REVIEW 11 cited by
Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
read the original abstract
Creating Computer-Aided Design (CAD) models requires significant expertise and effort. Text-to-CAD, which converts textual descriptions into CAD parametric sequences, is crucial in streamlining this process. Recent studies have utilized ground-truth parametric sequences, known as sequential signals, as supervision to achieve this goal. However, CAD models are inherently multimodal, comprising parametric sequences and corresponding rendered visual objects. Besides,the rendering process from parametric sequences to visual objects is many-to-one. Therefore, both sequential and visual signals are critical for effective training. In this work, we introduce CADFusion, a framework that uses Large Language Models (LLMs) as the backbone and alternates between two training stages: the sequential learning (SL) stage and the visual feedback (VF) stage. In the SL stage, we train LLMs using ground-truth parametric sequences, enabling the generation of logically coherent parametric sequences. In the VF stage, we reward parametric sequences that render into visually preferred objects and penalize those that do not, allowing LLMs to learn how rendered visual objects are perceived and evaluated. These two stages alternate throughout the training, ensuring balanced learning and preserving benefits of both signals. Experiments demonstrate that CADFusion significantly improves performance, both qualitatively and quantitatively.
Forward citations
Cited by 11 Pith papers
-
neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editing
neuralCAD-Edit benchmark shows even the best foundation model (GPT 5.2) scores 53% lower than human CAD experts in acceptance trials for multimodal-instructed 3D model edits.
-
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling
BIM-Edit benchmark finds best LLM scores only 49.5% average across geometric, semantic, and topological metrics on 324 IFC editing tasks, with no model fully solving more than 3.4%.
-
FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories
FllumaOne releases 100,000 kernel-validated CAD models as executable Python programs with aligned multimodal data including feature histories and geometry exports.
-
BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding
BRepCLIP is the first contrastive pretraining framework that tokenizes BRep CAD geometry into surface and curve vocabularies and aligns the resulting embeddings with CLIP text and image encoders, reporting large gains...
-
MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation
MUSE is a new benchmark and three-stage evaluation protocol for text-to-CAD generation that assesses functionality, manufacturability, and assemblability of B-Rep assemblies beyond geometric similarity.
-
Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation
Text2CAD-Bench supplies 600 dual-prompt examples across four geometric and domain levels to test LLMs on text-to-parametric CAD, finding solid basic performance but sharp drops on complex topology and advanced features.
-
CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
CAD-Coder generates valid CadQuery scripts from text via supervised fine-tuning followed by reinforcement learning with geometric Chamfer Distance rewards and chain-of-thought planning.
-
Nova3D: Code-Native Generation of Programmable 3D Assets
Nova3D generates 3D assets as executable Blender source, yielding named parts, assembly hierarchies, measurable constraints, and native joints that mesh-native generators do not expose.
-
ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation
CAD-IR scaffolds ambiguous text into executable CATIA procedures and, with expert-distilled skills, produces editable B-Rep variants of complex automotive parts.
-
Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
A hybrid agentic architecture integrates knowledge-based physical verification tools into LLM-driven CAD design loops, producing more complex and functionally valid designs than prior agentic baselines.
-
Memory-Augmented Reinforcement Learning Agent for CAD Generation
Memory-augmented RL agent with case and skill libraries plus dynamic retrieval improves success rate and geometric consistency for complex CAD model generation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.