Tag
Researchers from MIT and others developed GIFT, a system that teaches vision-language models to automatically convert 2D designs into accurate CAD programs for rapid prototyping, using model-generated data to correct mistakes and improve performance with less computation.
This paper presents a comprehensive empirical study on using foundation models (LLMs and VLMs) for automatic CAD generation from natural language, introducing the LLMForge framework with two critique regimes (IterTracer and IterVision) and evaluating seven models on a benchmark of 97 engineering design problems.
The user demonstrated a basic demo of generating CAD graphics via voice using Opus 4.8 with just two rounds of conversation, noting it's not yet industrial-grade but suitable for demos.
This paper proposes a memory-augmented reinforcement learning framework for CAD generation agents that integrates geometric kernel toolchains, dual-track memory, and dynamic utility retrieval to handle complex CAD models with long operation sequences and geometric constraints, achieving improved success rate and geometric consistency.
GenCAD introduces an image-conditional model that generates full parametric CAD command histories using transformers and diffusion priors, enabling precise and modifiable 3D modeling from images.
This paper introduces a new task formulation for CAD generation that incorporates finite element analysis as feedback, along with improved supervision signals like a text-only blueprint schema and multi-view image renderer, leading to better geometric reconstruction on benchmarks.