Research map / Large language models / Agents, code and math
Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek
Xueyang Li, Jiahao Li, Yu Song, Yunzhong Lou, Xiangdong Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Seek-CAD step-wise visual feedback (SVF) instead of 3D-PreMise or CADCodeVerify refinement (ablation) | Seek-CAD · 500 test CAD models | IoGT: 0.6562 -> 0.7226 (vs CADCodeVerify) | Improved |
| compare training-free Seek-CAD with fine-tuned CAD-Llama | Seek-CAD · 500 test CAD models | Novel / IoGT: IoGT 0.7023 -> 0.7226; Novel 77.64% -> 64.04% | Mixed |
| add one round of SVF refinement (ablation) | Seek-CAD · 500 test CAD models | IoGT: 0.6183 -> 0.7226 | Improved |
| add a second SVF round (ablation) | Seek-CAD · 500 test CAD models | Pass@2: 0.72 -> 0.55 | Hurt |
| add the local CAD corpus (RAG) (ablation) | Seek-CAD · 200 CAD models | compilable output: model A fails to compile entirely | Improved |
| add knowledge constraint system prompt (ablation) | Seek-CAD · 200 CAD models | Pass@1: 0.44 -> 0.68 | Improved |
| add vector search and text search in corpus retrieval (ablation) | Seek-CAD · 200 CAD models | IoGT: 0.6464 -> 0.7451 (w/o text search vs full) | Improved |
| add intermediate images in SVF (ablation) | Seek-CAD · 200 CAD models | IoGT: 0.6713 -> 0.7451 | Improved |
| add CoT in SVF (ablation) | Seek-CAD · 200 CAD models | G-Score: 3.6120 -> 3.8409 | Improved |
| add the ultimate image in SVF (ablation) | Seek-CAD · 200 CAD models | IoGT: 0.7036 -> 0.7451 | Improved |
| increase CAD command sequence length (complexity) | Seek-CAD · Low vs High length | IoGT / Novel: IoGT 0.7356 -> 0.6759; Novel 56.25% -> 69.34% | Mixed |
| replace local corpus with DeepCAD data | Seek-CAD vs baselines · DeepCAD (300 test) | IoGT: 0.7531 -> 0.8095 (vs CADCodeVerify) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CAD-Llama — CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation (CVPR 2025) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation (CVPR 2025 · similarity 0.92)
- cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning (ICLR 2026 · similarity 0.89)
- CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs (AAAI 2025 · similarity 0.89)
- From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach (AAAI 2025 · similarity 0.88)
- Generating CAD Code with Vision-Language Models for 3D Designs (ICLR 2025 · similarity 0.88)
- CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing (ICML 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
