Architect-Ant fine-tunes a vision-language model on the new AntPlan-270 dataset using procedural reasoning traces and preference optimization to output editable DSL furniture layouts that can be rendered into images.
arXiv preprint arXiv:2602.06507 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes an AI framework with LLM rule conversion, floor plan graph extraction, and compliance checking for multi-unit residential buildings under Australian policies.
citing papers explorer
-
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
Architect-Ant fine-tunes a vision-language model on the new AntPlan-270 dataset using procedural reasoning traces and preference optimization to output editable DSL furniture layouts that can be rendered into images.
-
Towards an automated AI-based framework for floor plan compliance checks for residential buildings
Proposes an AI framework with LLM rule conversion, floor plan graph extraction, and compliance checking for multi-unit residential buildings under Australian policies.