Related papers: Learning a Latent Pulse Shape Interface for Photoi…
Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space. To understand the latent space $\mathbf{x}_t \in \mathcal{X}$, we analyze them from a geometrical perspective. Our approach…
Current 3D-aware pretraining methods for embodied perception and manipulation are largely built on differentiable rendering frameworks, producing either fully implicit neural fields or fully explicit geometric primitives. Implicit…
Ultrafast lasers ($< 500$ fs) have enabled laser-matter interactions at intensities exceeding $10^{18} \rm{Wcm}^{-2}$ with only millijoules of laser energy. However, as pulse durations become shorter, larger spectral bandwidths are…
This paper presents a novel method for analyzing the latent space geometry of generative models, including statistical physics models and diffusion models, by reconstructing the Fisher information metric. The method approximates the…
At the laser acceleration of self-injected electron bunch by plasma wakefield it is important to form bunch with small energy spread and small size. It has been shown that laser-pulse shaping on radius, intensity and shape controls…
We propose the Variational Shape Learner (VSL), a generative model that learns the underlying structure of voxelized 3D shapes in an unsupervised fashion. Through the use of skip-connections, our model can successfully learn and infer a…
Fundamental to many applications of laser pulses in science and technology is an extended interaction length with matter that significantly exceeds the distance over which the pulse would normally diffract and transversely spread. At low…
Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the…
This work presents a reformulation of the recently proposed Wasserstein autoencoder framework on a non-Euclidean manifold, the Poincar\'e ball model of the hyperbolic space. By assuming the latent space to be hyperbolic, we can use its…
An experiment for studying laser self-guiding has been carried out for the high power ultrashort pulse laser interaction with an underdense plasma slab. Formation of an extremely long plasma channel and its bending are observed when the…
Photoinjectors and Free Electron Lasers (FEL) are amongst the most advanced systems in accelerator physics and have consistently pushed the boundaries of emittance and x-ray peak power. In this paper, laser shaping at the cathode is…
Modeling the time-dependent evolution of electron density is essential for understanding quantum mechanical behaviors of condensed matter and enabling predictive simulations in spectroscopy, photochemistry, and ultrafast science. Yet, while…
In recent experiments of laser pulse interaction at relativistic intensities with a low density plasma, the proton radiography technique showed evidence of long--lived field structures generated after the self-channeling of the laser pulse.…
In this study we consider the Hamiltonian approach for the construction of a map for a system with nonlinear resonant interaction, including phase trapping and phase bunching effects. We derive basic equations for a single resonant…
The present work proposes an inflow turbulence generation strategy using deep learning methods. This is achieved with the help of an autoencoder architecture with two different types of operational layers in the latent-space: a fully…
Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either…
Detailed two dimensional particle-in-cell (PIC) simulations and numerical calculations of electron density profiles, based on a simplified model, were performed to show for the first time that underdense plasma, induced by two pairs of…
The interaction of ultra-intense laser pulses with an underdense plasma is used in laser-plasma acceleration to create compact sources of ultrashort pulses of relativistic electrons and X-rays. The accelerating structure is a plasma wave,…
Experimental results, supported by precise modelling, demonstrate optimisation of a plasma-based injector with intermediate laser pulse energy ($<1$ J), corresponding to a normalised vector potential $a_0 = 2.15$, using ionisation injection…
The interaction of intense, ultra-short laser pulses with nanostructures offers promising avenues for spatiotemporal light control. While enhanced optical transmission through subwavelength apertures has been extensively studied in the…