Summer Semester 2026

Organizer: Karnik Ram (karnik.ram@tum.de)

Preliminary meeting: 14:00-14:30 on 03.02.2026 online.

In recent years there is a surge in applying deep learning to dynamical simulations at various scales: from molecular dynamics at the atomic scale, to cell dynamics at the mesoscopic scale, and to fluid and weather dynamics at the macroscopic scale. Remarkably, the architectures and training schemes used to simulate these systems at different scales are quite similar, leading to a unification of approaches and potentially the development of multi-scale simulation approaches. We will discuss and critique papers on all these topics in this seminar.

• Students are expected to study one paper in depth, and present and lead a discussion on it. Apart from the presentation and report, students are also expected to periodically submit one-paragraph summaries of the papers discussed, and participate in the discussions.
• Sessions will be held in-person (with a remote attendance option) once every two weeks, on Tuesday afternoon (14:30 - 16:30). There will be two paper presentations in every session. There will also be a catch-up lecture on certain relevant topics from deep learning (eg. diffusion models, graph learning) at the start based on interest.
• All class-related communications are over Discord, and the summaries, presentation, and report are managed on Gradescope.

Open to MSc. students with a good understanding of machine learning techniques (esp. deep learning), linear algebra, and calculus. BSc. students who are interested in enrolling must directly contact the organizer.

TBD

TBD

• Selected Topics in Deep Learning -- Equivariance & Dynamics WS25
• Selected Topics in Deep Learning -- Equivariance & Dynamics SS25
• Deep learning for the natural sciences WS24
• Deep learning for the natural sciences SS24