Jannis Chemseddine

I am a 2nd year PhD student at TU Berlin, advised by Prof. Dr. Gabriele Steidl. I mainly work on generative modeling, sampling, optimal transport and Bayesian inverse problems. Recently, I have also become interested in sampling of categorical data.

Papers

Preprints

Spherical Flows for Sampling Categorical Data

Jannis Chemseddine, Gregor Kornhardt, Gabriele Steidl

arXiv preprint, 2026

[paper]

Self-Aware Markov Models for Discrete Reasoning

Gregor Kornhardt, Jannis Chemseddine, Christian Wald, Gabriele Steidl

ICLR 2026 Workshop on Logical Reasoning of Large Language Models

[paper]

Telegrapher's Generative Model via Kac Flows

Richard Duong, Jannis Chemseddine, PK Friz, Gabriele Steidl

arXiv preprint, 2025

[paper] [code]

Trajectory Generator Matching for Time Series

T. Jahn, Jannis Chemseddine, Paul Hagemann, Christian Wald, Gabriele Steidl

arXiv preprint, 2025

[paper]

Journal/Conference Papers

Adapting Noise to Data: Generative Flows from 1D Processes

Jannis Chemseddine, Gregor Kornhardt, Richard Duong, Gabriele Steidl

International Conference on Machine Learning (ICML), 2026

[paper] [code]

Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry

Jannis Chemseddine, Christian Wald, Richard Duong, Gabriele Steidl

International Conference on Learning Representations (ICLR), 2025

[paper]

Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching

Jannis Chemseddine, Paul Hagemann, Christian Wald, Gabriele Steidl

Journal of Machine Learning Research, Vol. 26(141), 2025

[paper] [code]

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel

Paul Hagemann, Johannes Hertrich, Fabian Altekrüger, Robert Beinert, Jannis Chemseddine, Gabriele Steidl

International Conference on Learning Representations (ICLR), 2024

[paper] [code]

Other

Flow Matching Tutorial - CWI Autumn School 2025, Amsterdam

[code]