{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T19:47:27Z","timestamp":1784404047087,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681549","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"8461-8470","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["CAD Translator: An Effective Drive for Text to 3D Parametric Computer-Aided Design Generative Modeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7833-0170","authenticated-orcid":false,"given":"Xueyang","family":"Li","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0889-1289","authenticated-orcid":false,"given":"Yu","family":"Song","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2386-0017","authenticated-orcid":false,"given":"Yunzhong","family":"Lou","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5538-7367","authenticated-orcid":false,"given":"Xiangdong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00903"},{"key":"e_1_3_2_1_2_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23716--23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2020-22355"},{"key":"e_1_3_2_1_5_1","volume-title":"Computer Graphics Forum","author":"Cascaval Dan","unstructured":"Dan Cascaval, Mira Shalah, Phillip Quinn, Rastislav Bodik, Maneesh Agrawala, and Adriana Schulz. 2022. Differentiable 3d cad programs for bidirectional editing. In Computer Graphics Forum, Vol. 41. Wiley Online Library, 309--323."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"e_1_3_2_1_8_1","volume-title":"Luke Melas, and Ritobrata Ghosh.","author":"Dayma Boris","year":"2021","unstructured":"Boris Dayma, Suraj Patil, Pedro Cuenca, Khalid Saifullah, Tanishq Abraham, Ph\u00fac Le Khac, Luke Melas, and Ritobrata Ghosh. 2021. Dall\u00b7 e mini. HuggingFace. com. https:\/\/huggingface. co\/spaces\/dallemini\/dalle-mini (accessed Sep. 29, 2022) (2021)."},{"key":"e_1_3_2_1_9_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00661"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555452"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_2_1_14_1","volume-title":"Aditya Sanghi, and Nigel JW Morris.","author":"Jayaraman Pradeep Kumar","year":"2022","unstructured":"Pradeep Kumar Jayaraman, Joseph G Lambourne, Nishkrit Desai, Karl DD Willis, Aditya Sanghi, and Nigel JW Morris. 2022. Solidgen: An autoregressive model for direct b-rep synthesis. arXiv preprint arXiv:2203.13944 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01153"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480562","article-title":"Automate: A dataset and learning approach for automatic mating of cad assemblies","volume":"40","author":"Jones Benjamin","year":"2021","unstructured":"Benjamin Jones, Dalton Hildreth, Duowen Chen, Ilya Baran, Vladimir G Kim, and Adriana Schulz. 2021. Automate: A dataset and learning approach for automatic mating of cad assemblies. ACM Transactions on Graphics (TOG), Vol. 40, 6 (2021), 1--18.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02043"},{"key":"e_1_3_2_1_18_1","volume-title":"ReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Manipulation. In SIGGRAPH Asia 2023 Conference Papers. 1--12","author":"Kodnongbua Milin","year":"2023","unstructured":"Milin Kodnongbua, Benjamin Jones, Maaz Bin Safeer Ahmad, Vladimir Kim, and Adriana Schulz. 2023. ReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Manipulation. In SIGGRAPH Asia 2023 Conference Papers. 1--12."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01601"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01258"},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"Free2CAD: Parsing freehand drawings into CAD commands","volume":"41","author":"Li Changjian","year":"2022","unstructured":"Changjian Li, Hao Pan, Adrien Bousseau, and Niloy J Mitra. 2022. Free2CAD: Parsing freehand drawings into CAD commands. ACM Transactions on Graphics (TOG), Vol. 41, 4 (2022), 1--16.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01613"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00160"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563657.3596098"},{"key":"e_1_3_2_1_28_1","first-page":"36889","article-title":"Polyhistor: Parameter-efficient multi-task adaptation for dense vision tasks","volume":"35","author":"Liu Yen-Cheng","year":"2022","unstructured":"Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian, Zijian He, and Zsolt Kira. 2022. Polyhistor: Parameter-efficient multi-task adaptation for dense vision tasks. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36889--36901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614795"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02564"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614982"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555392"},{"key":"e_1_3_2_1_34_1","volume-title":"3d-ldm: Neural implicit 3d shape generation with latent diffusion models. arXiv preprint arXiv:2212.00842","author":"Nam Gimin","year":"2022","unstructured":"Gimin Nam, Mariem Khlifi, Andrew Rodriguez, Alberto Tono, Linqi Zhou, and Paul Guerrero. 2022. 3d-ldm: Neural implicit 3d shape generation with latent diffusion models. arXiv preprint arXiv:2212.00842 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_36_1","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan Junting","year":"2022","unstructured":"Junting Pan, Ziyi Lin, Xiatian Zhu, Jing Shao, and Hongsheng Li. 2022. St-adapter: Parameter-efficient image-to-video transfer learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 26462--26477.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Poole Ben","year":"2023","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2023. Dreamfusion: Text-to-3d using 2d diffusion. International Conference on Learning Representations (ICLR) (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.semeval-1.308"},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_28"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_44_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01759"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555525"},{"key":"e_1_3_2_1_50_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_51_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_52_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Wenhai","year":"2024","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2024. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01539"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"e_1_3_2_1_56_1","volume-title":"Hierarchical Neural Coding for Controllable CAD Model Generation. In International Conference on Machine Learning.","author":"Xu Xiang","year":"2023","unstructured":"Xiang Xu, Pradeep Kumar Jayaraman, Joseph G Lambourne, Karl DD Willis, and Yasutaka Furukawa. 2023. Hierarchical Neural Coding for Controllable CAD Model Generation. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_57_1","first-page":"8427","article-title":"Recursivemix: Mixed learning with history","volume":"35","author":"Yang Lingfeng","year":"2022","unstructured":"Lingfeng Yang, Xiang Li, Borui Zhao, Renjie Song, and Jian Yang. 2022. Recursivemix: Mixed learning with history. Advances in Neural Information Processing Systems, Vol. 35 (2022), 8427--8440.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_1","first-page":"28803","article-title":"Discovering design concepts for cad sketches","volume":"35","author":"Yang Yuezhi","year":"2022","unstructured":"Yuezhi Yang and Hao Pan. 2022. Discovering design concepts for cad sketches. Advances in Neural Information Processing Systems, Vol. 35 (2022), 28803--28814.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_59_1","volume-title":"CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_1_61_1","volume-title":"International Conference on Learning Representations(ICLR).","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations(ICLR)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681549","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":62,"alternative-id":["10.1145\/3664647.3681549","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681549","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}