Accurate and fast urban noise prediction is pivotal for public health and for regulatory workflows in cities, where the Environmental Noise Directive mandates regular strategic noise maps and action plans, often needed in permission workflows, right-of-way allocation, and construction scheduling. Physics-based solvers are too slow for such time-critical, iterative "what-if" studies. We evaluate conditional Normalizing Flows (Full-Glow) for generating for generating standards-compliant urban sound-pressure maps from 2D urban layouts in real time per 256x256 map on a single RTX 4090), enabling interactive exploration directly on commodity hardware. On datasets covering Baseline, Diffraction, and Reflection regimes, our model accelerates map generation by >2000 times over a reference solver while improving NLoS accuracy by up to 24% versus prior deep models; in Baseline NLoS we reach 0.65 dB MAE with high structural fidelity. The model reproduces diffraction and interference patterns and supports instant recomputation under source or geometry changes, making it a practical engine for urban planning, compliance mapping, and operations (e.g., temporary road closures, night-work variance assessments).
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows
Duke University(杜克大学);Carnegie Mellon University(卡内基梅隆大学)
规范化流是一类广泛使用的潜在变量生成模型,具有易于处理的可能性。仿射耦合(Dinh et al,2014-16)模型是一种特别常见的归一化流类型,其潜变量到可观测变量变换的雅可比矩阵是三角形的,允许在线性时间内计算可能性。尽管仿射耦合被广泛使用,但体系结构的特殊结构使得理解它们的表示能力具有挑战性。直到最近,三篇平行论文才解决了普遍近似的问题(Huang等人,2020;Zhang等人,2020;Koehler等人,2020年)--他证明了合理的规则分布可以用仿射耦合任意地近似--尽管网络具有接近奇异的雅可比矩阵。由于病态雅可比矩阵是基于似然性训练的障碍,因此基本问题仍然存在:哪些分布可以使用条件良好的仿射耦合流来近似?在本文中,我们表明,任何对数凹分布可以近似使用条件良好的仿射耦合流。在证明技术方面,我们发现并利用仿射耦合架构,欠阻尼朗之万动力学(一种常用于从吉布斯测度采样的随机微分方程)和Hénon映射(一种出现在辛同态研究中的结构化动力系统)之间的深层联系。我们的研究结果还通知训练仿射耦合的实践:我们近似填充版本的输入分布与iid高斯-一个战略,克勒等人。(2020)经验上观察到导致更好的条件流,但迄今没有理论基础。因此,我们的证明可以被视为在训练规范化流时高斯填充的好处提供了理论证据。
Waveflow: boundary-conditioned normalizing flows applied to fermionic wavefunctions
University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所);Canadian Institute for Advanced Research (CIFAR)(加拿大高等研究院);Acceleration Consortium(加速联盟)
Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
Arquimea Research Center(阿奎米亚研究中心);Department of Computer Science, University of York(约克大学计算机科学系);Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology(塞浦路斯技术大学电子工程与计算机科学系)
Generative AI for Urban Planning: Synthesizing Satellite Imagery via Diffusion Models
Massachusetts Institute of Technology(麻省理工学院);University of Florida(佛罗里达大学);The Singapore-MIT Alliance for Research and Technology(新加坡-麻省理工学院研究与技术联盟);Boston University(波士顿大学)
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
Institute of Nanotechnology, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院纳米技术研究所);Institute of Theoretical Informatics, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院理论信息学研究所)
AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions
School of Electrical Engineering and Computer Science, Nanjing University of Aeronautics and Astronautics(南京航空航天大学电子工程与计算机科学学院);School of Computer Science and Technology, North University of China(中北大学计算机科学与技术学院);School of Semiconductor and Physics, North University of China(中北大学半导体与物理学院)
Haar Wavelet based Block Autoregressive Flows for Trajectories
Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);Bosch Center for Artificial Intelligence(博世人工智能中心);CISPA Helmholtz Center for Information Security(亥姆霍兹信息安全中心)
Flow-based conditional cardiac anatomy generation for virtual cohorts
Delft University of Technology(代尔夫特理工大学);Hospital of the University of Pennsylvania(宾夕法尼亚大学医院);Ghent University(根特大学);University of Pennsylvania(宾夕法尼亚大学)
Generative Flows for Potential Outcomes and Counterfactuals
School of Industrial and Systems Engineering(工业与系统工程学院);Georgia Institute of Technology(佐治亚理工学院);Elmore Family School of Electrical and Computer Engineering(埃洛姆家族电气与计算机工程学院);Purdue University(普渡大学)
Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation
Institute of Intelligent Computing, University of Electronic Science and Technology of China (UESTC)(电子科技大学智能计算研究所);College of Systems Engineering, National University of Defense Technology(国防科技大学系统工程学院);Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology (BNRist)(信息科学与技术国家研究中心电子工程系);School of Information and Communication Engineering, University of Electronic Science and Technology of China (UESTC)(电子科技大学信息与通信工程学院)
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Huazhong University of Science and Technology(华中科技大学);Xi’an Jiaotong University(西安交通大学);University of Electronic Science and Technology of China(电子科技大学)
GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion Guidance
Applied Mathematics Department, ETSIAE-School of Aeronautics, Universidad Politécnica de Madrid, Spain(马德里理工大学应用数学系);Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI 48109, USA(密歇根大学航空航天工程系)