Metraipolis › archive › dc_e65e6e55324a
CAD-WAM: Anticipating Geometry for Text-to-CAD Generation — arXiv:2610.39306
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39306
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:41:54.066Z
- SHA-256 of the archived text
d6807ea66aae771e1762fa620c71593990690d5cc921466b312340254e3c9dfb- Stable URL of this page
https://metraipolis.com/documento/dc_e65e6e55324a
How to cite
CAD-WAM: Anticipating Geometry for Text-to-CAD Generation — arXiv:2610.39306 — arXiv (en), https://arxiv.org/abs/2610.39306 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e65e6e55324a (Metraipolis archive dc_e65e6e55324a, sha256 d6807ea66aae771e1762fa620c71593990690d5cc921466b312340254e3c9dfb)
BibTeX
@misc{dce65e6e55324a,
title = {CAD-WAM: Anticipating Geometry for Text-to-CAD Generation — arXiv:2610.39306},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39306},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e65e6e55324a; sha256 d6807ea66aae771e1762fa620c71593990690d5cc921466b312340254e3c9dfb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39306. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generating editable computer-aided design (CAD) models from text requires selecting operations that produce the intended changes to the geometry constructed so far. An incorrect operation can compromise subsequent steps, making reliable multi-step generation challenging. Existing methods based on large language models (LLMs) primarily learn to predict commands, without explicit supervision of the geometric states those commands should produce. Inspired by world-action models, we introduce CAD-WAM, which couples geometry-conditioned action generation with next-state prediction. We define complete modeling operations as actions in a CAD domain-specific language (DSL) and encode surface point clouds of intermediate solids into compact latent states using a pretrained variational autoencoder. An LLM backbone generates the next action from the target description and current geometric state, while an auxiliary head on the same backbone predicts the next state to provide geometric supervision during training. We construct step-wise training trajectories from parametric CAD models in the DeepCAD dataset, pairing each trajectory with an expert-level textual description. At inference, each generated action is executed by a CAD kernel, and the resulting solid is re-encoded to inform the next decision. On the DeepCAD test set, CAD-WAM outperforms the task-specific baselines in geometric accuracy and output validity, with larger gains on models requiring more operations, and produces more accurate geometry than general-purpose LLMs prompted with the same DSL. Ablations further show that next-state supervision reduces mean Chamfer distance by 13.2\% relative to an otherwise identical model trained only to predict actions. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2610.39306 — 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 2026-11-01T02:16:43.919Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).