Talks

• SympFormer: Accelerated Attention Blocks via Inertial Dynamics on Density Manifolds
  • Oberwolfach workshop Flows on Measure Spaces and Applications in Machine Learning, March 2026.
  • Minisymposium PDE, Measure Transport, and Geometric Perspectives on Generative Modeling at the SIAM Conference on Mathematics of Data Science, Salt Lake City, Utah, USA, November 2026.
  • Group Seminar, Chair for Mathematical Foundations of AI, LMU, Munich, October 2026.
• Gradient flows on probability measures and their inertial variants: from Wasserstein geometry to Transformers
  • Applied Numerical Analysis Seminar, Technical University of Munich, 28 May 2026.
  • Applied Analysis Seminar, University of Heidelberg, 12 May 2026.
  • Learning and Optimization in Luminy (LOL’26), 29 June–3 July 2026.
• Accelerated Stein Variational Gradient Flow
  • Minisymposium “New trends in geometric machine and deep learning”, Computational Methods in Applied Mathematics (CMAM 2026), 21 July 2026.
  • GSI’25 – 7th International Conference on Geometric Science of Information, Saint-Malo, France, 30 October 2025. Slides
  • Colloquium of the Signal Processing Department, University Carlos III Madrid, November 2025.
  • Postgraduate seminar organized by the Numerical Modeling of Differential Equations Research Group, TU Berlin, November 2025.
  • Stan Osher’s UCLA Level Set Seminar, April 2025.
  • Poster at Mathematical and Scientific Machine Learning 2025, Naples, August 2025.
  • Poster in the Foundations of Data Science and Machine Learning workshop at Foundations of Computational Mathematics 2026, Vienna, July 2026.
• Wasserstein Gradient Flows for Moreau Envelopes of $f$-Divergences in Reproducing Kernel Hilbert Spaces
  • Conference on Mathematics of Machine Learning 2025, Hamburg, 30 September 2025. Slides · Video
  • Stan Osher’s UCLA Level Set Seminar, 19 August 2024. Slides · Video
  • Poster at the Workshop and Summer School on Applied Analysis 2023, Chemnitz, 18–22 September 2023.
  • Poster at the Workshop on Optimal Transport – from Theory to Applications, Berlin, March 2024. Pitch
  • Poster at Learning and Optimization in Luminy 2024, June 2024.
  • Poster at the SIGMA Workshop 2024, CIRM, October 2024.
  • Poster at the Gradient Structures Workshop, Augsburg, February 2026.
  • Poster at TUM’s research retreat Advanced Mathematical Methods in Data Analysis and Signal Processing, Tutzing, March 2026 (Best Poster Award).
  • Poster in the Computational Optimal Transport workshop at Foundations of Computational Mathematics 2026, Vienna, July 2026.
• Wasserstein gradient flows of MMD-regularized $f$-divergences
  • Minisymposium Optimal Transport in Imaging – Flows, Regularization, and Machine Learning at the SIAM Conference on Imaging Science, Salt Lake City, Utah, USA, November 2026.
• Approximating $f$-Divergences with Rank Statistics
  • Poster at ICML 2026, Seoul, July 2026.
• Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences
  • Poster at ICML 2026, Seoul, July 2026.
• Interpolating between Optimal Transport and KL-Regularized Optimal Transport using Rényi Divergences
  • University of South Carolina Mathematics Graduate Colloquium, 12 September 2024. Slides
  • OT-DOM 24. Pitch · Poster
• Wasserstein Gradient Flows of MMD Functionals with Distance Kernel and Cauchy Problems on Quantile Functions
  • Joint Applied and Computational Mathematics and RTG Data Science Seminar, University of South Carolina, 30 August 2024. Slides

Expository talks

• Moving Mass, Decreasing Energy: Learning Probability Distributions with Wasserstein Gradient Flows
  BMS–BGSMath Junior Meeting 2026, Barcelona, 4 September 2026.
  Slides

• Training Neural Networks at the Edge of Stability
  Slides
  An overview of Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability and Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability, held in Benjamin Gess’ Mathematics of Machine Learning seminar.

• What does Adam have to do with symplectic manifolds? The geometry behind momentum methods in machine learning
  14th BMS Student Conference
  Slides

• What are … generative probability flows for sampling?
  In the “What is … ?” series of the Berlin Mathematical School
  Slides · Video

• Mode collapse and metastability in transformers
  Slides
  An overview of The emergence of clusters in self-attention dynamics and A Unified Perspective on the Dynamics of Deep Transformers, held in Benjamin Gess’ Mathematics of Machine Learning seminar, Berlin–Leipzig Hybrid Seminar SS25.

• “Zoom and enhance” geht wirklich – mit Atomic Norm Minimization
  Talk in German on my bachelor’s thesis Atomic Norm Minimisation for Superresolution.
  17. Dies Mathematicus, TU Berlin, 25 November 2022
  Slides · Video · MATLAB code

• 3 minute talk about the Kullback–Leibler Divergence
  Seminar Optimal Transport, Prof. Gabriele Steidl, summer semester 2021. Slides

• Adversarial Regularisation in Inverse Problems
  On the NeurIPS 2018 paper by Sebastian Lunz et al., seminar Neural Networks for Inverse Problems, winter semester 2021/22. Slides

• Compactly supported shearlets are optimally sparse
  Seminar Applied Functional Analysis, summer semester 2019. Slides

• Atomic Norm Minimisation for Superresolution
  Seminar Optimal Transport, summer semester 2021. Slides