Related papers: Accelerated Integration of Stiff Reactive Systems …

While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored. We aim to close this gap by proposing a unified probabilistic model for…

In designing efficient feedback control laws for fluid flow, the modern control theory can serve as a powerful tool if the model can be represented by a linear ordinary differential equation (ODE). However, it is generally difficult to find…

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…

This paper introduces an adaptive time splitting technique for the solution of stiff evolutionary PDEs that guarantees an effective error control of the simulation, independent of the fastest physical time scale for highly unsteady…

We present a hybrid transformer architecture that replaces discrete middle layers with a continuous-depth Neural Ordinary Differential Equation (ODE) block, enabling inference-time control over generation attributes via a learned steering…

Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter…

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of…

As the number of multiple-input multiple-output (MIMO) antennas increases drastically with the development towards 6G systems, channel state information (CSI) compression becomes crucial for mitigating feedback overhead. In recent years,…

Advancing defensive mechanisms against adversarial attacks in generative models is a critical research topic in machine learning. Our study focuses on a specific type of generative models - Variational Auto-Encoders (VAEs). Contrary to…

In coherent optical orthogonal frequency-division multiplexing (CO-OFDM) fiber communications, a novel end-to-end learning framework to mitigate Laser Phase Noise (LPN) impairments is proposed in this paper. Inspired by Autoencoder (AE)…

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…

This paper presents an approach to improve the forecast of computational fluid dynamics (CFD) simulations of urban air pollution using deep learning, and most specifically adversarial training. This adversarial approach aims to reduce the…

Central to active learning (AL) is what data should be selected for annotation. Existing works attempt to select highly uncertain or informative data for annotation. Nevertheless, it remains unclear how selected data impacts the test…

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

The neural dynamics underlying brain activity are critical to understanding cognitive processes and mental disorders. However, current voxel-based whole-brain dimensionality reduction techniques fall short of capturing these dynamics,…

We introduce the Kernel-Elastic Autoencoder (KAE), a self-supervised generative model based on the transformer architecture with enhanced performance for molecular design. KAE is formulated based on two novel loss functions: modified…

Vertebral fractures are a consequence of osteoporosis, with significant health implications for affected patients. Unfortunately, grading their severity using CT exams is hard and subjective, motivating automated grading methods. However,…

Solving time-dependent Partial Differential Equations (PDEs) using a densely discretized spatial domain is a fundamental problem in various scientific and engineering disciplines, including modeling climate phenomena and fluid dynamics.…

We consider the problem of inferring latent stochastic differential equations (SDEs) with a time and memory cost that scales independently with the amount of data, the total length of the time series, and the stiffness of the approximate…

The variational auto-encoder (VAE) is a deep latent variable model that has two neural networks in an autoencoder-like architecture; one of them parameterizes the model's likelihood. Fitting its parameters via maximum likelihood (ML) is…