architectural designers

Abstract: Insect exoskeletons abruptly acquire complex three-dimensional forms during metamorphosis from larva to pupa. This transformation occurs through the unfolding of preformed wrinkle structures inside the larval body under internal pressure. Inspired by this process, we investigate an inverse-origami strategy for fabricating curved surfaces. Whereas conventional origami produces three-dimensional objects by folding a flat sheet, this strategy produces curved surfaces by unfolding preformed wrinkle structures. The central design problem is to derive a wrinkle structure from a prescribed target surface. Our key idea is to regard a wrinkle structure as a unidirectional stretching field, which specifies at each point the stretch produced when the structure unfolds. We first derive such a field from the target surface geometry and then translate it into spatially varying wrinkle directions and spacing, so that the wrinkle structure unfolds into the target. The resulting numerical designs approximate the intrinsic metric of the target surface. We demonstrate the method on multiple target surfaces through numerical construction, mechanical unfolding simulations, and 3D-printed prototypes. This work provides a biologically inspired geometric design principle for encoding prescribed surface shapes in wrinkle structures, as well as a framework for designing and fabricating deployable curved surfaces.

Abstract: Daylight compliance assessment in residential buildings requires time-consuming raytracing simulations and specialist model preparation, limiting its integration into iterative architectural design. We present a machine learning-based methodology for predicting the spatial distribution of the Daylight Factor (DF) directly within Building Information Modelling (BIM) environments, delivering results in seconds without model export or manual curation. The approach addresses five gaps not jointly covered by any existing model: external obstruction encoding including balconies, own building height, variable material reflectances, non-orthogonal room geometries, and regulatory validation. Two models are developed: a default-materials model with fixed reflectances for preliminary design checks, and a custom-materials model with variable project-specific reflectances. Both are trained on about 20,000 synthetic Radiance-simulated rooms and validated on a held-out synthetic dataset and 102 rooms from 18 real building models. The default-materials model achieves $δ_1$ = 83.4% and MAE = 0.11% DF on synthetic data, and on real buildings predicts BBR (Swedish) compliance area within 4.85 pp MAE (bias +2.31 pp) and TEK17 (Norwegian) mean room DF within 0.304% DF MAE (bias +0.287% DF). The custom-materials variant shows 1.7-2.4$\times$ higher error across all metrics. Both models concentrate accuracy in the BBR compliance-critical zone (DF < 1%), achieving a sub-1% DF MAE of 0.105% DF and Compliance IoU of 0.883 on real buildings. All cases where compliance is overestimated are borderline, within 10.7 pp of the BBR threshold (median 3.2 pp) and 0.36% DF of the TEK17 threshold (median 0.10% DF). The default-materials model is recommended as a replacement for preliminary daylight simulations; the custom-materials variant requires further development before use in final compliance verification.

Abstract: Computational fluid dynamics (CFD) is computationally expensive for iterative building design. Deep learning surrogates offer faster predictions, but generalization across varying room dimensions remains challenging. This study compares two geometry-conditioned neural network surrogate models for rapid indoor airflow and temperature field prediction under varying room sizes. During the architectural design stage, this method is relevant for real-time assessment of whether conditioned supply air will effectively provide fresh and cool air throughout rooms with varying heights and lengths. The canvas-based neural network (CaNN) explicitly encodes room size by preserving different occupied regions within a fixed canvas, whereas the coordinate-based neural network (CoNN) uses normalized coordinate channels. Both employ U-Net autoencoders to separately predict airflow and temperature fields. Evaluation uses simplified rooms with varying heights and lengths as a controlled benchmark. The results show that CaNN achieves higher agreement with CFD results than CoNN, demonstrating its potential to support performance-driven building design.

Abstract: Foundation models are powerful generators, but many engineering domains require structured representations that general-purpose systems handle poorly. We introduce FLOORA (Floor Layout Optimization with RL Alignment), a family of small domain-specific language (DSL) models for architectural layout generation. With specialized data and alignment, our 0.6B model outperforms much larger frontier models, achieving VLM judge win rates up to 92.0% on out-of-distribution real-world buildings and 96.0% on synthetic buildings. Human evaluations further corroborate these results, with FLOORA selected as the best model in 89.3% of evaluations. FLOORA combines a token-efficient DSL, custom tokenization, domain-specific pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL) with learned human-preference and verifiable rewards. This pipeline improves architectural and geometric validity, supported by extensive empirical evaluation and ablation studies. Although focused on architecture, our results suggest that similar domain-specific recipes may be useful in other engineering domains with structured, verifiable outputs. Datasets, models, and inference code are available at https://github.com/AutodeskAILab/floora.