Search Results for author: Marten Lienen

Found 7 papers, 3 papers with code

Add and Thin: Diffusion for Temporal Point Processes

no code implementations NeurIPS 2023 David Lüdke, Marin Biloš, Oleksandr Shchur, Marten Lienen, Stephan Günnemann

Autoregressive neural networks within the temporal point process (TPP) framework have become the standard for modeling continuous-time event data.

Denoising Density Estimation +1

Assessing Robustness via Score-Based Adversarial Image Generation

no code implementations6 Oct 2023 Marcel Kollovieh, Lukas Gosch, Yan Scholten, Marten Lienen, Stephan Günnemann

In this work, we introduce Score-Based Adversarial Generation (ScoreAG), a novel framework that leverages the advancements in score-based generative models to generate adversarial examples beyond $\ell_p$-norm constraints, so-called unrestricted adversarial examples, overcoming their limitations.

Image Generation

From Zero to Turbulence: Generative Modeling for 3D Flow Simulation

1 code implementation29 May 2023 Marten Lienen, David Lüdke, Jan Hansen-Palmus, Stephan Günnemann

On this dataset, we show that our generative model captures the distribution of turbulent flows caused by unseen objects and generates high-quality, realistic samples amenable for downstream applications without access to any initial state.

torchode: A Parallel ODE Solver for PyTorch

1 code implementation22 Oct 2022 Marten Lienen, Stephan Günnemann

We introduce an ODE solver for the PyTorch ecosystem that can solve multiple ODEs in parallel independently from each other while achieving significant performance gains.

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

no code implementations14 Jul 2021 Johannes Gasteiger, Marten Lienen, Stephan Günnemann

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations.

Distance regression

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