AI Paper Atlas

Research map / Large language models / Agents, code and math

HouseTune: Two-Stage Floorplan Generation with LLM Assistance

Ziyang Zong, Guanying Chen, Zhaohuan Zhan, Fengcheng Yu, Guang Tan

AAAI 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add diffusion refinement stage after LLM layout (two-stage vs one-stage) (ablation)HouseTune · RPLAN 6 roomsDiversity (FID): 109.5 -> 7.5Improved
add diffusion refinement stage (ablation)HouseTune · RPLAN 6 roomsCompatibility: 10.6 -> 0.25Improved
replace task-only prompt with predefined CoT prompt (ablation)HouseTune Layout-Init · RPLAN 6 roomsIoU: 12.36% -> 21.41%Improved
add 'think step by step' to prompt vs common sense prompt (ablation)HouseTune Layout-Init · RPLAN 6 roomsIoU: 14.57% -> 20.69%Improved
predefined CoT vs basic CoT prompt (ablation)HouseTune Layout-Init · RPLAN 6 roomsIoU: 20.69% -> 21.41%Improved
swap Layout-Init LLM among DeepSeek-R1, DouBao-1.5Pro, GPT-4o (ablation)HouseTune · RPLAN 6 roomsIoU: 34.3% / 30.2% / 33.8%No clear effect
use DNPP-Diffusion instead of conditional diffusion (ablation)HouseTune · RPLAN 6 roomsMic IoU: 21.84% -> 34.15%Improved
use DNPP-Diffusion instead of conditional diffusion (ablation)HouseTune · RPLAN 6 roomsMac IoU: 17.75% -> 32.83%Improved
strong-to-weak prior preserving vs fixed (ablation)HouseTune · RPLAN 6 roomsMic IoU: 28.03 -> 34.15Improved
strong-to-weak prior preserving vs weak-to-strong (ablation)HouseTune · RPLAN 6 roomsMic IoU: 15.94 -> 34.15Improved
condition in both forward and reverse processes vs single (ablation)HouseTune · RPLAN 6 roomsDiversity (FID): 14.17 -> 7.47Improved
increase conditional participation ratio from 1e-3 to 1e-1 (ablation)HouseTune · RPLAN 6 roomsMac IoU: 28.67% -> 31.37%Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy