Neural Inverse Design of Self-Shaping Composites

The research project explores an LLM-driven approach to computational design and additive manufacturing, enabling the generation of fabrication-ready 3D objects directly from natural language and visual inputs. Through a multi-agent workflow, the system generates parametric toolpaths that integrate geometry, material distribution, and fabrication strategies into a unified design representation. An interactive interface allows users to refine their designs and translate them into machine-specific fabrication instructions. By connecting design intent directly to material deposition, the project aims to make advanced digital fabrication more accessible, flexible, and intuitive.