Date: September 22, 2026, 4:00 - 5:30 pm (doors open at 3:30 pm, open networking after the talks)

Location: SAP Labs Munich Campus (MUE03), Friedrich-Ludwig-Bauer-Straße 5, 85748 Garching bei München, Auditorium (AE.76)

Registration: here 

More information: Questions? Please contact iuc-tum@sap.com.

Confirmed speakers: 

Bhavatarini Kumaravel (TUM / MDSI): A Graph-Based Deep Q-Learning Agent for Grammar-Guided Structural Form-Finding
Bhavatarini's supervisor is the MDSI Core Member Prof. Pierluigi D'Acunto, TUM Chair for Structural Design, TUM School of Engineering and Design
The work investigates how graph-based deep reinforcement learning can be combined with a structural grammar in finding novel and materially efficient structural design solutions.

Annika Schneider (TUM / relAI): Decision-aligned Evaluation of Uncertainty Quantification
Annika is a relAI PhD student at Helmholtz Munich and TUM, supervised by relAI Fellow Dr. Vincent Fortuin, TUM Associate Professorship of AI for Scientific Modelling
This work investigates the question of how probabilistic models should be evaluated to ensure they perform in downstream decisions.

Sameer Ambekar (TUM / relAI / MDSI): Adressing Distribution Shifts: The Shift from Static to Thinking-based Vision-Language Models
Sameer is a relAI PhD student at Helmholtz Munich and TUM, supervised by relAI Fellow and MDSI Core Member Prof. Julia Schnabel, TUM Chair for Computational Imaging and AI in Medicine
Distribution shifts have remained a persistent challenge over the years, with solutions spanning from domain adaptation to test-time training and, most recently, post-training mechanisms for vision-language models. This is because models inevitably encounter unseen data at inference time, data they were never trained for.
This talk at SAP by Sameer will focus on addressing this problem, tracing it from convolutional architectures to modern vision-language models and reasoning models, and connecting these stages through a consistent pattern: models that allocate additional computation at test time, whether through adaptation or reasoning, generalize more reliably than those relying solely on fixed, pre-trained parameters. Sketching through these topics from his PhD research, the talk will provide an overview of addressing unseen data at test time through training, reasoning, and post-training mechanisms.