StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
cs.CV, cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Project page: https://ghadinehme.com/stepcad.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
- Hierarchical Neural Coding for Controllable CAD Model Generation
- cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
- CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
- Zero-to-CAD: Agentic Synthesis of Interpretable CAD Programs at Million-Scale Without Real Data
- CADEvolve: Creating Realistic CAD via Program Evolution
- DeepCoder: Learning to Write Programs
- Generative Optimization: A Perspective on AI-Enhanced Problem Solving in Engineering
- CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation
- CAD-Coder:Text-Guided CAD Files Code Generation
- Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
- SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
- CADReasoner: Iterative Program Editing for CAD Reverse Engineering
- Teaching Large Language Models to Self-Debug
- Planning with Large Language Models for Code Generation
- Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection
- Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding
- Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision
- CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
- Qwen2.5-Coder Technical Report
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models