Saved in:
Bibliographic Details
Main Authors: Li, Yuanbo, Shu, Dule, Chen, Yanying, Klenk, Matt, Ritchie, Daniel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.12561
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914327776198656
author Li, Yuanbo
Shu, Dule
Chen, Yanying
Klenk, Matt
Ritchie, Daniel
author_facet Li, Yuanbo
Shu, Dule
Chen, Yanying
Klenk, Matt
Ritchie, Daniel
contents Recovering Computer-Aided Design (CAD) programs from 3D geometries is a widely studied problem. Recent advances in large language models (LLMs) have enabled progress in CAD program synthesis, but existing methods rely on supervised training with paired shape-program data, which is often unavailable. We introduce PLLM, a self-training framework for CAD program synthesis from unlabeled 3D shapes. Given a pre-trained CAD-capable LLM and a shape dataset, PLLM iteratively samples candidate programs, selects high-fidelity executions, and augments programs to construct synthetic program-shape pairs for fine-tuning. We experiment on adapting CAD-Recode from DeepCAD to the unlabeled ABC dataset show consistent improvements in geometric fidelity and program diversity.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12561
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesis
Li, Yuanbo
Shu, Dule
Chen, Yanying
Klenk, Matt
Ritchie, Daniel
Computer Vision and Pattern Recognition
Recovering Computer-Aided Design (CAD) programs from 3D geometries is a widely studied problem. Recent advances in large language models (LLMs) have enabled progress in CAD program synthesis, but existing methods rely on supervised training with paired shape-program data, which is often unavailable. We introduce PLLM, a self-training framework for CAD program synthesis from unlabeled 3D shapes. Given a pre-trained CAD-capable LLM and a shape dataset, PLLM iteratively samples candidate programs, selects high-fidelity executions, and augments programs to construct synthetic program-shape pairs for fine-tuning. We experiment on adapting CAD-Recode from DeepCAD to the unlabeled ABC dataset show consistent improvements in geometric fidelity and program diversity.
title PLLM: Pseudo-Labeling Large Language Models for CAD Program Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.12561