Related papers: Variational autoencoder inverse mapper for extract…

The cosmic microwave background power spectra are a primary window into the early universe. However, achieving interpretable, likelihood-compatible compression and fast inference under weak model assumptions remains challenging. We propose…

In this contribution we analyse the cross sections for the exclusive vector meson production as well as the deeply virtual Compton scattering (DVCS) relying on the color dipole approach and considering the numerical solution of the…

Distributions are fundamental statistical elements that play essential theoretical and practical roles. The article discusses experiences of training neural networks to classify univariate empirical distributions and to represent them on…

Although Convolutional Neural Networks (CNNs) have achieved promising results in image classification, they still are vulnerable to affine transformations including rotation, translation, flip and shuffle. The drawback motivates us to…

Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively…

Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…

We study deeply virtual Compton scattering (DVCS) on a deuteron target. We model the Generalized Quark Distributions in the deuteron by using the impulse approximation for the lowest Fock-space state. Numerical predictions are given for the…

We introduce the study of neutrino scattering off protons in the deeply virtual kinematics, which describes under a unified formalism elastic and deep inelastic neutrino scattering. A real final state photon and a recoiling nucleon are…

Study of the structure and dynamics of the nucleon has been deeply renewed with the advent of a parameterization of the partonic structure of the nucleon in terms of the Generalized Parton Distributions (GPDs). Encoding the correlations…

We embark on a systematical analysis of the quark and gluon gravitational form factors (GFFs) of the proton, by connecting energy-momentum tensor (EMT) and the near-threshold vector meson photoproduction (NTVMP). Concretely, the quark…

Variational autoencoders (VAEs) are a popular generative model used to approximate distributions. The encoder part of the VAE is used in amortized learning of latent variables, producing a latent representation for data samples. Recently,…

An approach is proposed to calculate Generalized Parton Distributions (GPDs) in a Constituent Quark Model (CQM) scenario, considering the constituent quarks as complex systems. The GPDs are obtained from the wave functions of the non…

While Variational Inference (VI) is central to modern generative models like Variational Autoencoders (VAEs) and Denoising Diffusion Models (DDMs), its pedagogical treatment is split across disciplines. In statistics, VI is typically framed…

The Variational Autoencoder (VAE) is a seminal approach in deep generative modeling with latent variables. Interpreting its reconstruction process as a nonlinear transformation of samples from the latent posterior distribution, we apply the…

Importance estimators are explainability methods that quantify feature importance for deep neural networks (DNN). In vision transformers (ViT), the self-attention mechanism naturally leads to attention maps, which are sometimes interpreted…

Conditional variational autoencoders (CVAEs) are versatile deep generative models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes that the data samples…

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by competing models such as…

Novel view synthesis often needs the paired data from both the source and target views. This paper proposes a view translation model under cVAE-GAN framework without requiring the paired data. We design a conditional deformable module (CDM)…

The key reactions to study the Generalised Parton Distributions are Deeply Virtual Compton Scattering (DVCS) and Deeply Virtual Meson Production (DVMP). At COMPASS, these processes are investigated using a high intensity muon beam with a…

Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data…