# BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis

arXiv: https://arxiv.org/abs/2512.04832 · HTML: https://mlsanity.com/paper/2512.04832/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [SceneFormer: Indoor Scene Generation with Transformers](https://mlsanity.com/paper/2012.09793/) (2020)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising](https://mlsanity.com/paper/2211.13287/) (2022)
- [BLT: Bidirectional Layout Transformer for Controllable Layout Generation](https://mlsanity.com/paper/2112.05112/) (2021)
- [Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks](https://mlsanity.com/paper/1804.00823/) (2018)
- [Mixed Diffusion for 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2405.21066/) (2024)
- [FlairGPT: Repurposing LLMs for Interior Designs](https://mlsanity.com/paper/2501.04648/) (2025)
- [CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding](https://mlsanity.com/paper/2303.03565/) (2023)
- [Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers](https://mlsanity.com/paper/2505.04718/) (2025)
- [HouseTune: Two-Stage Floorplan Generation with LLM Assistance](https://mlsanity.com/paper/2411.12279/) (2024)
- [FloorPlan-DeepSeek (FPDS): A multimodal approach to floorplan generation using vector-based next room prediction](https://mlsanity.com/paper/2506.21562/) (2025)

## Built on by (most cited first, 1 of 1)

- [FLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design](https://mlsanity.com/paper/2609.36064/) (2026)

## Abstract (arXiv)

We present a BIM-native tokenization for room-level layout synthesis in Building Information Modeling (BIM) scenes. The core contribution is representational: we encode each room as a sequence of BIM-Token Bundles, realized as columns of a sparse attribute-feature matrix that unifies categorical and continuous attributes of walls, openings, and entities under wall-referenced (translation/scale-invariant) coordinates. A mixed-type embedding module produces a unified token vector from this matrix; a single Transformer backbone is then trained in two modes: encoder-only for room embeddings and retrieval, and encoder-decoder for autoregressive entity placement, which we call Data-Driven Entity Prediction (DDEP). On a controlled same-data benchmark with shared ontology and evaluation harness, DDEP outperforms ATISS and BLT baselines bridged into our representation, with ablations identifying joint continuous-feature embedding and entity ordering as primary drivers. Encoder embeddings cluster rooms by type more tightly than large general-purpose text encoders, which in turn retain an edge on within-type ranking. We frame this work as evidence that modestly sized, domain-specific sequence models over well-designed BIM tokenizations are a useful primitive for constraint-aware spatial generation, complementary to general-purpose LLMs/VLMs which we also benchmark.