@inproceedings{zhu-etal-2025-plangpt-vl,
title = "{P}lan{GPT}-{VL}: Enhancing Urban Planning with Domain-Specific Vision-Language Models",
author = "Zhu, He and
Su, Junyou and
Chen, Minxin and
Wang, Wen and
Deng, Yijie and
Chen, Guanhua and
Zhang, Wenjia",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.169/",
pages = "2461--2483",
ISBN = "979-8-89176-333-3",
abstract = "In the field of urban planning, existing Vision-Language Models (VLMs) frequently fail to effectively analyze planning maps, which are critical for urban planners and educational contexts. Planning maps require specialized understanding of spatial configurations, regulatory requirements, and multi-scale analysis.To address this challenge, we introduce PlanGPT-VL, the first domain-specific VLM tailored for urban planning maps. PlanGPT-VL employs three innovations:(1) PlanAnno-V framework for high-quality VQA data synthesis,(2) Critical Point Thinking (CPT) to reduce hallucinations through structured verification, and(3) PlanBench-V benchmark for systematic evaluation.Evaluation on PlanBench-V shows that PlanGPT-VL outperforms general-purpose VLMs on planning map interpretation tasks, with our 7B model achieving performance comparable to larger 72B models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-plangpt-vl">
<titleInfo>
<title>PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyou</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minxin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijie</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjia</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>In the field of urban planning, existing Vision-Language Models (VLMs) frequently fail to effectively analyze planning maps, which are critical for urban planners and educational contexts. Planning maps require specialized understanding of spatial configurations, regulatory requirements, and multi-scale analysis.To address this challenge, we introduce PlanGPT-VL, the first domain-specific VLM tailored for urban planning maps. PlanGPT-VL employs three innovations:(1) PlanAnno-V framework for high-quality VQA data synthesis,(2) Critical Point Thinking (CPT) to reduce hallucinations through structured verification, and(3) PlanBench-V benchmark for systematic evaluation.Evaluation on PlanBench-V shows that PlanGPT-VL outperforms general-purpose VLMs on planning map interpretation tasks, with our 7B model achieving performance comparable to larger 72B models.</abstract>
<identifier type="citekey">zhu-etal-2025-plangpt-vl</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.169/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2461</start>
<end>2483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models
%A Zhu, He
%A Su, Junyou
%A Chen, Minxin
%A Wang, Wen
%A Deng, Yijie
%A Chen, Guanhua
%A Zhang, Wenjia
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F zhu-etal-2025-plangpt-vl
%X In the field of urban planning, existing Vision-Language Models (VLMs) frequently fail to effectively analyze planning maps, which are critical for urban planners and educational contexts. Planning maps require specialized understanding of spatial configurations, regulatory requirements, and multi-scale analysis.To address this challenge, we introduce PlanGPT-VL, the first domain-specific VLM tailored for urban planning maps. PlanGPT-VL employs three innovations:(1) PlanAnno-V framework for high-quality VQA data synthesis,(2) Critical Point Thinking (CPT) to reduce hallucinations through structured verification, and(3) PlanBench-V benchmark for systematic evaluation.Evaluation on PlanBench-V shows that PlanGPT-VL outperforms general-purpose VLMs on planning map interpretation tasks, with our 7B model achieving performance comparable to larger 72B models.
%U https://aclanthology.org/2025.emnlp-industry.169/
%P 2461-2483
Markdown (Informal)
[PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models](https://aclanthology.org/2025.emnlp-industry.169/) (Zhu et al., EMNLP 2025)
ACL