@inproceedings{zeng-etal-2025-card,
title = "{CARD}: Cross-modal Agent Framework for Generative and Editable Residential Design",
author = "Zeng, Pengyu and
Yin, Jun and
Zhang, Miao and
Dai, Yuqin and
Li, Jizhizi and
Jin, ZhanXiang and
Lu, Shuai",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.473/",
doi = "10.18653/v1/2025.emnlp-main.473",
pages = "9304--9319",
ISBN = "979-8-89176-332-6",
abstract = "In recent years, architectural design automation has made significant progress, but the complexity of open-world environments continues to make residential design a challenging task, often requiring experienced architects to perform multiple iterations and human-computer interactions. Therefore, assisting ordinary users in navigating these complex environments to generate and edit residential design is crucial. In this paper, we present the CARD framework, which leverages a system of specialized cross-modal agents to adapt to complex open-world environments. The framework includes a point-based cross-modal information representation (CMI-P) that encodes the geometry and spatial relationships of residential rooms, a cross-modal residential generation model, supported by our customized Text2FloorEdit model, that acts as the lead designer to create standardized floor plans, and an embedded expert knowledge base for evaluating whether the designs meet user requirements and residential codes, providing feedback accordingly. Finally, a 3D rendering module assists users in visualizing and understanding the layout. CARD enables cross-modal residential generation from free-text input, empowering users to adapt to complex environments without requiring specialized expertise."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2025-card">
<titleInfo>
<title>CARD: Cross-modal Agent Framework for Generative and Editable Residential Design</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pengyu</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqin</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jizhizi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ZhanXiang</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Lu</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>In recent years, architectural design automation has made significant progress, but the complexity of open-world environments continues to make residential design a challenging task, often requiring experienced architects to perform multiple iterations and human-computer interactions. Therefore, assisting ordinary users in navigating these complex environments to generate and edit residential design is crucial. In this paper, we present the CARD framework, which leverages a system of specialized cross-modal agents to adapt to complex open-world environments. The framework includes a point-based cross-modal information representation (CMI-P) that encodes the geometry and spatial relationships of residential rooms, a cross-modal residential generation model, supported by our customized Text2FloorEdit model, that acts as the lead designer to create standardized floor plans, and an embedded expert knowledge base for evaluating whether the designs meet user requirements and residential codes, providing feedback accordingly. Finally, a 3D rendering module assists users in visualizing and understanding the layout. CARD enables cross-modal residential generation from free-text input, empowering users to adapt to complex environments without requiring specialized expertise.</abstract>
<identifier type="citekey">zeng-etal-2025-card</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.473</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.473/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>9304</start>
<end>9319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CARD: Cross-modal Agent Framework for Generative and Editable Residential Design
%A Zeng, Pengyu
%A Yin, Jun
%A Zhang, Miao
%A Dai, Yuqin
%A Li, Jizhizi
%A Jin, ZhanXiang
%A Lu, Shuai
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zeng-etal-2025-card
%X In recent years, architectural design automation has made significant progress, but the complexity of open-world environments continues to make residential design a challenging task, often requiring experienced architects to perform multiple iterations and human-computer interactions. Therefore, assisting ordinary users in navigating these complex environments to generate and edit residential design is crucial. In this paper, we present the CARD framework, which leverages a system of specialized cross-modal agents to adapt to complex open-world environments. The framework includes a point-based cross-modal information representation (CMI-P) that encodes the geometry and spatial relationships of residential rooms, a cross-modal residential generation model, supported by our customized Text2FloorEdit model, that acts as the lead designer to create standardized floor plans, and an embedded expert knowledge base for evaluating whether the designs meet user requirements and residential codes, providing feedback accordingly. Finally, a 3D rendering module assists users in visualizing and understanding the layout. CARD enables cross-modal residential generation from free-text input, empowering users to adapt to complex environments without requiring specialized expertise.
%R 10.18653/v1/2025.emnlp-main.473
%U https://aclanthology.org/2025.emnlp-main.473/
%U https://doi.org/10.18653/v1/2025.emnlp-main.473
%P 9304-9319
Markdown (Informal)
[CARD: Cross-modal Agent Framework for Generative and Editable Residential Design](https://aclanthology.org/2025.emnlp-main.473/) (Zeng et al., EMNLP 2025)
ACL