Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference

September 28, 2025

We put a preprint on the arXiv dealing with position-blind pytychography. Compared to the standard setup, here we ask ourselves how well the reconstruction problem can be solved, when the scan position are completely unknown. Furthermore, we explore how to leverage a powerful data-driven prior with a variational inference approach. This is joint work Simon Welker, Lorenz Kuger Berthy Feng, Martin Burger, Timo Gerkmann, Henry Chapman. Part of this project was done during my DAAD funded research stay at Caltech, in Oktober 2024.

The preprint is available on the arXiv: Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference.

Bridging AI and Theory: Workshop on the Mathematics of Transformers at DESY

October 15, 2025

At a recent workshop hosted by DESY, around 30 experts from across Europe came together to explore the theoretical foundations of transformers, the core architecture behind modern large language models. Organized by researchers from DESY, Helmholtz Imaging,...

Introduction to Regularization and Learning Methods for Inverse Problems

August 27, 2025

Together with Danielle Bednarski we uploaded our lecture notes Introduction to Regularization and Learning Methods for Inverse Problems to arXiv. The notes are based on a course we taught at the University of Hamburg in the winter term 2024/2025.

Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies

June 30, 2025

Together with Leon Bungert and Philipp Wacker we uploaded a paper to arXiv, which shows how CBO can be used to create closed-box adversarial attacks. Beyond that we establish an interesting connection between CBO and evolution strategies. The paper can be f...

Analysis of mean-field models arising from self-attention dynamics in transformer architectures with layer normalization

June 5, 2025

I’m happy to share that our paper Analysis of mean-field models arising from self-attention dynamics in transformer architectures with layer normalization has been published in the Philosophical Transactions of the Royal Society A.

Tim Roith

Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inference

You May Also Enjoy

Bridging AI and Theory: Workshop on the Mathematics of Transformers at DESY

Introduction to Regularization and Learning Methods for Inverse Problems

Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies

Analysis of mean-field models arising from self-attention dynamics in transformer architectures with layer normalization