Foundation Models for Automatic CAD Generation

• URL: http://arxiv.org/abs/2607.05573v1
• Date: Mon, 06 Jul 2026 19:17:49 GMT
• Title: Foundation Models for Automatic CAD Generation
• Abstract summary: This chapter presents an empirical study of foundation models for automatic Computer-Aided Design (CAD) generation of mechanical parts.<n>We introduce LLMForge, a multi-model text-to-CAD framework integrating spatial validation, analytic feature scoring, mesh synthesis, and multi-round iterative refinement.<n>Under IterTracer, the four highest-ranked models form a tight cluster (overall mean in [0.885, 0.890]) with 98.97% success, showing that compact instruction-tuned models can match substantially larger systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-language specifications. This chapter presents an empirical study of foundation models for automatic Computer-Aided Design (CAD) generation of mechanical parts, using a unified evaluation pipeline and a curated benchmark of 97 engineering design problems. We introduce LLMForge, a multi-model text-to-CAD framework integrating JSON-schema validation, analytic feature scoring, mesh synthesis, and multi-round iterative refinement, studied under two critique regimes. IterTracer uses a Phong-shaded ray-trace renderer with analytic visual metrics (silhouette IoU, hole visibility, edge clearance, aspect-ratio conformance) for lightweight geometry-aware feedback across rounds. IterVision replaces the analytic scorer with a VLM semantic critic (Qwen2.5-VL-72B) that evaluates rendered views via chain-of-thought visual reasoning, assessing spatial coherence and design intent. On a benchmark spanning four canonical geometry families (plates with holes and bolt circles, multi-feature boxes, flanged cylinders, and L-brackets), we evaluate seven foundation models: DeepSeek-V3.2, Qwen3-235B-A22B, Llama-3.3-70B, Gemma-3-27B, GLM-4.5, MiniMax-M2.1, and INTELLECT. Under IterTracer, the four highest-ranked models form a tight cluster (overall mean in [0.885, 0.890]) with 98.97% mesh success, showing that compact instruction-tuned models can match substantially larger systems. VLM-based critique in IterVision yields 100% watertight mesh generation on the leading model while surfacing systematic difficulty on rotationally symmetric geometries such as cylinders, where visual and semantic scoring diverge most. We discuss benchmark design, failure modes, CAD-oriented prompting, and implications for industrial workflows and scalable automated mechanical design.

Related papers

• Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control [86.64250947574749]
  Reconstructing articulated 3D objects is important for animation, gaming, and robotic simulations.<n>Recent neural networks can estimate the articulated structure of 3D objects, but their generalization remains limited by the scarcity of annotated data.<n>We introduce Instruct-Particulate, a model that takes a 3D mesh together with a target kinematic specification.
  arXiv  Detail & Related papers  (2026-06-12T17:59:36Z)
• Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence [63.11502936651325]
  We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence.<n>It takes only RGB images as input while internalizing both forms of geometric prior within a unified autoregressive backbone.<n>GAMSI achieves state-of-the-art performance on seven spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2026-05-25T01:33:19Z)
• RISE-Video: Can Video Generators Decode Implicit World Rules? [71.92434352963427]
  We present RISE-Video, a pioneering reasoning-oriented benchmark for Text-Image-to-Video (TI2V) synthesis.<n>RISE-Video comprises 467 meticulously human-annotated samples spanning eight rigorous categories.<n>We propose an automated pipeline leveraging Large Multimodal Models (LMMs) to emulate human-centric assessment.
  arXiv  Detail & Related papers  (2026-02-05T18:36:10Z)
• Visual Autoregressive Modelling for Monocular Depth Estimation [69.01449528371916]
  We propose a monocular depth estimation method based on visual autoregressive ( VAR) priors.<n>Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism.<n>We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets.
  arXiv  Detail & Related papers  (2025-12-27T17:08:03Z)
• A Study of Finetuning Video Transformers for Multi-view Geometry Tasks [38.47908309127428]
  General-purpose models pretrained on videos can be readily transferred to multi-view problems with minimal adaptation.<n>Top cross-dataset generalization results for optical flow estimation with end-point error (EPE) of 0.69, 1.78, and 3.15 on the Sintel clean, Sintel final, and KITTI datasets.
  arXiv  Detail & Related papers  (2025-12-21T10:41:11Z)
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model [76.08429266631823]
  We propose an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM)<n>URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction.<n> Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-11-02T13:45:51Z)
• Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View [69.6117755984012]
  Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision.<n>We propose a unified category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image.
  arXiv  Detail & Related papers  (2025-10-13T17:49:15Z)
• Human-in-the-Loop: Quantitative Evaluation of 3D Models Generation by Large Language Models [0.0]
  This paper introduces a human in the loop framework for the quantitative evaluation of Large Language Models generated 3D models.<n>We propose a comprehensive suite of similarity and complexity metrics, including volumetric accuracy, surface alignment, dimensional fidelity, and topological intricacy.<n>Our findings demonstrate improved generation fidelity with increased semantic richness, with code level prompts achieving perfect reconstruction.
  arXiv  Detail & Related papers  (2025-09-06T11:04:15Z)
• HybridMQA: Exploring Geometry-Texture Interactions for Colored Mesh Quality Assessment [7.526258700061012]
  Mesh quality assessment (MQA) models play a critical role in the design, optimization, and evaluation of mesh operation systems.<n>We introduce HybridMQA, a hybrid full-reference colored MQA framework that integrates model-based and projection-based approaches.<n>Our method employs graph learning to extract detailed 3D representations, which are then projected to 2D using a novel feature rendering process.
  arXiv  Detail & Related papers  (2024-12-02T21:35:33Z)
• CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning [61.21923643289266]
  Chain of Manipulations is a mechanism that enables Vision-Language Models to solve problems step-by-step with evidence.<n>After training, models can solve various visual problems by eliciting intrinsic manipulations (e.g., grounding, zoom in) actively without involving external tools.<n>Our trained model, textbfCogCoM, achieves state-of-the-art performance across 9 benchmarks from 4 categories.
  arXiv  Detail & Related papers  (2024-02-06T18:43:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.