13 citations · 16 across the 15 of their papers we have counts for
15 papers
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…
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…
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…
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…
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…
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…
Byte Pair Encoding for Efficient Time Series Forecasting
Leon Götz, Marcel Kollovieh, Stephan Günnemann +1
Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even…
Generative Modeling with Bayesian Sample Inference
Marten Lienen, Marcel Kollovieh, Stephan Günnemann
We present a novel view of diffusion-like generative modeling from the perspective of iterative Gaussian posterior inference. By treating the generated sample as an unknown variabl…
Unlocking Point Processes through Point Set Diffusion
David Lüdke, Enric Rabasseda Raventós, Marcel Kollovieh +1
Point processes model the distribution of random point sets in mathematical spaces, such as spatial and temporal domains, with applications in fields like seismology, neuroscience,…
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
Marcel Kollovieh, Marten Lienen, David Lüdke +2
Recent advancements in generative modeling, particularly diffusion models, have opened new directions for time series modeling, achieving state-of-the-art performance in forecastin…
Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
Leon Götz, Marcel Kollovieh, Stephan Günnemann +1
Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merg…
Assessing Robustness via Score-Based Adversarial Image Generation
Marcel Kollovieh, Lukas Gosch, Marten Lienen +3
Most adversarial attacks and defenses focus on perturbations within small -norm constraints. However, threat models cannot capture all relevant semantics-preservin…
Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider +3
Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused…
U-PET: MRI-based Dementia Detection with Joint Generation of Synthetic FDG-PET Images
Marcel Kollovieh, Matthias Keicher, Stephan Wunderlich +3
Alzheimer's disease (AD) is the most common cause of dementia. An early detection is crucial for slowing down the disease and mitigating risks related to the progression. While the…
Self-Supervised Learning from Unlabeled Fundus Photographs Improves Segmentation of the Retina
Jan Kukačka, Anja Zenz, Marcel Kollovieh +2
Fundus photography is the primary method for retinal imaging and essential for diabetic retinopathy prevention. Automated segmentation of fundus photographs would improve the quali…