{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T02:24:28Z","timestamp":1781663068378,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755550","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"1948-1956","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["FreeCAD: A Multimodal Framework for 3D CAD Model Generation from Free-Form Prompts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6788-4566","authenticated-orcid":false,"given":"Dawei","family":"Lin","sequence":"first","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8330-2180","authenticated-orcid":false,"given":"Meng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6687-8377","authenticated-orcid":false,"given":"Ziming","family":"Wang","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3397-1885","authenticated-orcid":false,"given":"Tieru","family":"Wu","sequence":"additional","affiliation":[{"name":"School of AI, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7926-7936","authenticated-orcid":false,"given":"Yuanning","family":"Liu","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Sai Sravan Yarlagadda, and Amir Barati Farimani","author":"Badagabettu Akshay","year":"2024","unstructured":"Akshay Badagabettu, Sai Sravan Yarlagadda, and Amir Barati Farimani. 2024. Query2CAD: Generating CAD models using natural language queries. arXiv preprint arXiv:2406.00144 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry. arXiv preprint arXiv:2410.03417","author":"Chen Tianrun","year":"2024","unstructured":"Tianrun Chen, Chunan Yu, Yuanqi Hu, Jing Li, Tao Xu, Runlong Cao, Lanyun Zhu, Ying Zang, Yong Zhang, Zejian Li, and Linyun Sun. 2024. Img2CAD: Conditioned 3D CAD Model Generation from Single Image with Structured Visual Geometry. arXiv preprint arXiv:2410.03417 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171-4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171-4186."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00024"},{"key":"e_1_3_2_1_5_1","volume-title":"European Conference on Computer Vision. 19-36","author":"Dupont Elona","year":"2024","unstructured":"Elona Dupont, Kseniya Cherenkova, Dimitrios Mallis, Gleb Gusev, Anis Kacem, and Djamila Aouada. 2024. TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Clouds. In European Conference on Computer Vision. 19-36."},{"key":"e_1_3_2_1_6_1","volume-title":"Mikaela Angelina Uy, and Minhyuk Sung.","author":"Hong Eunji","year":"2024","unstructured":"Eunji Hong, Minh Hieu Nguyen, Mikaela Angelina Uy, and Minhyuk Sung. 2024. MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images. arXiv preprint arXiv:2406.10853 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01153"},{"key":"e_1_3_2_1_8_1","first-page":"8776","article-title":"UCSG-NET-Unsupervised Discovering of Constructive Solid Geometry Tree","author":"Kania Kacper","year":"2020","unstructured":"Kacper Kania, Maciej Zieba, and Tomasz Kajdanowicz. 2020. UCSG-NET-Unsupervised Discovering of Constructive Solid Geometry Tree. In Advances in Neural Information Processing Systems. 8776-8786.","journal-title":"Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00451"},{"key":"e_1_3_2_1_10_1","first-page":"7552","article-title":"Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts","author":"Khan Mohammad Sadil","year":"2024","unstructured":"Mohammad Sadil Khan, Sankalp Sinha, Sheikh Talha Uddin, Didier Stricker, Sk Aziz Ali, and Muhammad Zeshan Afzal. 2024b. Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts. In Advances in Neural Information Processing Systems. 7552-7579.","journal-title":"Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530133"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32531"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681549"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_15_1","volume-title":"Mesh Graphormer. In Proceedings of the IEEE international conference on computer vision. 12919-12928","author":"Lin Kevin","year":"2021","unstructured":"Kevin Lin, Lijuan Wang, and Zicheng Liu. 2021. Mesh Graphormer. In Proceedings of the IEEE international conference on computer vision. 12919-12928."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02564"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614982"},{"key":"e_1_3_2_1_20_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2020","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2020. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2020)."},{"key":"e_1_3_2_1_21_1","unstructured":"Open Cascade SAS. 1999. Open CASCADE Technology (OCCT): 3D Modeling Libraries. https:\/\/www.opencascade.com\/. 2025-01-06."},{"key":"e_1_3_2_1_22_1","volume-title":"3d-gpt: Procedural 3d modeling with large language models. arXiv preprint arXiv:2310.12945","author":"Sun Chunyi","year":"2023","unstructured":"Chunyi Sun, Junlin Han, Weijian Deng, Xinlong Wang, Zishan Qin, and Stephen Gould. 2023. 3d-gpt: Procedural 3d modeling with large language models. arXiv preprint arXiv:2310.12945 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01155"},{"key":"e_1_3_2_1_25_1","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 6000-6010.","journal-title":"Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32849"},{"key":"e_1_3_2_1_27_1","volume-title":"Quoc V. Le, and Denny Zhou.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"e_1_3_2_1_29_1","volume-title":"CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM. arXiv preprint arXiv: 2411.04954","author":"Xu Jingwei","year":"2024","unstructured":"Jingwei Xu, Chenyu Wang, Zibo Zhao, Wen Liu, Yi Ma, and Shenghua Gao. 2024b. CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM. arXiv preprint arXiv: 2411.04954 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the International Conference on Machine Learning. 38443-38461","author":"Xu Xiang","year":"2023","unstructured":"Xiang Xu, Pradeep Kumar Jayaraman, Joseph G. Lambourne, Karl D.D. Willis, and Yasutaka Furukawa. 2023. Hierarchical neural coding for controllable CAD model generation. In Proceedings of the International Conference on Machine Learning. 38443-38461."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658129"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the International Conference on Machine Learning. 24698-24724","author":"Xu Xiang","year":"2022","unstructured":"Xiang Xu, Karl DD Willis, Joseph G Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, and Yasutaka Furukawa. 2022. SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks. In Proceedings of the International Conference on Machine Learning. 24698-24724."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"e_1_3_2_1_34_1","volume-title":"Text2CAD: Text to 3D CAD Generation via Technical Drawings. arXiv preprint arXiv:2411.06206","author":"Yavartanoo Mohsen","year":"2024","unstructured":"Mohsen Yavartanoo, Sangmin Hong, Reyhaneh Neshatavar, and Kyoung Mu Lee. 2024. Text2CAD: Text to 3D CAD Generation via Technical Drawings. arXiv preprint arXiv:2411.06206 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Jiaqi Han, Rahul Thomas, Haotong Zhang, Suya You, and Leonidas Guibas.","author":"You Yang","year":"2024","unstructured":"Yang You, Mikaela Angelina Uy, Jiaqi Han, Rahul Thomas, Haotong Zhang, Suya You, and Leonidas Guibas. 2024. Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization. arXiv preprint arXiv:2408.01437 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Ali Mahdavi Amiri, and Hao Zhang","author":"Yu Fenggen","year":"2023","unstructured":"Fenggen Yu, Qimin Chen, Maham Tanveer, Ali Mahdavi Amiri, and Hao Zhang. 2023. D2CSG: unsupervised learning of compact CSG trees with dual complements and dropouts. In Advances in Neural Information Processing Systems. 22807 - 22819."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01147"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358850"},{"key":"e_1_3_2_1_39_1","volume-title":"CAD-Editor","author":"Yuan Yu","year":"2025","unstructured":"Yu Yuan, Shizhao Sun, Qi Liu, and Jiang Bian. 2025. CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing. arXiv preprint arXiv:2502.03997 (2025)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01388"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:13:05Z","timestamp":1765307585000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755550"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":40,"alternative-id":["10.1145\/3746027.3755550","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755550","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}