Conference Agenda

Differentiable Wave-Optics for Single-Shot X-Ray Phase-Contrast Imaging of Plasma Targets

Ritz Ann Aguilar¹, Long Yang¹, Lingen Huang¹, Michael Bussmann^1,2, Ulrich Schramm^1,3, Thomas Cowan^1,4, Jeffrey Kelling^1,5

1: Helmholtz-Zentrum Dresden-Rossendorf, Germany; 2: Center for Advanced Systems Understanding, Germany; 3: Technische Universität Dresden, Germany; 4: European XFEL, Germany; 5: Technische Universität Chemnitz, Germany

Performance Bounds for Reliability and Hallucination Risk in Remote-Sensing Super-Resolution

David Iagaru^1,2, Jakob Gawlikowski¹

1: German Aerospace Center (DLR), Remote Sensing Technology Institute, Germany; 2: Ecole Polytechnique, Department of Applied Mathematics, Paris, France.

CaMoEMMIL: Clustering-Aware Mixture Of Experts For Multimodal Multiple Instance Learning In Lung Transplantation

Dinesh Adhithya Haridoss, Ewa Szczurek

Helmholtz Munich, Germany

Modelling Patient Variation Across Datasets And Diseases With Contrastive Learning On Single-Cell Data

Vladimir A. Shitov^1,4, Benjamin M. Frey^1,4, Mohammad Moghareh Dehkordi², Till Richter^1,2, Mojtaba Bahrami^1,3, Emma Maria Schonner², Youssef Naciri Zerta¹, Fabian J. Theis^1,2,3, Malte D. Luecken^1,4

1: Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Munich, Germany; 2: School of Computing, Information and Technology, Technical University of Munich, Munich, Germany.; 3: TUM School of Life Sciences Weihenstephan, Technical University of Munich, Germany.; 4: Comprehensive Pneumology Center (CPC) with the CPC-M bioArchive and Institute of Lung Health and Immunity, Helmholtz Munich, Member of the German Center for Lung Research (DZL), Munich, Germany.

No Data? No Problem: Robust Vision-Tabular Learning with Missing Values

Marta Hasny^1,2, Laura Daza^1,2, Keno Bressem², Maxime Di Folco^1,2,3, Julia A. Schnabel^1,2,4

1: Helmholtz Munich, Germany; 2: Technical University of Munich, Germany; 3: Telecom Paris, France; 4: King's College London, UK

Reliable and Sustainable AI for Scientific Discovery

Gitta Kutyniok

LMU Munich, Germany

AI and Future of Medicine

Daniel Rueckert

Technical University of Munich, Germany

Deep Graph Learning for Temporal Data

Ingo Scholtes

University of Würzburg, Germany

Neurosymbolic Models of Uncertainty and Logical Reasoning

Annemarie Friedrich

Universität Augsburg, Germany

Rethinking the Foundations of Weather and Climate Modelling

Martin Schultz

FZJ, Germany

A Multi-Sensor Foundation Model for Earth Observation

Nassim Ait Ali Braham^1,2, Aaron Christian Banze^1,3, Julien Mairal⁴, Jocelyn Chanussot⁴, Conrad Martin Albrecht¹, Xiao Xiang Zhu²

1: German Aerospace Center (DLR), Germany; 2: Technical University of Munich (TUM), Germany; 3: University of the Bundeswehr Munich, Germany; 4: Universite Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, France

OneProtGPT: Bridging Protein Embeddings and Large Language Models for Protein Understanding

Javad Kasravi, Alina Bazarova, Stefan Kesselheim

Jülich Supercomputing Centre, Forschungszentrum Jülich, 52428 Jülich, Germany

AMPFormer: A Peptide Foundation Model for Antimicrobial Discovery

Pankhil Gawade^1,2, Adam Izdebski^1,2, Marcelo DT Torres⁴, Cesar De La Fuente-nunez⁴, Ewa Szczurek^1,3

1: Institute of AI for Health, Helmholtz Zentrum Munchen; 2: Technical University of Munich, TUM School of Computation, Information and Technology; 3: Faculty of Mathematics, Informatics and Mechanics, University of Warsaw; 4: University of Pennsylvania, Philadelphia, PA, USA.

