arXiv:2606. 23129v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectral dilemma: periodic activations capture fine details but act as all-pass filters that memorise noise, while spatially compact activations regularise effectively but suffer from low-frequency bias.
By Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti, Luigi Di Stefano
ROMNet is a hybrid reduced‑order modeling and machine‑learning framework designed to improve waveform inversion for acoustic waves. It replaces the costly nonlinear mapping from a reduced‑order model (ROM) matrix to wave speed with a neural network that outputs a simpler ROM matrix, thereby reducing computational effort. The method is validated on two training datasets—random Gaussian‑based media and the GeoFWI benchmark—and compared against direct ROM inversion and two deep‑learning FWI approaches, Fourier‑DeepONet and InversionNet.
By Liliana Borcea, Alexander Mamonov, Kui Ren, Haizhao Yang, Chugang Yi
arXiv:2607. 05025v1 Announce Type: new Abstract: Vibration-based damage identification in civil infrastructure is a challenging, ill-posed inverse problem due to measurement noise, sparse sensor arrays, and environmental variability.
By Ana Fernandez Navamuel, A. Javier Omella, Diego Zamora-Sanchez, David Pardo
The paper introduces a conditional variational autoencoder (CVAE) that learns to map shock response spectrum (SRS) curves back to acceleration time series, addressing the ill‑posed inverse problem. Unlike traditional iterative optimization methods that rely on predefined sinusoidal bases, the CVAE provides a data‑driven, non‑iterative solution. Experiments show the model achieves higher spectral fidelity, generalizes well to unseen spectra, and runs three to six orders of magnitude faster than classical techniques.
By Adam Watts (Los Alamos National Laboratory), Andrew Jeon (Los Alamos National Laboratory), Destry Newton (Los Alamos National Laboratory), Ryan Bowering (University of Rochester)
arXiv:2607. 02537v1 Announce Type: cross Abstract: Jamming and spoofing pose significant threats to wireless and satellite navigation by disrupting radio-frequency (RF) signals and compromising availability and integrity.
By Nisha L. Raichur, Lucas Heublein, Dominik Seu{\ss}, Frank Deinzer, Felix Ott
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.
By Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie
arXiv:2606. 27304v1 Announce Type: new Abstract: Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engineering structures.
By Santosh Kapuria, Abhishek
The paper presents a physics‑enhanced machine learning method that combines a long short‑term memory network with an Extended Kalman Filter to identify fast‑varying natural frequencies and damping ratios of Linear Time‑Varying systems. Using vibration data and a physics‑based model, the approach is validated on synthetic data from a 2‑blade offshore wind turbine, achieving a maximum RMS error of 0.0012 Hz for the first Fore‑Aft mode. The study also demonstrates robustness to incorrect damping assumptions and improves damping ratio estimation compared to covariance‑driven stochastic subspace identification.
By Melisa Bozaci, Alice Cicirello
Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engineering structures. However, the practical deployment of deep learning models is often hindered by the limited availability of labelled experimental data and the high computational cost of generating large-scale high-fidelity simulation datasets.
SuperPCA is a new algorithm for high‑dimensional principal component analysis that exploits an approximate eigenspace of the sample covariance matrix. The authors show that the subspace spanned by several leading eigenvectors contains useful signal information long before individual eigenvectors converge, and they derive posteriori bounds on the angle between this subspace and the true signal subspace. By using only a small number of subsampled coordinates, SuperPCA can achieve up to a ten‑fold improvement in accuracy over classical PCA while reducing data acquisition costs, especially when the signals are approximately sparse.
By Irina-Beatrice Haas, Maike Meier, Yuji Nakatsukasa, Taejun Park
arXiv:2607. 01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets.
By Qijun Chen, Shaofan Li
arXiv:2606. 11518v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations.
By Pengqing Shi, Jie Yin, Stephen Tierney, Junbin Gao