activity
20212026
most citedSelf-Supervised Learning from Unlabeled Fundus Photographs Improves Segmentation of the Retina

2 citations · 2 across the 4 of their papers we have counts for

collaborators

9 papers

cs.LG2026

Interpolating Discrete Diffusion Models with Controllable Resampling

Marcel Kollovieh, Sirine Ayadi, Stephan Günnemann

Discrete diffusion models form a powerful class of generative models across diverse domains, including text and graphs. However, existing approaches face fundamental limitations. M…

cs.LG2026

3D Molecule Generation from Rigid Motifs via SE(3) Flows

Roman Poletukhin, Marcel Kollovieh, Eike Eberhard +1

Three-dimensional molecular structure generation is typically performed at the level of individual atoms, yet molecular graph generation techniques often consider fragments as thei…

cs.LG2025

Discrete Bayesian Sample Inference for Graph Generation

Ole Petersen, Marcel Kollovieh, Marten Lienen +1

Generating graph-structured data is crucial in applications such as molecular generation, knowledge graphs, and network analysis. However, their discrete, unordered nature makes th…

cs.CV2025

GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation

Phillip Mueller, Talip Uenlue, Sebastian Schmidt +4

Precise geometric control in image generation is essential for engineering \& product design and creative industries to control 3D object features accurately in image space. Tradit…

cs.LG2025

Edit-Based Flow Matching for Temporal Point Processes

David Lüdke, Marten Lienen, Marcel Kollovieh +1

Temporal point processes (TPPs) are a fundamental tool for modeling event sequences in continuous time, but most existing approaches rely on autoregressive parameterizations that a…

stat.ML2025

Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling

Niclas Dern, Lennart Redl, Sebastian Pfister +3

Sampling from unnormalized target distributions, e.g.\ Boltzmann distributions , is fundamental to many scientific applications yet comp…