Related papers: Learning a Latent Pulse Shape Interface for Photoi…

We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the…

Acquiring temporally high-frequency and spatially high-resolution turbulent wake flow fields in particle image velocimetry (PIV) experiments remains a significant challenge due to hardware limitations and measurement noise. In contrast,…

We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework…

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these…

Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple distributions such as isotropic Gaussian. In this paper, we…

In the frame of laser-driven wakefield acceleration, the main characteristics oflaser propagation and plasma wave excitation are described, with an emphasis onthe role of propagation distance for electron acceleration. To…

This work describes a novel data-driven latent space inference framework built on paired autoencoders to handle observational inconsistencies when solving inverse problems. Our approach uses two autoencoders, one for the parameter space and…

We propose a novel shape representation useful for analyzing and processing shape collections, as well for a variety of learning and inference tasks. Unlike most approaches that capture variability in a collection by using a template model…

This paper shows how data-driven machine learning approaches can improve growth control, reproducibility, and physical insight in the pulsed laser deposition (PLD) growth of correlated oxides. Despite well-known relationships between growth…

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures,…

Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a generative perspective…

Designing a high-quality plasma injector electron source driven by a laser beam relies on numerical parametric studies using particle-in-cell codes. The common input parameters to explore are laser characteristics, plasma species and…

Presented is a novel way to combine snapshot compressive imaging and lateral shearing interferometry in order to capture the spatio-spectral phase of an ultrashort laser pulse in a single shot. A deep unrolling algorithm is utilised for the…

The propagation of a superintense laser pulse in an underdense, inhomogeneous plasma has been studied numerically by two-dimensional particle-in-cell simulations on a time scale extending up to several picoseconds. The effects of the ion…

We use Bayesian optimization in combination with three-dimensional particle-in-cell simulations to determine the optimal laser and plasma parameters that, for a given laser pulse energy, maximize the cut-off energy of an electron beam…

We propose and demonstrate a generative deep learning approach for the shape recognition of an arbitrary object from its acoustic scattering properties. The strategy exploits deep neural networks to learn the mapping between the latent…

Coherent control of ultrafast quantum phenomena benefits from pulse-shaping capabilities allowing to modulate the envelope and instantaneous phase of optical fields on femtosecond time scales. While such control is available for optical…

This research demonstrates high-repetition-rate laser-accelerated ion beams via dual, intersecting, counterpropagating laser-driven blast waves to precisely shape underdense gas into long-lived near-critical density targets. The collision…

Industrial use of ultrashort-pulse surface structuring would significantly increase by an effective utilization of the average laser powers available currently. However, the unexplained degradation of surfaces processed with numerous pulses…

Collective effects, such as waves and instabilities, are integral to our understanding of most plasma phenomena. We have been able to study these in ultracold neutral plasmas by shaping the initial density distribution through spatial…