Saved in:
Bibliographic Details
Main Authors: Klimenko, Nikita, Salehipour, Hesam, Eftekhar, Parham, Khasahmadi, Amir, Weber, Ramon Elias
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.18932
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918519082319872
author Klimenko, Nikita
Salehipour, Hesam
Eftekhar, Parham
Khasahmadi, Amir
Weber, Ramon Elias
author_facet Klimenko, Nikita
Salehipour, Hesam
Eftekhar, Parham
Khasahmadi, Amir
Weber, Ramon Elias
contents 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-tuning to generate a hypergraph-based textual representation that encodes spatial relationships and connectivity information within floor plans. We train and evaluate our approach on the RPLAN dataset, and further demonstrate its generalizability on a separate out-of-distribution dataset, which we release in this paper. Our method outperforms state-of-the-art techniques based on rasterized or vectorized representations across a diverse set of metrics. We also show improved data efficiency, particularly under distribution shift. The hypergraph formulation enables the generation of floor plans for arbitrary, irregular, user-specified boundaries by decoupling apartment footprints from their functional and geometric subdivisions. Furthermore, we show that the proposed methodology offers a high degree of editability, making it particularly well suited to design-oriented workflows supported by LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18932
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation
Klimenko, Nikita
Salehipour, Hesam
Eftekhar, Parham
Khasahmadi, Amir
Weber, Ramon Elias
Machine Learning
Artificial Intelligence
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-tuning to generate a hypergraph-based textual representation that encodes spatial relationships and connectivity information within floor plans. We train and evaluate our approach on the RPLAN dataset, and further demonstrate its generalizability on a separate out-of-distribution dataset, which we release in this paper. Our method outperforms state-of-the-art techniques based on rasterized or vectorized representations across a diverse set of metrics. We also show improved data efficiency, particularly under distribution shift. The hypergraph formulation enables the generation of floor plans for arbitrary, irregular, user-specified boundaries by decoupling apartment footprints from their functional and geometric subdivisions. Furthermore, we show that the proposed methodology offers a high degree of editability, making it particularly well suited to design-oriented workflows supported by LLMs.
title HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.18932