DeepCAD
PulseAugur coverage of DeepCAD — every cluster mentioning DeepCAD across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
TraceCAD enhances LLM-based CAD generation with persistent recovery
Researchers have developed TraceCAD, a novel recovery layer designed to enhance the reliability of CAD generation by Large Language Models (LLMs). This system maintains persistent state, linking requested features, mode…
-
AI model CADENA reconstructs 3D meshes into editable CAD programs step-by-step
Researchers have developed CADENA, a novel AI model designed to reconstruct 3D meshes into editable parametric CAD programs. Unlike previous methods that generate the entire program at once, CADENA builds the program st…
-
AI-powered spec-driven development emerges for AutoCAD drawings
While a direct text-to-CAD drawing generator is not yet available, a spec-driven development approach is emerging for creating technical drawings. This method involves writing a specification in a requirements.md file, …
-
New datasets aim to advance AI-assisted CAD program generation
Researchers have introduced two new datasets aimed at advancing AI-assisted Computer-Aided Design (CAD). CADBench offers a unified benchmark with 18,000 samples across six families, five input modalities, and six metric…
-
New benchmarks assess AI's CAD program generation capabilities
Two new benchmarks, CADBench and BenchCAD, have been released to evaluate AI's ability to generate Computer-Aided Design (CAD) programs from various inputs. These benchmarks aim to standardize the assessment of multimod…
-
New diffusion model advances computer-aided design generation
Researchers have developed a novel cascaded discrete diffusion framework to improve computer-aided design (CAD) generation. This approach addresses limitations of existing methods by operating directly on discrete CAD t…