| Conference: EuCAIF
Workshop
The third “European AI for Fundamental Physics Conference” (EuCAIFCon) will be held in Heidelberg, from 24th to 28th of August 2026. The aim of this event is to provide a platform for establishing new connections between AI activities across various branches of fundamental physics, by bringing together researchers that face similar challenges and/or use similar AI solutions. The conference will be organized “horizontally”: sessions are centered on specific AI methods and themes, while being cross-disciplinary regarding the scientific questions. EuCAIFCon 2026 is organised by EuCAIF | | | |
| IWR School 2026
AI for Science
The summer school is designed for PhD students who want to leverage state-of-the-art AI in their research. Applicants may come from any scientific discipline, including physics, biology, medicine, neuroscience, and climate science.
The school offers a comprehensive overview of key topics in Artificial Intelligence and Machine Learning, including Generative AI, Explainability, Simulation-based Inference, Agentic AI, Robustness and Validation of AI Methods, Vision-Language Models, Self-Supervised Learning, Knowledge Integration, and Causality. In addition to expert lectures, the program features hands-on sessions and best-practice sessions focused on how to use the latest AI tools in research.
Participants are expected to have a solid understanding of the core concepts of machine learning. | Scientific Organizer:
Carsten Rother
Ulrich Köthe
Co-Organizer:
Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA) | Mathematikon
Im Neuenheimer Feld 205
69120 Heidelberg | |
| Real-Time Deep Learning for Label-Free Imaging Flow Cytometry
Natan T. Shaked, Chair of the Department of Biomedical Engineering at Tel Aviv University
Rare-cell detection in liquid biopsies is particularly challenging because target cells occur at extremely low concentrations within large populations of blood cells. To address this challenge, I will present a label-free imaging flow cytometry platform that combines a high-speed motion-sensitive event-based camera, real-time neural networks, and interferometric phase microscopy. Cells flowing through a microfluidic channel are continuously monitored by the event-based camera, which captures sparse temporal information
at very high acquisition rates while generating minimal data for real-time classification using spiking neural networks. Upon detection of a potential rare cell, the event-based system triggers a slower interferometric imaging module to acquire a single-shot quantitative phase measurement for more detailed analysis. | | EINC building, Im Neuenheimer Feld 225a, Heidelberg, Seminar room R00.222 (ground floor), | |
| EBRAINS Users Days 2026
Agenda
Introductory presentations on EBRAINS will be given on 6 October, covering topics such as:
- How to create an EBRAINS account
- EBRAINS Collaboratory
- EBRAINS Lab
Hands-on tutorials will be given on 7 October, covering tools and services such as:
- Medical Informatics Platform
- The Virtual Brain
- SpiNNaker
- Knowledge Graph
- Siibra
- Human Intracerebral EEG Platform powered by CHORUS
| | European Institute for Neuromorphic Computing
Im Neuenheimer Feld 225a, 69120 Heidelberg, Germany | |
17.11.2026
11:15 AM - 12:15 PM | Foundation Models for the Data we Actually Have in Medicine: TabPFN and Beyond
Frank Hutter
Most data in cancer research is tabular: patient records, biomarker panels, clinical trial results, and features derived from omics. For decades, gradient-boosted trees have dominated this domain, and deep learning has struggled, especially in the small-sample regime typical of clinical studies. TabPFN is a tabular foundation model that changes this picture. Pre-trained on millions of synthetic datasets, it performs in-context learning: given a new dataset, it yields well-calibrated predictions in seconds, without hyperparameter tuning, and natively handles missing values, outliers, and mixed data types. In this talk, I will explain the ideas behind TabPFN, our Nature 2025 paper, and the fast-paced developments since then. TabPFN has already been used in hundreds of medical prediction use cases, and we are keen to work with partners to identify & solve the hardest challenges of tabular predictions whose solutions would bring the greatest benefit to society. | Oliver Stegle
Moritz Gerstung | Kommunikationszentrum (KoZ) des DKFZ
and via Stream
| |
09.12.2026
11:00 AM - 12:00 PM | Nationwide disease prediction from electronic health records and genetics
Andrea Ganna
The talk will present recent advances in disease prediction through the integration of nationwide health data and genomic information. It will describe a foundation model trained on Finnish nationwide health data, covering more than 7 million individuals and 3 billion health events, to model and predict health trajectories. The talk will examine the current strengths and limitations of this approach, including challenges related to fairness and generalizability. It will then show how polygenic scores complement electronic-health-record-based prediction, with the two approaches providing distinct strengths across disease domains. Finally, the talk will discuss how integrating genomic and EHR data can improve trial emulation, strengthen causal inference, and improve biomarker discovery. | | Kommunikationszentrum (KoZ) des DKFZ
and via Stream | |