The Mean is the Mirage: Entropy-Adaptive Model Mergingunder Heterogeneous Domain Shifts in Medical Imaging

Sameer Ambekar^1,2,3,4, Reza Nasirigerdeh^5,4, Peter J. Schuffler^5,1,4, Lina Felsner¹, Daniel M. Lang^1,2, Julia A. Schnabel^1,2,3,5,6

1: School of Computation, Information and Technology, Technical University of Munich, Germany; 2: Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Germany; 3: relAI – Konrad Zuse School of Excellence in Reliable AI; 4: Munich Center for Machine Learning (MCML); 5: Institute of Pathology, Technical University of Munich, Germany; 6: School of Biomedical Engineering and Imaging Sciences, King’s College London, UK.

ConvexGating infers gating strategies from clusters in single cell cytometry data

Vincent D Friedrich^1,2, Karola Mai^3,4, Thomas P Hofer⁵, Elfriede Nößner⁵, Lorenzo Bonaguro^3,6,7, Celia L Hartmann^3,8, Aleksej Frolov^3,8,9, Caterina Carraro^3,6, Doaa Hamada^3,10,11, Mehrnoush Hadaddzadeh-Shakiba^3,8, Heidi Theis⁷, Dalila Juliana Silva Ribeiro¹², Dagmar Wachten¹², F Thomas Wunderlich¹³, Markus Scholz^1,14, Fabian J Theis^15,16,17, Matthias Becker^3,4, Marc D Beyer^3,7,8, Joachim L Schultze^3,6,7, Maren Büttner^3,7,15

1: University of Leipzig, Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig, Germany; 2: Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Leipzig, Germany; 3: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Bonn, Germany; 4: Modular High Performance Computing and Artificial Intelligence, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany; 5: Research Group Tissue Control of Immunocytes, Helmholtz Center Munich, Munich, Germany; 6: Life and Medical Sciences (LIMES) Institute, University of Bonn, Bonn, Germany; 7: PRECISE Platform for Single Cell Genomics and Epigenomics, DZNE and University of Bonn and West German Genome Center (WGGC), Bonn, Germany; 8: Immunogenomics & Neurodegeneration, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Bonn, Germany; 9: Department of Microbiology and Immunology, The Peter Doherty Institute for Infection and Immunity, University of Melbourne, Melbourne, VIC, Australia; 10: Molecular Immunology in Neurodegeneration, German Center for Neurodegenerative Diseases and the University of Bonn, Germany; 11: Medical Microbiology and Immunology Department, Faculty of Medicine, Mansoura University, Egypt; 12: Institute of Innate Immunity, Biophysical Imaging, Medical Faculty, University of Bonn, Bonn, Germany; 13: Max Planck Institute for Metabolism Research, Center for Endocrinology, Diabetes and Preventive Medicine (CEDP), Cologne, Germany; 14: University of Leipzig, Faculty of Mathematics and Computer Science, Leipzig, Germany; 15: Institute of Computational Biology, Helmholtz Center Munich, Germany; 16: Department of Mathematics, Technical University of Munich, Germany; 17: TUM School of Life Sciences Weihenstephan, Technical University of Munich, Germany

From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs

Boyong Wu^1,2, Sanghwan Kim^1,2,3, Zeynep Akata^1,2,3

1: Technical University of Munich, Germany; 2: Helmholtz Munich, Germany; 3: Munich Center for Machine Learning (MCML), Germany

Cross Modalities Pretraining of Sparse Lidar and Dense Image Foundation Model for Global Carbon Stock Mapping

Audita Widya Astuti^1,2, Aldino Rizaldy¹, Gunjan Joshi¹, Weikang Yu¹, Peter Steinbach¹, Qi Zhang², Xiao Xiang Zhu², Pedram Ghamisi¹

1: Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany; 2: Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany

ICD-Code Extraction from Clinical Notes using Large Language Models in a RAG pipeline

Ludwig Krause¹, Martin Dyrba^1,2, Thomas Kirste¹, João Areias Saraiva^1,2

1: Hybrid Methods in Artificial Intelligence and Machine Learning, University of Rostock, Germany; 2: German Center for Neurodegenerative Diseases, Rostock, Germany

Bridging Scales: Adapting Human 3D Foundation Models for Mouse Micro-CT Phenotyping

Yoland Savriama, Arnd Heuser

Max-Delbrück-Centrum für Molekulare Medizin in der Helmholtz-Gemeinschaft, Germany

TiViT: Time Series Representations Lie Hidden in Pretrained Vision Transformers

Simon Roschmann^1,2,3,4, Quentin Bouniot^1,2,3,4, Vasilii Feofanov⁵, Ievgen Redko⁵, Zeynep Akata^1,2,3,4

