{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:36:30Z","timestamp":1782452190943,"version":"3.54.5"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00659","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7014-7024","source":"Crossref","is-referenced-by-count":1,"title":["CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation"],"prefix":"10.1109","author":[{"given":"Jianyu","family":"Wu","sequence":"first","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Yue","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinzhu","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyang","family":"Guo","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongzhan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shixiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gencad: Imageconditioned computer-aided design generation with transformer-based contrastive representation and diffusion priors","volume":"2","author":"Alam","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Query2cad: Generating cad models using natural language queries","author":"Badagabettu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2018.1431235"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1102\/1470-7330.2005.0018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3080"},{"key":"ref7","article-title":"Img2cad: Conditioned 3d cad model generation from single image with structured visual geometry","volume":"2","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530078"},{"key":"ref12","article-title":"Compressing large language models by joint sparsification and quantization","volume-title":"Forty-first International Conference on Machine Learning","author":"Guo"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref17","article-title":"Solidgen: An autoregressive model for direct b-rep synthesis","volume-title":"Transactions on Machine Learning Research","volume":"2","author":"Kumar Jayaraman"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00451"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0242"},{"key":"ref20","volume":"4","author":"Kingma","journal-title":"Auto-encoding variational bayes."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00983"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01258"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530133"},{"key":"ref24","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1797"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","first-page":"82757","article-title":"Afbench: A large-scale benchmark for airfoil design","volume":"37","author":"Liu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3658155"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00361"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3730842"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3124762"},{"key":"ref33","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref35","article-title":"Sketchgraphs: A large-scale dataset for modeling relational geometry in computer-aided design","author":"Seff","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01155"},{"key":"ref39","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459818"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"ref43","article-title":"Next-gpt: Any-to-any multimodal llm","volume-title":"In Forty-first International Conference on Machine Learning","author":"Wu"},{"key":"ref44","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Cad-mllm: Unifying multimodalityconditioned cad generation with mllm","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"24698","article-title":"Skexgen: Autoregressive generation of cad construction sequences with disentangled codebooks","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref47","first-page":"38443","article-title":"Hierarchical neural coding for controllable cad model generation","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3658129"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763891"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.104048"},{"key":"ref51","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","volume-title":"Thirtyseventh Conference on Neural Information Processing Systems","author":"Zhao"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/200"},{"key":"ref53","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444324.pdf?arnumber=11444324","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:00Z","timestamp":1777611960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444324\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00659","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}