Paper
Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts
External resource. Not made or verified by Public Protocol.
A 2024 paper, accepted at NeurIPS 2024, presenting a transformer that turns a text description into a parametric CAD sequence, trained on about 170,000 models with about 660,000 text annotations generated by language models. The authors state that code and annotations will be public.
https://arxiv.org/abs/2409.17106
- Maintainer
- Khan, Sinha, Sheikh, Stricker, Ali and Afzal
- Licence, as stated at its source
- CC BY 4.0 for the paper, as the arXiv page shows; no licence stated for code or data
- Open or commercial
- Open
- Maturity
- PrototypeOur reading, 16 November 2026
- Safety
- S0
- Review
- Listed 16 November 2026by Public Protocol editors
- Checked
- 16 November 2026
- Next check due
- 16 May 2027
- Steward
- Public Protocol editors
Where it sits in the blueprint
- Domains
- Stages
Design
- Elements it supports
Recorded when its maker or a reviewer places it against single elements.
- Context
Climate, setting, scale, cost and skill: not stated in this entry. Check the source against your own place and numbers.
Verification
No verification is recorded on Public Platform for this entry. Records are added when someone reads it for accuracy, reviews it with a stated qualification, builds it or measures it.
Record
- How it came in
Seed catalogue, 16 November 2026. Listed in the seed research on open machines and design for manufacturing. The abstract page was opened on the date shown.
- Licence
CC BY 4.0 for the paper, as the arXiv page shows; no licence stated for code or data. Read at https://arxiv.org/abs/2409.17106. How licences are recorded
- Something wrong?