1 citations · 3 across the 8 of their papers we have counts for
9 papers
SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics
Gregor Kornhardt, Moritz Piening, Jannis Chemseddine +1
Evaluating text generation requires measuring how well the generated distribution matches the data distribution. For autoregressive models, this is done by the perplexity. Diffusio…
Spherical Flows for Sampling Categorical Data
Jannis Chemseddine, Gregor Kornhardt, Gabriele Steidl
We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the p…
Self-Aware Markov Models for Discrete Reasoning
Gregor Kornhardt, Jannis Chemseddine, Christian Wald +1
Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed n…
Adapting Noise to Data: Generative Flows from 1D Processes
Jannis Chemseddine, Gregor Kornhardt, Richard Duong +1
The default Gaussian latent in flow-based generative models poses challenges when learning certain distributions such as heavy-tailed ones. We introduce a general framework for lea…
Telegrapher's Generative Model via Kac Flows
Richard Duong, Jannis Chemseddine, Peter K. Friz +1
We break the mold in flow-based generative modeling by proposing a new model based on the damped wave equation, also known as telegrapher's equation. Similar to the diffusion equat…
Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
Jannis Chemseddine, Christian Wald, Richard Duong +1
We deal with the task of sampling from an unnormalized Boltzmann density by learning a Boltzmann curve given by energies starting in a simple density . First, we e…
Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
Jannis Chemseddine, Paul Hagemann, Gabriele Steidl +1
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While th…
Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distances
Jannis Chemseddine, Paul Hagemann, Christian Wald
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While th…
Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
Paul Hagemann, Johannes Hertrich, Fabian Altekrüger +3
We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modeling. This MMD, which is…