28.03.2025

Hybrid Reinforcement Learning with Baseline Controllers

This project, conducted in collaboration with Siemens AG, explores hybrid reinforcement learning methods and development of physics-based simulations to improve the reliability and efficiency of industrial automation systems.
read more

Kontakt: olivia.garland@tum.de

25.03.2025

Master Thesis: Multimodal AI for PDAC Precursor Detection in Pathology

The Schuefflerlab for Computational Pathology at the TUM Institute for Pathology is offering a CIT Master’s thesis in the field of medical machine learning and pathology AI (artificial intelligence). The study explores the potential unimodal and multimodal deep learning models to predict precursors of pancreatic ductal adenocarcinoma (PDAC) from histology and/or spatial transcriptomics data. Please find the attached PDF for a detailed description.

Kontakt: peter.schueffler@tum.de

20.03.2025

Physics-based machine learning for hyperspectral neuronavigation

At the lab for AI in Medicine, we offer a project on physics-based machine learning for hyperspectral neuronavigation
read more

Kontakt: ivan.ezhov@tum.de

19.03.2025

Master Thesis: Pathology Foundation Model for Immunohistochemistry (IHC)

The Schuefflerlab is offering a new Master thesis Project. In this project, our objective is to develop a foundation model trained directly on IHC slides to enable more accurate automated analysis, and to facilitate downstream tasks such as staining estimation and cancer subtype classification, ultimately improving clinical decision making.
read more

Kontakt: jingsong.liu@tum.de

18.03.2025

Abschlussarbeiten, Bachelor- und Masterarbeiten

Our Research Group on Pancreatic Neuropathy and Pain is actively seeking passionate Master’s and Bachelor’s students, as well as interns, specializing in biological and chemical sciences. Our work blends molecular biology with comprehensive analysis of human pancreatic tissue, advanced 3D culture models, live cell imaging, genetically engineered mouse models (GEMMs) of pancreatic cancer, and murine models of acute and chronic pancreatitis. We operate with the Collaborative Research Center 1321 (Modelling and Targeting of Pancreatic Cancer), the DKTK (German Cancer Consortium) Munich site, the CCC München (Cancer Comprehensive Center-TZM München), and the Pancreatic Cancer Alliance Munich (PCAM). Crucially, our research is driven by insides gleaned directly from human tissue and diseases, aiming to develop in vitro and in vivo models that faithfully replicate human conditions. Comprising an international team of biologists and clinicians, our mission is to unravel key disease mechanisms in pancreatic disorders, with the ultimate aim of devising innovative therapeutic strategies. Here are our current projects: 1. Exploring the role of the exosomes in cancer cell progression and metastasis. 2. Investigating the involvement of mast cells in pain perception during acute and chronic pancreatitis 3. Examining the immunological effects of chemotherapy in pancreatic cancer. 4. Establishing of multi-cellular 3D ex-vivo systems, including organoids ad ECM scaffolds. 5. Cloning of Gene-Therapy Tools for treatment of PDAC. Our methodologies encompass a wide range of molecular biology techniques such as nucleic acid isolation, PCR, protein isolation, real-time PCR, Western blotting, cloning, bacterial transformation and plasmid isolation. We also employ cell sorting using FACS, gene editing with CRISPR Cas9, multiplex immunohistochemistry, cell culture techniques, and ECM scaffold preparation. In addition to gaining practical experience with state-of-the-art research techniques, successful candidates will have the chance to contribute to groundbreaking projects at the forefront of cancer biology and translational medicine. Join our dynamic team and help pioneer discoveries aimed at enhancing patient outcomes in pancreatic diseases. For any inquiries, please don’t hesitate to contact Dr. Rouzanna Istvánffy via e-mail at rouzanna.istvanffy@tum.de.

Wenn Sie selbst eine Diplomarbeit ausschreiben wollen, lesen Sie bitte vorher unbedingt das 'Best Practice Manual Stellenanzeigen'.

Kontakt: rouzanna.istvanffy@tum.de

17.03.2025

Measurement of Liquid-Liquid-Equilibria (LLE) of different solvents in electrolytes and biological systems

At the Laboratory of Chemical Process Engineering, we are studying the effects of salts and other biological compounds on the liquid-liquid equilibria (LLE) of water-alcohol solutions.
read more

Kontakt: hamzah.elfaitory@tum.de

17.03.2025

Column experiments for Managed Aquifer Recharge

Master's theses or study project as part of the Smart-SWS project: Linking flood protection and drought prevention
read more

Kontakt: lea.augustin@tum.de

14.03.2025

Master Thesis: Microrobots for ATP Sensing

The Microrobotic Bioengineering Lab (MRBL) is offering a Master’s thesis position on developing new sensing capability for soft microrobots. In this project, you will explore ways to incorporate a suitable ATP sensor into the material of the soft microrobot, enabling real-time metabolic rate sensing. You will also gain hands-on experience in high-throughput fabrication of soft microrobots and learn to test them in cell culture experiments.
read more

Kontakt: Philipp.harder@tum.de

13.03.2025

AI-Driven Photovoltaic Energy Forecasting

Predicting PV energy generation over a 24-hour period is challenging due to the dynamic nature of solar irradiance and weather conditions. This thesis aims to develop innovative approaches that combine physical modeling of PV system performance with advanced machine learning techniques to generate accurate short-term forecasts.
read more

Kontakt: lingga_aksara.putra@tum.de

13.03.2025

AI-Driven Wind Energy Forecasting

Wind energy is characterized by variability and non- linear behavior, complicating grid management and energy planning. Accurately forecasting wind energy generation is essential for optimizing grid operations, reducing energy costs, and ensuring system reliability. This thesis will explore innovative approaches to predict the generated wind energy over a 24-hour horizon by leveraging physical models (such as turbine power curves) and data-driven machine-learning techniques.
read more

Kontakt: lingga_aksara.putra@tum.de