BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement

arXiv, Under Review

Yuhao Du, Shunian Chen, Wenbo Zan, Peizhao Li, Mingxuan Wang, Dingjie Song, Bo Li, Yan Hu, Benyou Wang

TL;DR BlenderLLM improves CAD script generation through instruction tuning and iterative self-improvement, supported by the BlendNet training dataset and CADBench evaluation suite for assessing script functionality and accuracy.

← All publications