, respectively. Furthermore, to systematically evaluate fundamental visually grounded circuit perception, we introduce CircuitPerception-Bench, a diagnostic benchmark comprising 2,700 multiple-choice samples across three dimensions: component recognition, spatial understanding, and quantitative reasoning. CircuitPerception-Bench focuses on fundamental visually grounded perception and complements external benchmarks such as AMS Benchmark. Experimental results show that multimodal models trained with CircuitPile achieve significant performance gains on the internal benchmark and demonstrate favorable transferability on the external public AMS Benchmark. For example, applying CircuitPile-based SFT to Qwen3-VL-8B improves the scores on CircuitPerception-Bench and AMS Benchmark from 0.5759 and 0.5067 to 0.7703 and 0.5988, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2026-circuitpile">
<titleInfo>
<title>CircuitPile: A Data Synthesis Framework for Enhancing Multimodal LLMs’ Perception on Circuit Schematics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyue</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huanyong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhui</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>In recent years, multimodal large language models have achieved substantial progress, yet their performance remains limited in specialized domains such as circuit diagram understanding. A key bottleneck lies in the lack of diverse and large-scale training data tailored to the structural characteristics of circuit diagrams, together with the high cost of expert annotation. To address this challenge, we propose CircuitPile, a systematic data synthesis framework for circuit visual-language modeling. CircuitPile integrates heterogeneous circuit resources from multiple sources and constructs standardized label spaces and multi-granularity visual representations. Based on this framework, we build 738K domain-specific pre-training samples and 100K task-oriented instruction-tuning samples for the pre-training and supervised fine-tuning stages, respectively. Furthermore, to systematically evaluate fundamental visually grounded circuit perception, we introduce CircuitPerception-Bench, a diagnostic benchmark comprising 2,700 multiple-choice samples across three dimensions: component recognition, spatial understanding, and quantitative reasoning. CircuitPerception-Bench focuses on fundamental visually grounded perception and complements external benchmarks such as AMS Benchmark. Experimental results show that multimodal models trained with CircuitPile achieve significant performance gains on the internal benchmark and demonstrate favorable transferability on the external public AMS Benchmark. For example, applying CircuitPile-based SFT to Qwen3-VL-8B improves the scores on CircuitPerception-Bench and AMS Benchmark from 0.5759 and 0.5067 to 0.7703 and 0.5988, respectively.</abstract>
<identifier type="citekey">chang-etal-2026-circuitpile</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.226/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>5062</start>
<end>5094</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CircuitPile: A Data Synthesis Framework for Enhancing Multimodal LLMs’ Perception on Circuit Schematics
%A Chang, Hongyu
%A Li, Xinyue
%A Liu, Huanyong
%A Zhang, Feng
%A Yin, Yuhui
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F chang-etal-2026-circuitpile
%X In recent years, multimodal large language models have achieved substantial progress, yet their performance remains limited in specialized domains such as circuit diagram understanding. A key bottleneck lies in the lack of diverse and large-scale training data tailored to the structural characteristics of circuit diagrams, together with the high cost of expert annotation. To address this challenge, we propose CircuitPile, a systematic data synthesis framework for circuit visual-language modeling. CircuitPile integrates heterogeneous circuit resources from multiple sources and constructs standardized label spaces and multi-granularity visual representations. Based on this framework, we build 738K domain-specific pre-training samples and 100K task-oriented instruction-tuning samples for the pre-training and supervised fine-tuning stages, respectively. Furthermore, to systematically evaluate fundamental visually grounded circuit perception, we introduce CircuitPerception-Bench, a diagnostic benchmark comprising 2,700 multiple-choice samples across three dimensions: component recognition, spatial understanding, and quantitative reasoning. CircuitPerception-Bench focuses on fundamental visually grounded perception and complements external benchmarks such as AMS Benchmark. Experimental results show that multimodal models trained with CircuitPile achieve significant performance gains on the internal benchmark and demonstrate favorable transferability on the external public AMS Benchmark. For example, applying CircuitPile-based SFT to Qwen3-VL-8B improves the scores on CircuitPerception-Bench and AMS Benchmark from 0.5759 and 0.5067 to 0.7703 and 0.5988, respectively.
%U https://aclanthology.org/2026.aacl-long.226/
%P 5062-5094
Markdown (Informal)
[CircuitPile: A Data Synthesis Framework for Enhancing Multimodal LLMs’ Perception on Circuit Schematics](https://aclanthology.org/2026.aacl-long.226/) (Chang et al., AACL-IJCNLP 2026)
ACL