1: Helmholtz Munich, Germany; 2: Technical University of Munich, Germany; 3: Munich Center for Machine Learning, Germany; 4: Munich Data Science Institute, Germany; 5: Paris Noah’s Ark Lab, France

Physics-Aligned Self-Supervised Learning for Scientific Imaging

Bashir Kazimi¹, Stefan Sandfeld^1,2

1: Institute for Advanced Simulation—Materials Data Science and Informatics (IAS-9), Forschungszentrum Jülich, Germany; 2: Chair of Materials Data Science and Materials Informatics, Faculty 5—Georesources and Materials Engineering, RWTH Aachen University,

MADRNA: A Physics-Informed Machine-Learned Coarse-Grained Force Field for RNA

Emile de Bruyn¹, Anton Dorn¹, Fabrice von der Lehr², Philipp Knechtges², Alexander Schug³, Stefan Kesselheim¹

1: Forschungszentrum Jülich (FZJ), Germany; 2: Deutsches Zentrum für Luft- und Raumfahrt (DLR), Germany; 3: Karlsruhe Institute of Technology, Germany

Inverse Design of Multilayer Thin Films using Robust Deep Learning

Jonas Schaible^1,2, Asena Karolin Özdemir³, Charlotte Debus³, Sven Burger², Achim Streit³, Christiane Becker^1,4, Klaus Jäger^1,2, Markus Götz^3,5

1: Helmholtz Centre for Materials and Energy, Germany; 2: Zuse Institute Berlin, Germany; 3: Scientific Computing Center, Germany; 4: HTW Berlin, Germany; 5: Helmholtz AI, Germany

AI-quifer – Predicting Offshore Groundwater Occurrences through the Application of Artificial Intelligence

Laura Haffert¹, Marion Jegen¹, Christian Siebert², Caroline Arnold³, Tino Rödiger²

1: GEOMAR Helmholtz Centre for Ocean Research Kiel, Germany; 2: UFZ, Helmholtz Centre for Environmental Research, Germany; 3: Helmholtz Centre Hereon, Germany

Reinforce Adjoint Matching: Fine-tuning Diffusion and Flow Matching Models without Reward Gradients

Andreas Bergmeister¹, Jakiw Pidstrigach², Stefanie Jegelka¹, Nikolas Nüsken³, Carles Domingo-Enrich⁴

1: TUM, Germany; 2: University of Oxford, United Kingdom; 3: King’s College London, United Kingdom; 4: Microsoft Research, United States

SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis

Marie Brockschmidt^1,2, Maresa Schröder^1,2, Stefan Feuerriegel^1,2

1: LMU Munich; 2: Munich Center for Machine Learning (MCML)

Stitch: Training-Free Position Control in Multimodal Diffusion Transformers

Jessica Bader^1,2, Mateusz Pach^1,2, María A. Bravo^1,2, Serge Belongie³, Zeynep Akata^1,2

1: Helmholtz Munich, Germany; 2: Technical University of Munich; 3: University of Copenhagen

Causal Machine Learning for Predictive Biomarker Discovery and Subgroup Refinement in Metastatic Colorectal Cancer

Alina J. Arneth¹, Julian W. Holch^2,3,4, Octavia-Andreea Ciora^5,6, Volker Heinemann^2,3,4, Stefan Feuerriegel^5,6, Michael P. Menden^1,7

1: Department of Biochemistry and Pharmacology, Bio21 Molecular Science and Biotechnology Institute, The University of Melbourne, Australia; 2: Department of Medicine III and Comprehensive Cancer Center Munich, University Hospital, Ludwig-Maximilians University Munich, Germany; 3: Comprehensive Cancer Center Munich, Germany; 4: German Cancer Consortium (DKTK), partner site Munich, German Cancer Research Center (DKFZ), Germany; 5: LMU Munich School of Management, LMU Munich, Germany; 6: Munich Center for Machine Learning, Germany; 7: Computational Health Center, Institute of Computational Biology, Helmholtz Munich, Germany

Neural Operator-Based Surrogate Modeling for Efficient Prediction of Temperature and Residual Stresses in Tempered Glass

Tarek Hussein, Johannes Schilp

Universität Augsburg, Germany

GRIP: Physics-Informed Neural Network for Gradient Retention Time Prediction in Liquid Chromatography

Kevin George¹, F.P. Jake Haeckl¹, Gerrit Großmann², Alexey Gurevich¹, Azat Tagirdzhanov¹

1: Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Germany; 2: German Research Center for Artificial Intelligence (DFKI) Kaiserslautern

