11 papers
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…
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 com…
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…
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…
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…
Generative Modeling with Bayesian Sample Inference
Marten Lienen, Marcel Kollovieh, Stephan Günnemann +1
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…