{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:45:19Z","timestamp":1780055119913,"version":"3.54.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728969","type":"print"},{"value":"9783031728976","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72897-6_21","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:36:36Z","timestamp":1733088996000},"page":"368-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["CadVLM: Bridging Language and\u00a0Vision in\u00a0the\u00a0Generation of\u00a0Parametric CAD Sketches"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5752-0929","authenticated-orcid":false,"given":"Sifan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir Hosein","family":"Khasahmadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mor","family":"Katz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pradeep Kumar","family":"Jayaraman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yewen","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karl","family":"Willis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9483-8984","authenticated-orcid":false,"given":"Bang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"21_CR1","unstructured":"Azerbayev, Z., et al.: Llemma: an open language model for mathematics. arXiv preprint arXiv:2310.10631 (2023)"},{"key":"21_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR3","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.cad.2016.01.003","volume":"74","author":"JD Camba","year":"2016","unstructured":"Camba, J.D., Contero, M., Company, P.: Parametric cad modeling: an analysis of strategies for design reusability. Comput. Aided Des. 74, 18\u201331 (2016)","journal-title":"Comput. Aided Des."},{"key":"21_CR4","unstructured":"Chen, Q., Hu, X., Wang, Z., Hong, Y.: Medblip: bootstrapping language-image pre-training from 3d medical images and texts. arXiv preprint arXiv:2305.10799 (2023)"},{"key":"21_CR5","unstructured":"Chen, X., et\u00a0al.: Pali: a jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, S., Han, B., He, T., Li, B.: Camml: context-aware multimodal learner for large models. arXiv preprint arXiv:2401.03149 (2024)","DOI":"10.18653\/v1\/2024.acl-long.223"},{"key":"21_CR7","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi, L., Chiriatti, M.: Gpt-3: its nature, scope, limits, and consequences. Mind. Mach. 30, 681\u2013694 (2020)","journal-title":"Mind. Mach."},{"key":"21_CR8","unstructured":"Ganin, Y., Bartunov, S., Li, Y., Keller, E., Saliceti, S.: Computer-aided design as language (2021)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Jones, B.T., Hu, M., Kodnongbua, M., Kim, V.G., Schulz, A.: Self-supervised representation learning for cad. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21327\u201321336 (2023)","DOI":"10.1109\/CVPR52729.2023.02043"},{"key":"21_CR11","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, vol.\u00a01, p.\u00a02 (2019)"},{"key":"21_CR12","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"21_CR13","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Li, P., Guo, J., Zhang, X., Yan, D.M.: Secad-net: self-supervised cad reconstruction by learning sketch-extrude operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316826 (2023)","DOI":"10.1109\/CVPR52729.2023.01613"},{"key":"21_CR15","unstructured":"Lindsay, A., Paterson, A., Graham, I.: Identifying and quantifying inefficiencies within industrial parametric cad models. In: Advances in Manufacturing Technology XXXII: Proceedings of the 16th International Conference on Manufacturing Research, vol.\u00a08, p.\u00a0227 (2018)"},{"key":"21_CR16","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"21_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"21_CR18","unstructured":"Luo, H., et al.: Wizardmath: empowering mathematical reasoning for large language models via reinforced evol-instruct. arXiv preprint arXiv:2308.09583 (2023)"},{"key":"21_CR19","first-page":"5077","volume":"34","author":"W Para","year":"2021","unstructured":"Para, W., et al.: Sketchgen: generating constrained cad sketches. Adv. Neural. Inf. Process. Syst. 34, 5077\u20135088 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR20","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"21_CR21","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR22","unstructured":"Seff, A., Ovadia, Y., Zhou, W., Adams, R.P.: Sketchgraphs: a large-scale dataset for modeling relational geometry in computer-aided design. arXiv preprint arXiv:2007.08506 (2020)"},{"key":"21_CR23","unstructured":"Seff, A., Zhou, W., Richardson, N., Adams, R.P.: Vitruvion: a generative model of parametric cad sketches. arXiv preprint arXiv:2109.14124 (2021)"},{"key":"21_CR24","unstructured":"Singhal, K., et\u00a0al.: Large language models encode clinical knowledge. arXiv preprint arXiv:2212.13138 (2022)"},{"key":"21_CR25","unstructured":"Singhal, K., et\u00a0al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)"},{"key":"21_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., Le, H., Gotmare, A.D., Bui, N.D., Li, J., Hoi, S.C.: Codet5+: open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Willis, K.D., Jayaraman, P.K., Lambourne, J.G., Chu, H., Pu, Y.: Engineering sketch generation for computer-aided design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2105\u20132114 (2021)","DOI":"10.1109\/CVPRW53098.2021.00239"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Wu, R., Xiao, C., Zheng, C.: Deepcad: a deep generative network for computer-aided design models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6772\u20136782 (2021)","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"21_CR30","unstructured":"Xu, X., Jayaraman, P.K., Lambourne, J.G., Willis, K.D., Furukawa, Y.: Hierarchical neural coding for controllable cad model generation. arXiv preprint arXiv:2307.00149 (2023)"},{"key":"21_CR31","unstructured":"Xu, X., Willis, K.D., Lambourne, J.G., Cheng, C.Y., Jayaraman, P.K., Furukawa, Y.: Skexgen: autoregressive generation of cad construction sequences with disentangled codebooks. In: International Conference on Machine Learning, pp. 24698\u201324724. PMLR (2022)"},{"key":"21_CR32","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1162\/tacl_a_00461","volume":"10","author":"L Xue","year":"2022","unstructured":"Xue, L., et al.: Byt5: towards a token-free future with pre-trained byte-to-byte models. Trans. Assoc. Comput. Linguist. 10, 291\u2013306 (2022)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"21_CR33","unstructured":"Zha, L., et\u00a0al.: Tablegpt: towards unifying tables, nature language and commands into one gpt. arXiv preprint arXiv:2307.08674 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72897-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:20:21Z","timestamp":1733095221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72897-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031728969","9783031728976"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72897-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}