AI to accelerate Scientific Understanding

Exploring the Frontiers of AI-driven Research

Machine learning models have demonstrated a vast capacity to learn complex phenomena from data and to reproduce them accurately, for example by providing precise predictions of molecular properties or by generating human language in natural conversations. However, due to their black-box nature, such models often resemble oracles with vast stores of knowledge rather than scientific tools capable of reporting or communicating the reasoning underlying their predictions. This limitation constrains their potential impact in scientific applications, where understanding why a model arrives at a prediction can be as important as the prediction itself and can substantially accelerate scientific discovery and understanding.

In this workshop, we seek to develop a broader and more systematic understanding of how the explanation and interpretation of artificial intelligence models can enable AI-driven research from both theoretical and applied perspectives. In particular, we aim to explore how AI-driven research can be enriched beyond model validation and trust assessment. The workshop will include invited talks, poster sessions, and dedicated time for discussion, fostering informal exchange across disciplines such as molecular science, medicine, digital humanities, geoscience, and related fields.

Confirmed Speaker

The workshop is currently in the planning phase. So far, we are pleased to announce that the following renowned speakers have confirmed their participation. 
The speaker list will be continuously updated in the coming days.

• Prof. Przemysław Biecek, Warsaw University of Technology, Department of CAD/CAM Systems Design and Computer-Aided Medicine
• Dr. Jochen Büttner, Max Planck Institute for Geoanthropology Jena
• Prof. Dr. Gustau Camps-Valls, Universitat de València, Image and Signal Processing
• Dr. Maximilian Dax, Research group leader at ELLIS Institute and MPI in Tübingen
• Prof. Dr. Begüm Demir, BIFOLD/TU Berlin, Remote Sensing Image Analysis
• Prof. Dr. Martin Hebart, Universitätsklinikum Giessen, Professor for Computational Cognitive Neuroscience and Quantitative Psychiatry
• Dr. Anna Hedström, postdoctoral fellow at the ETH AI Center of ETH Zürich
• Prof. Dr. Dagmar Kainmüller, Max-Delbrück-Centrum für Molekulare Medizin (MDC), Biomedical Image Analysis
• Prof. Dr. Frederick Klauschen, Ludwig-Maximilians-Universität Munich, Director and Chair, Pathology & Dean of Research 
• Univ.-Prof. Dipl.-Ing. Dr.techn. Dominik Kowald, University of Graz, Professor for AI-based Information Retrieval in Digital Humanities 
• Dr. rer. nat. Sebastian Lapuschkin, Head of Explainable Artificial Intelligence Group, Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institute
• Prof. Dr. Anatole von Lilienfeld, University of Toronto, Professor & Clark Chair of Advanced Materials at the Vector Institute
• Dr. med. Philipp Keyl, Junior Group Leader, Institute of Pathology, LMU Munich
• Prof. Dr. Marina Meila, Cheriton School of Computer Science, University of Waterloo and Canada CIFAR Chair in AI, Vector Institute
• Prof. Dr. Tomaso Poggio, Massachusetts Institute of Technology, CSAIL, McDermott Professor in Brain Sciences
• Prof. Iyad Rahwan, Director of the Max Planck Institute for Human Development
• Prof. Dr. Katharina Rohlfing, Paderborn University, Institute of German Studies and Comparative Literature - German and General Linguistics
• Prof. Dr. Alexandre Tkatchenko, University of Luxembourg, Professor in Theoretical Condensed Matter Physics
• Prof. Dr.-Ing. Britta Wrede, Bielefeld University, Professor for Medical Assistance Systems
• Prof. Dr. Carlos Zednik, Eindhoven University of Technology, Industrial Engineering and Innovation Science

About the Workshop

The workshop is jointly organized by ELLIS Unit Berlin and BIFOLD - The Berlin Institute for the Foundations of Learning and Data.

Date: 26.05.2026 - 29.05.2026

Location: Ciniq, Salzufer 6, 10587 Berlin

The aim of the three-day-workshop plus an optional preceding half-day tutorial is to bring together internationally renowned scientists, local scholars, and students. The tutorial offers a concise introduction to paradigms and tools that enrich AI-driven research with transparency and understanding. Through hands-on discussions, practical software demonstrations, and concrete application examples, participants will gain familiarity with key explanation methods for machine learning models. No prior experience is required - the tutorial is designed to ensure everyone can follow the main workshop with confidence.

Registration: Please register here. 

While preference will be given to ELLIS and ELIZA researchers, applications are warmly welcomed from qualified individuals worldwide.

The final agenda is still under revision but will comprise keynotes, scientific presentations of varying length, poster sessions, and in-depth discussions in an informal and engaging setting.