HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation
For architectural design, this work introduces a novel hypergraph representation that enables editable floor plan generation with LLMs, though the approach is domain-specific and incremental.
HypergraphFormer uses an LLM fine-tuned to generate hypergraph-based textual representations for floor plan generation, outperforming SOTA methods on the RPLAN dataset and a new out-of-distribution dataset, with improved data efficiency and editability.
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.