Key Features

Generates vector-style floorplans from structured representations.
Uses markup to encode editable architectural layout information.
Supports semantic room and geometry-aware floorplan generation.
Targets outputs that are more useful than flat floorplan images.
Relevant to CAD, architecture, and interior design workflows.
Helps preserve topology and layout structure.
Useful for automated design iteration and layout prototyping.
Provides a public research basis for floorplan generation.

The system represents floorplans through markup-like structured data, allowing generated layouts to encode walls, rooms, doors, spatial relationships, and geometry in a form that can be parsed and edited. This is technically important because vector floorplans require consistency, closure, topology, and semantic labels. A markup representation gives the model a more controllable output space than pixels alone.


FML is valuable because floorplan generation has practical constraints that image models often ignore. By producing vector-like structured representations, it can support downstream editing, validation, CAD conversion, and design iteration.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner
Zero to AI Engineer Program

Zero to AI Engineer

Skip the degree. Learn real-world AI skills used by AI researchers and engineers. Get certified in 8 weeks or less. No experience required.

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!