Metraipolis › archive › dc_477cb56c7bd0
VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence — arXiv:2609.03811
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03811
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:41:56.322Z
- SHA-256 of the archived text
22ed679062b18a137db411b93d0cb2bcf7e9fb77eab0b6ce28be989fbf61a0ed- Stable URL of this page
https://metraipolis.com/documento/dc_477cb56c7bd0
How to cite
VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence — arXiv:2609.03811 — arXiv (en), https://arxiv.org/abs/2609.03811 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_477cb56c7bd0 (Metraipolis archive dc_477cb56c7bd0, sha256 22ed679062b18a137db411b93d0cb2bcf7e9fb77eab0b6ce28be989fbf61a0ed)
BibTeX
@misc{dc477cb56c7bd0,
title = {VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence — arXiv:2609.03811},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03811},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_477cb56c7bd0; sha256 22ed679062b18a137db411b93d0cb2bcf7e9fb77eab0b6ce28be989fbf61a0ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03811. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI-assisted computer-aided design (CAD) for industrial products involves two challenging phases. Part-level generation maps diverse forms of user intent, including renders, text descriptions, 2D drawings, and real photographs, to executable programs in a CAD domain-specific language. Assembly-level generation must additionally handle interacting parts, plan mating relations, estimate poses, and place all parts correctly. Existing specialized CAD models are commonly trained on narrow input domains, such as renders or texts, and often generalize poorly, while general-purpose frontier models cover broader inputs but perform inconsistently across CAD domains. We present VisCAD, a foundation model suite designed to provide both broad generalization and strong CAD capability for realistic industrial products. At its core is VisCAD-M1, a 27B model trained through mid-training and post-training for part-level design generation. On PubCADBench and RealCADBench, VisCAD-M1 achieves the highest average part-level score among the evaluated models, reaching 0.5540 compared with 0.5496 for the strongest frontier model. Reusing VisCAD-M1 as a test-time verifier can further raise the score to 0.5797, an approximately 5 percent relative improvement over the previous state of the art. VisCAD also includes a domain-specific harness that leverages frontier models for complex assembly generation and demonstrates advantages over general-purpose harnesses in both quantitative and qualitative evaluations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.03811 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T01:11:43.612Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).