CAD-WAM: Anticipating Geometry for Text-to-CAD Generation
CAD-WAM generates text-to-CAD models by predicting both the next executable CAD-DSL action and the next geometric state. It encodes intermediate solids as latent states from surface point clouds, and uses an auxiliary state-prediction head for geometric supervision during training. At inference, each predicted action is executed by a CAD kernel and the resulting solid is re-encoded for the next decision, improving geometric accuracy and validity on DeepCAD.
