Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models Article Swipe

PDF

Jianxing Liao , Junyan Xu , Yongqi Sun , Matthew F. Tang , Sailing He , Jau‐Chyn Liao , Shui Yu , Yun Li , Xiao Han ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.19490

Designing complex computer-aided design (CAD) models is often time-consuming due to challenges such as computational inefficiency and the difficulty of generating precise models. We propose a novel language-guided framework for industrial design automation to address these issues, integrating large language models (LLMs) with computer-automated design (CAutoD).Through this framework, CAD models are automatically generated from parameters and appearance descriptions, supporting the automation of design tasks during the detailed CAD design phase. Our approach introduces three key innovations: (1) a semi-automated data annotation pipeline that leverages LLMs and vision-language large models (VLLMs) to generate high-quality parameters and appearance descriptions; (2) a Transformer-based CAD generator (TCADGen) that predicts modeling sequences via dual-channel feature aggregation; (3) an enhanced CAD modeling generation model, called CADLLM, that is designed to refine the generated sequences by incorporating the confidence scores from TCADGen. Experimental results demonstrate that the proposed approach outperforms traditional methods in both accuracy and efficiency, providing a powerful tool for automating industrial workflows and generating complex CAD models from textual prompts. The code is available at https://jianxliao.github.io/cadllm-page/

Related Topics

Automated Guided Vehicle

Fibonacci Sequence

The Human Centipede (First Sequence)

The Human Centipede 2 (Full Sequence)

The Human Centipede 3 (Final Sequence)

Geometric Modeling

Main Sequence

G-Type Main-Sequence Star

Lax Automated People Mover

Building Information Modeling

Sequence (Game)

Automated Manual Transmission

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2505.19490
PDF: https://arxiv.org/pdf/2505.19490
OA Status: green
OpenAlex ID: https://openalex.org/W4414586338

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4414586338

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2505.19490

Digital Object Identifier
Title: Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-05-26

Full publication date if available
Authors: Jianxing Liao, Junyan Xu, Yongqi Sun, Matthew F. Tang, Sailing He, Jau‐Chyn Liao, Shui Yu, Yun Li, Xiao Han

