The Flow has not summarised this story yet — read it at arXiv AI.
arXiv:2603. 21210v3 Announce Type: replace Abstract: Designing urban spaces that provide pedestrian wind comfort and safety requires time-resolved Computational Fluid Dynamics (CFD) simulations, but their current computational cost makes extensive design exploration impractical.
arXiv:2608.03323v2 Announce Type: replace Abstract: Estimating room layouts from multi-view imagery is a core task for indoor scene understanding. Existing methods are typically limited either by poo...
Fast Localized Urban Microclimate Emulator (FLUME) is a rapid, data‑efficient framework that predicts three‑dimensional wind and temperature fields in urban environments using a Fourier neural operator. It incorporates a Multi‑Directional Distance Feature (MDDF) to capture building geometry effects and is trained on CFD simulations of only 23 urban blocks, achieving mean absolute errors of 0.2 m/s for velocity and 0.19 °C for temperature on unseen configurations. An ensemble approach provides epistemic uncertainty estimates, with higher uncertainty in roof‑level shear layers, building wakes, and near‑ground vertical velocity.
arXiv:2512. 16275v2 Announce Type: replace-cross Abstract: Automated floor plan generation lies at the intersection of combinatorial search, geometric constraint satisfaction, and functional design requirements -- a confluence that has historically resisted a unified computational treatment.
arXiv:2610.18511v1 Announce Type: new Abstract: Buildings cause nearly 40\% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60\% and acco...
The paper introduces the Estimator from Scratch, a neural network that embeds RC thermal building equations to estimate parameters, and its extension, the Pretrained Estimator, which is pretrained on multiple buildings to avoid initial‑guess dependence. Both methods outperform a genetic‑algorithm estimator and a fully black‑box neural network across simulated and real buildings, achieving superior prediction accuracy and lower, more consistent MPC costs. The Pretrained Estimator is highlighted as a robust, computationally efficient, and initial‑guess‑free alternative for RC parameter estimation, with potential applicability to other control‑oriented dynamical systems.