Who Owns Human Experience? Ethical Implications of Transforming Tacit Knowledge into Neural Models

Christopher Koska¹, Markus Schatzl²

1: University Augsburg, Germany; 2: ergonoi GbR

Towards Useful and Private Synthetic Omics: Community Benchmarking of Generative Models for Transcriptomics Data

Hakime Öztürk^1,2, Tejumade Afonja³, Joonas Jälkö⁴, Ruta Binkyte³, Pablo Rodriguez-Mier⁵, Sebastian Lobentanzer⁶, Andrew Wicks^7,8, Jules Kreuer⁹, Sofiane Ouaari⁹, Nico Pfeifer⁹, Shane Menzies¹⁰, Sikha Pentyala¹⁰, Daniil Filienko¹⁰, Steven Golob¹⁰, Patrick McKeever¹⁰, Jineta Banerjee¹¹, Luca Foschini¹¹, Martine De Cock^10,12, Julio Saez-Rodriguez¹³, Mario Fritz³, Oliver Stegle^1,2, Antti Honkela⁴

1: European Molecular Biology Laboratory (EMBL), Genome Biology Unit, Heidelberg, Germany; 2: Division of Computational Genomics and Systems Genetics, German Cancer Research Center (DKFZ), Heidelberg, Germany; 3: CISPA Helmholtz Center for Information Security, Saarbrücken, Germany; 4: University of Helsinki, Finland; 5: Heidelberg University, Germany; 6: Helmholtz Munich, Germany; 7: Division of Tumorigenesis and Molecular Cancer Prevention, German Cancer Research Center (DKFZ), Heidelberg, Germany; 8: DKFZ Hector Cancer Institute at the University Medical Center Mannheim, Germany; 9: Eberhard Karls Universität Tübingen, Germany; 10: University of Washington Tacoma, USA; 11: Sage Bionetworks, Seattle, USA; 12: Ghent University, Ghent, Belgium; 13: European Bioinformatics Institute (EMBL-EBI), UK

HemAutomaton: A lightweight NCA-based pipeline for large-scale extraction of white blood cells from whole slide images

Michael Deutges¹, Altana Namsaraeva¹, Tabita Ghete², Markus Metzler², Carsten Marr¹, Maximilian Buser¹

1: Helmholtz Munich, Germany; 2: Universitätsklinikum Erlangen, Germany

DeepRVAT2: Unified Modeling of Coding and Regulatory Rare Variation at Genome Scale for Enhanced Gene Discovery and Diagnostics

Eva Holtkamp^1,2, Shubhankar Londhe^1,2, Anna Starovoit², Merit Back², Thibault Bechtler⁴, Brian Clarke⁴, Oliver Stegle^4,5,6, Julien Gagneur^1,2,3

1: Computational Health Center, Helmholtz Center Munich, Neuherberg, Germany; 2: chool ofComputation, Information and Technology, Technical University of Munich, Garching, Germany; 3: Institute of Human Genetics, School of Medicine, Technical University of Munich, Munich, Germany; 4: German Cancer Research Center (DKFZ), Heidelberg, Germany; 5: European Molecular Biology Laboratory (EMBL), Heidelberg, Germany; 6: Heidelberg University, Germany

The Mean is the Mirage: Entropy-Adaptive Model Mergingunder Heterogeneous Domain Shifts in Medical Imaging

Sameer Ambekar^1,2,3,4, Reza Nasirigerdeh^5,4, Peter J. Schuffler^5,1,4, Lina Felsner¹, Daniel M. Lang^1,2, Julia A. Schnabel^1,2,3,5,6

1: School of Computation, Information and Technology, Technical University of Munich, Germany; 2: Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Germany; 3: relAI – Konrad Zuse School of Excellence in Reliable AI; 4: Munich Center for Machine Learning (MCML); 5: Institute of Pathology, Technical University of Munich, Germany; 6: School of Biomedical Engineering and Imaging Sciences, King’s College London, UK.

