PulseAugur
EN
LIVE 14:55:37

HypergraphFormer uses LLMs to generate editable floor plans

By PulseAugur Editorial · [1 sources] ·

Researchers have developed HypergraphFormer, a new method for generating editable floor plans using large language models. This approach represents floor plans as hypergraphs, capturing spatial relationships and connectivity. Trained on the RPLAN dataset and tested on out-of-distribution data, HypergraphFormer surpasses existing methods in performance and data efficiency. Its hypergraph formulation allows for flexible generation of plans with irregular boundaries and offers a high degree of editability, making it suitable for LLM-supported design workflows. AI

IMPACT Enables more flexible and editable architectural design tools powered by LLMs.

RANK_REASON Academic paper detailing a new method for floor plan generation using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

HypergraphFormer uses LLMs to generate editable floor plans

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Nikita Klimenko, Hesam Salehipour, Parham Eftekhar, Amir Khasahmadi, Ramon Elias Weber ·

    HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation

    arXiv:2605.18932v2 Announce Type: replace-cross Abstract: In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a large language model (LLM). The model is trained via supervised fine-tu…

RELATED ENTITIES

RELATED TOPICS