Search Results for author: Stathi Fotiadis

Found 9 papers, 4 papers with code

Score Normalization for a Faster Diffusion Exponential Integrator Sampler

1 code implementation31 Oct 2023 Guoxuan Xia, Duolikun Danier, Ayan Das, Stathi Fotiadis, Farhang Nabiei, Ushnish Sengupta, Alberto Bernacchia

As a simple fix, we propose to instead reparameterise the score (at inference) by dividing it by the average absolute value of previous score estimates at that time step collected from offline high NFE generations.

Image generation with shortest path diffusion

1 code implementation1 Jun 2023 Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili, Da-Shan Shiu, Alberto Bernacchia

We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring.

Deblurring Image Generation

Towards Fast Simulation of Environmental Fluid Mechanics with Multi-Scale Graph Neural Networks

no code implementations5 May 2022 Mario Lino, Stathi Fotiadis, Anil A. Bharath, Chris Cantwell

Numerical simulators are essential tools in the study of natural fluid-systems, but their performance often limits application in practice.

Graph Neural Network

Disentangled Generative Models for Robust Prediction of System Dynamics

1 code implementation26 Aug 2021 Stathi Fotiadis, Mario Lino, Shunlong Hu, Stef Garasto, Chris D Cantwell, Anil Anthony Bharath

Deep neural networks have become increasingly of interest in dynamical system prediction, but out-of-distribution generalization and long-term stability still remains challenging.

Disentanglement Out-of-Distribution Generalization

Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks

no code implementations9 Jun 2021 Mario Lino, Chris Cantwell, Anil A. Bharath, Stathi Fotiadis

Continuum mechanics simulators, numerically solving one or more partial differential equations, are essential tools in many areas of science and engineering, but their performance often limits application in practice.

Graph Neural Network Inductive Bias

Fully Convolutional Approach for Simulating Wave Dynamics

no code implementations1 Jan 2021 Mario Lino Valencia, Chris D Cantwell, Eduardo Pignatelli, Stathi Fotiadis, Anil Anthony Bharath

In this work, we investigate the performance of fully convolutional networks to predict the motion and interaction of surface waves in open and closed complex geometries.

Simulating Surface Wave Dynamics with Convolutional Networks

no code implementations1 Dec 2020 Mario Lino, Chris Cantwell, Stathi Fotiadis, Eduardo Pignatelli, Anil Bharath

We investigate the performance of fully convolutional networks to simulate the motion and interaction of surface waves in open and closed complex geometries.

Comparing recurrent and convolutional neural networks for predicting wave propagation

1 code implementation ICLR Workshop DeepDiffEq 2019 Stathi Fotiadis, Eduardo Pignatelli, Mario Lino Valencia, Chris Cantwell, Amos Storkey, Anil A. Bharath

Dynamical systems can be modelled by partial differential equations and numerical computations are used everywhere in science and engineering.

Cannot find the paper you are looking for? You can Submit a new open access paper.