List of authors in order
Landing page: https://arxiv.org/abs/2505.19490

Publisher landing page
PDF URL: https://arxiv.org/pdf/2505.19490

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2505.19490

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4414586338
doi	https://doi.org/10.48550/arxiv.2505.19490
ids.doi	https://doi.org/10.48550/arxiv.2505.19490
ids.openalex	https://openalex.org/W4414586338
fwci
type	preprint
title	Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10181
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.982699990272522
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Natural Language Processing Techniques
topics[1].id	https://openalex.org/T10601
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9704999923706055
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Handwritten Text Recognition Techniques
topics[2].id	https://openalex.org/T14339
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9269999861717224
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1707
topics[2].subfield.display_name	Computer Vision and Pattern Recognition
topics[2].display_name	Image Processing and 3D Reconstruction
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2505.19490
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2505.19490
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2505.19490
locations[1].id	doi:10.48550/arxiv.2505.19490
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2505.19490
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5073845819
authorships[0].author.orcid	https://orcid.org/0009-0002-5474-4163
authorships[0].author.display_name	Jianxing Liao
authorships[0].author_position	first
authorships[0].raw_author_name	Liao, Jianxing
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5043282426
authorships[1].author.orcid	https://orcid.org/0000-0002-3789-2319
authorships[1].author.display_name	Junyan Xu
authorships[1].author_position	middle
authorships[1].raw_author_name	Xu, Junyan
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100649791
authorships[2].author.orcid	https://orcid.org/0000-0002-2155-0293
authorships[2].author.display_name	Yongqi Sun
authorships[2].author_position	middle
authorships[2].raw_author_name	Sun, Yatao
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5042357347
authorships[3].author.orcid	https://orcid.org/0000-0001-5858-5126
authorships[3].author.display_name	Matthew F. Tang
authorships[3].author_position	middle
authorships[3].raw_author_name	Tang, Maowen
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5049549826
authorships[4].author.orcid	https://orcid.org/0000-0002-3401-1125
authorships[4].author.display_name	Sailing He
authorships[4].author_position	middle
authorships[4].raw_author_name	He, Sicheng
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5016840889
authorships[5].author.orcid	https://orcid.org/0000-0001-5985-2994
authorships[5].author.display_name	Jau‐Chyn Liao
authorships[5].author_position	middle
authorships[5].raw_author_name	Liao, Jingxian
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5005228053
authorships[6].author.orcid	https://orcid.org/0000-0003-4485-6743
authorships[6].author.display_name	Shui Yu
authorships[6].author_position	middle
authorships[6].raw_author_name	Yu, Shui
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5107860546
authorships[7].author.orcid	https://orcid.org/0009-0008-9740-5130
authorships[7].author.display_name	Yun Li
authorships[7].author_position	middle
authorships[7].raw_author_name	Li, Yun
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5100634186
authorships[8].author.orcid	https://orcid.org/0000-0003-3787-3529
authorships[8].author.display_name	Xiao Han
authorships[8].author_position	last
authorships[8].raw_author_name	Xiao, Hongguan
authorships[8].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2505.19490
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10181
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.982699990272522
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Natural Language Processing Techniques
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2505.19490
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2505.19490
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2505.19490
primary_location.id	pmh:oai:arXiv.org:2505.19490
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2505.19490
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2505.19490
publication_date	2025-05-26
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	25, 77, 98, 151
abstract_inverted_index.We	23
abstract_inverted_index.an	112
abstract_inverted_index.as	13
abstract_inverted_index.at	170
abstract_inverted_index.by	128
abstract_inverted_index.in	145
abstract_inverted_index.is	6, 121, 168
abstract_inverted_index.of	19, 61
abstract_inverted_index.to	10, 33, 90, 123
abstract_inverted_index.(1)	76
abstract_inverted_index.(2)	97
abstract_inverted_index.(3)	111
abstract_inverted_index.CAD	48, 67, 100, 114, 161
abstract_inverted_index.Our	70
abstract_inverted_index.The	166
abstract_inverted_index.and	16, 55, 85, 94, 148, 158
abstract_inverted_index.are	50
abstract_inverted_index.due	9
abstract_inverted_index.for	29, 154
abstract_inverted_index.key	74
abstract_inverted_index.the	17, 59, 65, 125, 130, 139
abstract_inverted_index.via	107
abstract_inverted_index.LLMs	84
abstract_inverted_index.both	146
abstract_inverted_index.code	167
abstract_inverted_index.data	79
abstract_inverted_index.from	53, 133, 163
abstract_inverted_index.such	12
abstract_inverted_index.that	82, 103, 120, 138
abstract_inverted_index.this	46
abstract_inverted_index.tool	153
abstract_inverted_index.with	42
abstract_inverted_index.(CAD)	4
abstract_inverted_index.large	38, 87
abstract_inverted_index.novel	26
abstract_inverted_index.often	7
abstract_inverted_index.tasks	63
abstract_inverted_index.these	35
abstract_inverted_index.three	73
abstract_inverted_index.(LLMs)	41
abstract_inverted_index.called	118
abstract_inverted_index.design	3, 31, 44, 62, 68
abstract_inverted_index.during	64
abstract_inverted_index.model,	117
abstract_inverted_index.models	5, 40, 49, 88, 162
abstract_inverted_index.phase.	69
abstract_inverted_index.refine	124
abstract_inverted_index.scores	132
abstract_inverted_index.(VLLMs)	89
abstract_inverted_index.CADLLM,	119
abstract_inverted_index.address	34
abstract_inverted_index.complex	1, 160
abstract_inverted_index.feature	109
abstract_inverted_index.issues,	36
abstract_inverted_index.methods	144
abstract_inverted_index.models.	22
abstract_inverted_index.precise	21
abstract_inverted_index.propose	24
abstract_inverted_index.results	136
abstract_inverted_index.textual	164
abstract_inverted_index.TCADGen.	134
abstract_inverted_index.accuracy	147
abstract_inverted_index.approach	71, 141
abstract_inverted_index.designed	122
abstract_inverted_index.detailed	66
abstract_inverted_index.enhanced	113
abstract_inverted_index.generate	91
abstract_inverted_index.language	39
abstract_inverted_index.modeling	105, 115
abstract_inverted_index.pipeline	81
abstract_inverted_index.powerful	152
abstract_inverted_index.predicts	104
abstract_inverted_index.prompts.	165
abstract_inverted_index.proposed	140
abstract_inverted_index.(TCADGen)	102
abstract_inverted_index.Designing	0
abstract_inverted_index.available	169
abstract_inverted_index.framework	28
abstract_inverted_index.generated	52, 126
abstract_inverted_index.generator	101
abstract_inverted_index.leverages	83
abstract_inverted_index.providing	150
abstract_inverted_index.sequences	106, 127
abstract_inverted_index.workflows	157
abstract_inverted_index.annotation	80
abstract_inverted_index.appearance	56, 95
abstract_inverted_index.automating	155
abstract_inverted_index.automation	32, 60
abstract_inverted_index.challenges	11
abstract_inverted_index.confidence	131
abstract_inverted_index.difficulty	18
abstract_inverted_index.framework,	47
abstract_inverted_index.generating	20, 159
abstract_inverted_index.generation	116
abstract_inverted_index.industrial	30, 156
abstract_inverted_index.introduces	72
abstract_inverted_index.parameters	54, 93
abstract_inverted_index.supporting	58
abstract_inverted_index.demonstrate	137
abstract_inverted_index.efficiency,	149
abstract_inverted_index.integrating	37
abstract_inverted_index.outperforms	142
abstract_inverted_index.traditional	143
abstract_inverted_index.Experimental	135
abstract_inverted_index.aggregation;	110
abstract_inverted_index.dual-channel	108
abstract_inverted_index.high-quality	92
abstract_inverted_index.inefficiency	15
abstract_inverted_index.innovations:	75
abstract_inverted_index.automatically	51
abstract_inverted_index.computational	14
abstract_inverted_index.descriptions,	57
abstract_inverted_index.descriptions;	96
abstract_inverted_index.incorporating	129
abstract_inverted_index.computer-aided	2
abstract_inverted_index.semi-automated	78
abstract_inverted_index.time-consuming	8
abstract_inverted_index.language-guided	27
abstract_inverted_index.vision-language	86
abstract_inverted_index.(CAutoD).Through	45
abstract_inverted_index.Transformer-based	99
abstract_inverted_index.computer-automated	43
abstract_inverted_index.https://jianxliao.github.io/cadllm-page/	171
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	9
citation_normalized_percentile