ConvexGating infers gating strategies from clusters in single cell cytometry data

Vincent D Friedrich^1,2, Karola Mai^3,4, Thomas P Hofer⁵, Elfriede Nößner⁵, Lorenzo Bonaguro^3,6,7, Celia L Hartmann^3,8, Aleksej Frolov^3,8,9, Caterina Carraro^3,6, Doaa Hamada^3,10,11, Mehrnoush Hadaddzadeh-Shakiba^3,8, Heidi Theis⁷, Dalila Juliana Silva Ribeiro¹², Dagmar Wachten¹², F Thomas Wunderlich¹³, Markus Scholz^1,14, Fabian J Theis^15,16,17, Matthias Becker^3,4, Marc D Beyer^3,7,8, Joachim L Schultze^3,6,7, Maren Büttner^3,7,15

1: University of Leipzig, Institute for Medical Informatics, Statistics, and Epidemiology, Leipzig, Germany; 2: Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Leipzig, Germany; 3: Systems Medicine, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Bonn, Germany; 4: Modular High Performance Computing and Artificial Intelligence, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany; 5: Research Group Tissue Control of Immunocytes, Helmholtz Center Munich, Munich, Germany; 6: Life and Medical Sciences (LIMES) Institute, University of Bonn, Bonn, Germany; 7: PRECISE Platform for Single Cell Genomics and Epigenomics, DZNE and University of Bonn and West German Genome Center (WGGC), Bonn, Germany; 8: Immunogenomics & Neurodegeneration, Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Bonn, Germany; 9: Department of Microbiology and Immunology, The Peter Doherty Institute for Infection and Immunity, University of Melbourne, Melbourne, VIC, Australia; 10: Molecular Immunology in Neurodegeneration, German Center for Neurodegenerative Diseases and the University of Bonn, Germany; 11: Medical Microbiology and Immunology Department, Faculty of Medicine, Mansoura University, Egypt; 12: Institute of Innate Immunity, Biophysical Imaging, Medical Faculty, University of Bonn, Bonn, Germany; 13: Max Planck Institute for Metabolism Research, Center for Endocrinology, Diabetes and Preventive Medicine (CEDP), Cologne, Germany; 14: University of Leipzig, Faculty of Mathematics and Computer Science, Leipzig, Germany; 15: Institute of Computational Biology, Helmholtz Center Munich, Germany; 16: Department of Mathematics, Technical University of Munich, Germany; 17: TUM School of Life Sciences Weihenstephan, Technical University of Munich, Germany

From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs

Boyong Wu^1,2, Sanghwan Kim^1,2,3, Zeynep Akata^1,2,3

1: Technical University of Munich, Germany; 2: Helmholtz Munich, Germany; 3: Munich Center for Machine Learning (MCML), Germany

Cross Modalities Pretraining of Sparse Lidar and Dense Image Foundation Model for Global Carbon Stock Mapping

Audita Widya Astuti^1,2, Aldino Rizaldy¹, Gunjan Joshi¹, Weikang Yu¹, Peter Steinbach¹, Qi Zhang², Xiao Xiang Zhu², Pedram Ghamisi¹

1: Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany; 2: Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany

ICD-Code Extraction from Clinical Notes using Large Language Models in a RAG pipeline

Ludwig Krause¹, Martin Dyrba^1,2, Thomas Kirste¹, João Areias Saraiva^1,2

1: Hybrid Methods in Artificial Intelligence and Machine Learning, University of Rostock, Germany; 2: German Center for Neurodegenerative Diseases, Rostock, Germany

Causal Machine Learning for Predictive Biomarker Discovery and Subgroup Refinement in Metastatic Colorectal Cancer

Alina J. Arneth¹, Julian W. Holch^2,3,4, Octavia-Andreea Ciora^5,6, Volker Heinemann^2,3,4, Stefan Feuerriegel^5,6, Michael P. Menden^1,7

1: Department of Biochemistry and Pharmacology, Bio21 Molecular Science and Biotechnology Institute, The University of Melbourne, Australia; 2: Department of Medicine III and Comprehensive Cancer Center Munich, University Hospital, Ludwig-Maximilians University Munich, Germany; 3: Comprehensive Cancer Center Munich, Germany; 4: German Cancer Consortium (DKTK), partner site Munich, German Cancer Research Center (DKFZ), Germany; 5: LMU Munich School of Management, LMU Munich, Germany; 6: Munich Center for Machine Learning, Germany; 7: Computational Health Center, Institute of Computational Biology, Helmholtz Munich, Germany

Neural Operator-Based Surrogate Modeling for Efficient Prediction of Temperature and Residual Stresses in Tempered Glass

Tarek Hussein, Johannes Schilp

Universität Augsburg, Germany

GRIP: Physics-Informed Neural Network for Gradient Retention Time Prediction in Liquid Chromatography

Kevin George¹, F.P. Jake Haeckl¹, Gerrit Großmann², Alexey Gurevich¹, Azat Tagirdzhanov¹

1: Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Germany; 2: German Research Center for Artificial Intelligence (DFKI) Kaiserslautern