{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:12Z","timestamp":1784268432787,"version":"3.55.0"},"reference-count":72,"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\/501100001866","name":"National Research Fund","doi-asserted-by":"publisher","award":["BRIDGES2021\/IS\/16849599\/FREE-3D"],"award-info":[{"award-number":["BRIDGES2021\/IS\/16849599\/FREE-3D"]}],"id":[{"id":"10.13039\/501100001866","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\/iccv51701.2025.00684","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7284-7294","source":"Crossref","is-referenced-by-count":10,"title":["CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers"],"prefix":"10.1109","author":[{"given":"Dimitrios","family":"Mallis","sequence":"first","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmet Serda","family":"Karadeniz","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Cavada","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danila","family":"Rukhovich","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niki","family":"Foteinopoulou","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kseniya","family":"Cherenkova","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anis","family":"Kacem","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djamila","family":"Aouada","sequence":"additional","affiliation":[{"name":"SnT, University of Luxembourg,Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Generating cad code with vision-language models for 3d designs","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Alrashedy"},{"key":"ref3","year":"2023","journal-title":"Introducing the next generation of claude"},{"key":"ref4","article-title":"Query2cad: Generating cad models using natural language queries","author":"Badagabettu","year":"2024","journal-title":"ArXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3722\/cadaps.2012.771-794"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/16864360.2017.1397894"},{"key":"ref7","article-title":"Large language models as tool makers","author":"Cai","year":"2023","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00273"},{"key":"ref10","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"ArXiv"},{"key":"ref11","year":"2024","journal-title":"Freecad"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref13","article-title":"Transcad: A hierarchical transformer for cad sequence inference from point clouds","volume-title":"ECCV","author":"Dupont","year":"2024"},{"key":"ref14","article-title":"Large language models(1lms) on tabular data: Prediction, generation, and understanding - a survey","author":"Fang","year":"2024","journal-title":"ArXiv"},{"key":"ref15","journal-title":"The oca file format"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0955"},{"key":"ref18","article-title":"Tool documentation enables zero-shot toolusage with large language models","author":"Hsieh","year":"2023","journal-title":"ArXiv"},{"key":"ref19","article-title":"Visual sketchpad: Sketching as a visual chain of thought for multimodal language models","author":"Hu","year":"2024","journal-title":"ArXiv"},{"key":"ref20","year":"2012","journal-title":"Dxf reference"},{"key":"ref21","article-title":"Davinci: A single-stage architecture for constrained cad sketch inference","volume-title":"BMVC","author":"Karadeniz","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00631"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00451"},{"key":"ref24","article-title":"Querycad: Grounded question answering for cad models","author":"Kienle","year":"2024","journal-title":"ArXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618219"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.579"},{"key":"ref28","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681549"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1115\/DETC2024-143740","article-title":"Llm4cad: Multi-modal large language models for 3d computer-aided design generation","volume-title":"International Design Engineering Technical Conferences and Computers and Information in Engineering Conference","author":"Li","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref33","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","author":"Lu","year":"2023","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Dynamic prompt learning via policy gradient for semistructured mathematical reasoning","volume-title":"ICLR","author":"Lu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.0705d8bd"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00194"},{"key":"ref38","article-title":"The llama 3 herd of models","year":"2024","journal-title":"ArXiv"},{"key":"ref39","article-title":"Webgpt: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"ArXiv"},{"key":"ref40","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/16864360.2017.1353733"},{"key":"ref42","article-title":"Talm: Tool augmented language models","author":"Parisi","year":"2022","journal-title":"ArXiv"},{"key":"ref43","article-title":"Gorilla: Large language model connected with massive apis","author":"Patil","year":"2023","journal-title":"ArXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3704435"},{"key":"ref45","article-title":"Can large language models understand symbolic graphics programs?","author":"Qiu","year":"2024","journal-title":"ArXiv"},{"key":"ref46","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"The Journal of Machine Learning Research"},{"key":"ref47","article-title":"Cad-recode: Reverse engineering cad code from point clouds","author":"Rukhovich","year":"2024","journal-title":"ArXiv"},{"key":"ref48","article-title":"SketchGraphs: A large-scale dataset for modeling relational geometry in computer-aided design","volume-title":"ICMLW","author":"Seff","year":"2020"},{"key":"ref49","article-title":"Vitruvion: A generative model of parametric cad sketches","volume-title":"ICLR","author":"Seff","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01366"},{"key":"ref51","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","author":"Shen","year":"2023","journal-title":"ArXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635752"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01155"},{"key":"ref56","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"ArXiv"},{"key":"ref57","article-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation framework","volume":"abs\/2308.08155","author":"Wu","year":"2023","journal-title":"ArXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_21"},{"key":"ref60","author":"Wu","year":"2024","journal-title":"Cad-llm: Large language model for cad generation"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3148853"},{"key":"ref62","first-page":"24698","article-title":"Skexgen: Autoregressive generation of cad construction sequences with disentangled codebooks","volume-title":"ICML","author":"Xu","year":"2022"},{"key":"ref63","article-title":"Hierarchical neural coding for controllable cad model generation","volume-title":"ICML","author":"Xu","year":"2023"},{"key":"ref64","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv"},{"key":"ref65","article-title":"Discovering design concepts for cad sketches","author":"Yang","year":"2022","journal-title":"arXiv"},{"key":"ref66","article-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action","author":"Yang","year":"2023","journal-title":"ArXiv"},{"key":"ref67","article-title":"Neural-symbolic vqa: Disentangling reasoning from vision and language understanding","author":"Yi","year":"2018","journal-title":"NIPS"},{"key":"ref68","article-title":"Img2cad: Reverse engineering 3d cad models from images through vlm-assisted conditional factorization","author":"You","year":"2024","journal-title":"ArXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00360"},{"key":"ref70","article-title":"Socratic models: Composing zeroshot multimodal reasoning with language","author":"Zeng","year":"2022","journal-title":"ArXiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CSIE.2009.536"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01307"}],"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\/11443354.pdf?arnumber=11443354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:56Z","timestamp":1777612136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443354\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00684","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}