CRAFT: Corrective and Robust Multi-Agent Framework for Text-to-Parametric CAD
cs.CV, cs.AI, cs.GR
Submitted: 2026-10-16
Updated: 2026-10-16
Comments: Accepted at the 2026 IEEE International Conference on LLM-Aided Design (ICLAD). 11 pages, 5 figures, 10 tables. Code: https://github.com/idealab-isu/CRAFT
Code: https://github.com/idealab-isu/CRAFT
Project page: https://openscad.org
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DreamFusion: Text-to-3D using 2D Diffusion
- Shap-E: Generating Conditional 3D Implicit Functions
- Evaluating Large Language Models Trained on Code
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Generating CAD Code with Vision-Language Models for 3D Designs
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- GPT-4o System Card
- Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs