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.

BioXPT-Brain: a foundation model integrating 3D vasculature and spatial transcriptomics to decode aging and vascular dementia

Laurent H. A. Simons^1,2, Louis B. Kümmerle^1,2,4, Fabian Theis^2,3,4, Ali Ertürk^1,5,6,7

1: Institute for Intelligent Biotechnologies, Helmholtz Zentrum München, Neuherberg, Germany; 2: Institute of Computational Biology, Helmholtz Zentrum München, Neuherberg, Germany; 3: School of Computing, Information and Technology, Technical University of Munich, Munich, Germany; 4: TUM School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany; 5: Institute for Stroke and Dementia Research, Klinikum der Universität München, Ludwig-Maximilians University Munich, Munich, Germany; 6: School of Medicine, Koç University, İstanbul, Turkey; 7: Munich Cluster for Systems Neurology (SyNergy), 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

Leveraging multi-modal representations

Stefanie Jegelka

TUM, 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

RenewBench: Real Energy Data You Can Actually Use

Elena Vollmer^1,3, Andreas Beckert^2,3, Hadeer El Ashhab^1,3, Paul Keil^2,3, Benjamin Schäfer^1,3, Beate Geyer^2,3, Markus Götz^1,3, Tobias Weigel^2,3, Kaleb Phipps¹

1: Karlsruhe Institute of Technology (KIT), Germany; 2: Helmholtz-Center Hereon, Germany; 3: Helmholtz AI, 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

AI for Fundamental Physics: Learning from Big Data at the LHC

Judith Katzy

DESY, Germany

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

Andreas Bergmeister¹, Stefanie Jegelka¹, Jakiw Pidstrigach², 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

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

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

Multimodal Representation Learning for Pan-Cancer Type Classification Using Attention-Based Set Encoding and Contrastive Pre-Training

Fabian Janosch Krüger, Bora Uyar, Altuna Akalin

Max Delbrück Center for Molecular Medicine, Germany

Higher-Order Hit-&-Run Samplers for Linearly Constrained Densities

Richard D. Paul^1,2, Anton Stratmann¹, Johann F. Jadebeck¹, Martin Beyß¹, Hanno Scharr¹, David Rügamer^2,3, Katharina Nöh¹

1: Forschungszentrum Jülich, Germany; 2: Department of Statistics, LMU Munich; 3: Munich Center for Machine Learning (MCML)

Simple Yet Effective: Basic Population and Evolutionary Statistics Contain Richest Information to Infer Systematic Variant Effects

Zhengyuan Xue^1,2,3, Francesco Paolo Casale^2,4, Daniel Kotlarz^1,5

1: 1Institute of Translational Genomics, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany; 2: School of Computation, Information and Technology, Technical University of Munich, Garching, Germany; 3: Helmholtz Association—Munich School for Data Science (MUDS), Munich, Germany; 4: Helmholtz Pioneer Campus, Helmholtz Zentrum München, German Research Center for Environmental Health, Neuherberg, Germany; 5: Department of Pediatrics, Dr. von Hauner Children's Hospital, University Hospital, Ludwig Maximilian University Munich, Munich, Germany

Bringing Gaps between Farmers and AI with XAI Principles

Chandrabali Karmakar¹, Arnab Bhowmik², Dumitru Corneliu Octavian³

1: German Aerospace Center (DLR), Germany; 2: German Aerospace Center (DLR), Germany; 3: German Aerospace Center (DLR), Germany

Abstracts Explorer: LLM-Powered Semantic Exploration of Scientific Conference Proceedings

Till Korten, Peter Steinbach

Helmholtz Zentrum Dresden Rossendorf (HZDR), Germany

Systematic benchmarking of imaging-based spatial transcriptomics preprocessing

Louis Kümmerle¹, Daria Romanovskaia^1,2, Habib Rehman³, Valentina Beliaeva^1,2, Fabian Theis¹, Malte Lücken^1,2

1: Institute of Computational Biology, Helmholtz Munich, Germany; 2: Institute of Lung Health and Immunity, Helmholtz Munich, Germany; 3: Indiana University School of Medicine

Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases

Jun Li¹, Mingxuan Liu², Jiazhen Pan¹, Che Liu³, Wenjia Bai³, Cosmin Bercea¹, Julia Schnabel^1,4,5

1: Technical University of Munich, Germany; 2: University of Trento, Italy; 3: Imperial College London, United Kingdom; 4: Helmholtz Munich, Germany; 5: King's College London, United Kingdom

Geometry-Aware Edge Pooling for Graph Neural Networks

Katharina Limbeck^1,2, Lydia Mezrag^3,4, Guy Wolf^3,4, Bastian Rieck^1,5

1: Helmholtz Munich, Germany; 2: Technical University of Munich, Germany; 3: University of Montreal, Canada; 4: Mila - Quebec Artificial Intelligence Institute, Canada; 5: University of Fribourg, Switzerland

Phenotype-driven virtual screening accelerates therapeutic discovery for idiopathic pulmonary fibrosis

Kevin Merchant¹, Adam Izdebski¹, Serra Korkmaz¹, Arun Kumar Verma¹, Michael Gerckens¹, Gerald Gerald Burgstaller¹, Ewa Szczurek^1,2

1: Helmholtz Munich; 2: Faculty of Mathematics, Informatics and Mechanics, University of Warsaw

Machine Learning-based RNA Design for the Development of Efficient mRNA Therapeutics

Zahra Mir, Annalisa Marsico

Helmholtz Munich, Computational Health Center, Computational Biology (ICB), Germany

Reinterpreting Protein Sequences as Structured Signals: A CNN-Residual Approach to Neuropeptide Classification

Ana Beatriz Miranda Valentin¹, Marcus Vinicius da Silva Rodrigues¹, Robson Parmezan Bonidia¹, Elisângela Aparecida da Silva Lizzi¹, Ulisses Nunes da Rocha², Glaucia Maria Bressan¹

1: Federal University of Technology-Paraná, Brazil; 2: Helmholtz Centre for Environmental Research, Deutschland

Extracting 1D JWST Spectra from 2D Spectrograms with Deep Learning

Soorya Narayan¹, William Gillard¹, Stephane Ayache², Julien Zoubian¹

1: Centre de Physique des Particules de Marseille, France; 2: Laboratoire d'Informatique et des Systèmes, Marseille, France

Segmentation of glands in big cohort data by deep learning

Phuong Thanh Nguyen, Hans J. Grabe, Mark O. Wielpütz, Alexander Teumer

Universitätsmedizin Greifswald, Germany

Subclass-Conditioned Flow Matching for Long-Tailed Chest X-Ray Augmentation

Felix Nützel¹, Mischa Dombrowski¹, Bernhard Kainz^1,2

1: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Germany; 2: Imperial College London, UK

MoA: Mixture of Aggregators Improves Slide-Level Diagnosis in Computational Pathology

Fatih Ozlugedik^1,3, Furkan Dasdelen^1,2,3, Rao Muhammed Umer¹, Carsten Marr^1,3

1: Helmholtz Munich, Germany; 2: TUM; 3: LMU

Topic Modeling and Opinion Analysis of Hyperloop Discussions on Twitter Using Latent Dirichlet Allocation

Kanak Pandit^1,4, Aditeya Prajapati², Sanyam Jain³, Steve Fernandes⁵, Aditya Ranjan Shandliya⁶, Muhammad Saeed^1,4,7

1: University of Stuttgart , Germany; 2: University of Southern California, USA; 3: Boston University, USA; 4: ARENA2036 e.V.; 5: University of Mumbai, India; 6: Hochschule Bremen, Germany; 7: Swinburne University of Technology, Melbourne, Australia

Sentiment Analysis of Indian Hyperloop Tweets for Opinion Inversion Prediction

Kanak Pandit^1,4, Sanyam Jain³, Prem Sharma⁵, Aditeya Prajapati², Upkar Chaurasiya⁷, Muhammad Saeed^1,4,6

1: University of Stuttgart, Germany; 2: University of Southern California, USA; 3: Boston University, USA; 4: ARENA2036, Germany; 5: Deakin University; 6: Swinburne University of Technology, Australia; 7: University of Mumbai, India

Test-time augmentation with synthetic data addresses distribution shifts in spectral imaging

Ahmad Bin Qasim^1,2,3, Alessandro Motta¹, Alexander Studier-Fischer⁴, Jan Sellner^1,2,3,5, Leonardo Ayala¹, Marco Hübner^1,3, Marc Bressan⁴, Berkin Özdemir⁴, Karl Friedrich Kowalewski^4,6, Felix Nickel^4,7, Silvia Seidlitz^1,2,3,5, Lena Maier-Hein^1,2,3,5,7

1: Division of Intelligent Medical Systems (IMSY), German Cancer Research Center (DKFZ), Heidelberg, Germany; 2: Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany; 3: Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany; 4: Department of General, Visceral, and Transplantation Surgery, Heidelberg University Hospital, Heidelberg, Germany; 5: National Center for Tumor Diseases (NCT), A Partnership between DKFZ and University Medical Center Heidelberg, Heidelberg, Germany; 6: Department of Urology, University Medical Center Mannheim, Heidelberg University, Mannheim, Germany; 7: Medical Faculty, Heidelberg University, Heidelberg, Germany

HoloZip: A Machine Learning-Based Approach for Extreme X-ray Holographic Data Compression

Vahid Rahmani¹, Johannes Hagemann¹, Christian Schroer^1,2,3

1: Deutsches Elektronen-Synchrotron DES, Germany; 2: Department Physik, Universität Hamburg UHH, Germany; 3: HELMHOLTZ IMAGING

Optimal conversion from Rényi Differential Privacy to $f$-Differential Privacy

Anneliese Riess^1,2, Juan Felipe Gomez³, Flavio du Pin Calmon³, Julia Schnabel^1,2, Georgios Kaissis⁴

1: Helmholtz Munich, Germany; 2: Technical University of Munich, Germany; 3: Harvard University, USA; 4: Hasso-Plattner-Institut, Germany

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

Simon Roschmann^1,2,3,4, Paul Krzakala^5,6, Sonia Mazelet⁶, Quentin Bouniot^1,2,3,4, 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: Télécom Paris, France; 6: École Polytechnique, France

AtlasAlign: PointTransformer-based alignment of spatial omics to mouse brain common coordinate framework

Josef Salg^1,2, Wasim Aftab², Christian Schiffer³, Hannah Spitzer^2,4

1: Technical University of Munich (TUM), Germany; 2: Institute for Stroke and Dementia Research (ISD), Germany; 3: Institute of Neuroscience and Medicine (INM-1) Forschungszentrum Jülich, Germany; 4: Institute of Computational Biology, Helmholtz Munich, Germany

UdonPred: Untangling Protein Intrinsic DisorderPrediction

Julius Schlensok^1,2, David Wagemann¹, Tobias Senoner¹, Markus Haak³, Burkhard Rost^1,4,5

1: School of Computation, Information and Technology (CIT), Faculty of Informatics, Chair of Bioinformatics & Computational Biology - i12, Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching/Munich, Germany; 2: Institute of Computational Biology (ICB), Helmholtz München, Ingolstädter Landstraße 1, 85764 Neuherberg, Germany; 3: Translational Microbiome Data Integration, School of Life Sciences, Technical University of Munich (TUM), Alte Akademie 8, 85354 Freising, Germany; 4: Institute for Advanced Study (TUM-IAS), Technical University of Munich (TUM), Lichtenbergstr. 2a, 85748 Garching/Munich, Germany; 5: School of Life Sciences Weihenstephan (TUM-WZW), Technical University of Munich (TUM), Alte Akademie 8, 85354 Freising, Germany

Fused Transformer Blocks Improve Pretraining Efficiency and Contextual Language Understanding

Jörn Schmiedel

factorize.bio, Germany

Persona Vectors: Steering Towards Faithful Verbalized Uncertainty Expression in LLMs

Arsen Sheverdin^1,2, Tim G. J. Rudner³, Vincent Fortuin^1,4

1: Helmholtz AI, Munich; 2: Technical University of Munich; 3: University of Toronto; 4: Technical University of Nuremberg

Scalable and interpretable representation alignment with ordinal similarity

Diogo Soares¹, Pankhil Gawade^1,2, Andrea Dittadi¹, Ewa Szczurek^1,3

1: Helmholtz Munich, AIH, Germany; 2: Technical University of Munich, Germany; 3: University of Warsaw, Poland

Multimodal Data-driven Transfer Learning Impelled Framework for Spatiotemporal Forecasting of Urban Pollution (PM2.5)

Narendran Sobanapuram Muruganandam, Erika Von Schneidemesser

Research Institute for Sustainability, Germany

A Hierarchical Bayesian Multiple Instance Learning Framework for Joint Localization and Testing of Spatial Differential Expression

Niklas Stotzem^1,2, Simon Chang³, Na Cai⁴, Francesco Paolo Casale^1,2

1: Helmholtz Munich, Germany; 2: Technical University of Munich, Germany; 3: Regensburg University, Germany; 4: ETH Zurich, Switzerland

Trustworthy Deep Surrogates for Inverse Materials Design with Calibrated Uncertainty

Hui Min Teh¹, Tarek Iraki¹, Stefan Sandfeld^1,2

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

In-Model Bias Mitigation Methods for Age Confounding in Dementia Detection

Jaya Terli¹, Majid Ramedani¹, Stefan Teipel^1,2, Martin Dyrba¹

1: Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Rostock, Germany; 2: Klinik für Psychosomatische Medizin und Psychotherapie (KPM), Universitätsmedizin Rostock, Germany

Modeling Neuro–Behavioral State Dynamics from Longitudinal Multimodal Recordings

Jens Tillmann¹, Tobias Schmidt², Ziyan Huang¹, Amine Bahlouli¹, Steffen Schneider², Jan Gründemann^1,3

1: Deutsches Zentrum für Neurodegenerative Erkrankungen e. V. (DZNE), Germany; 2: Helmholtz Munich, Neuherberg, Germany; 3: University of Bonn, Medical Faculty, Bonn, Germany

Consistent Representation Learning for Modeling Neuro-Behavioral State Dynamics

Tobias Schmidt^1,4, Jens Tillmann², Rodrigo González Laiz^1,4, Kristián Szuppinger¹, Ziyan Huang², Amine Bahlouli², Jan Gründemann^2,3, Steffen Schneider^1,4

1: Helmholtz Zentrum München Deutsches Forschungszentrum für Gesundheit und Umwelt ( GmbH ) Germany; 2: German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany; 3: University of Bonn, Medical Faculty, Bonn, Germany; 4: Munich Center for Machine Learning

Self-supervised Denoising Of Raw Tomography Detector Data For Improved Image Reconstruction

Israt Jahan Tulin, Sebastian Starke, Dominic Windisch, André Bieberle, Peter Steinbach

Helmholtz-Zentrum Dresden - Rossendorf e. V., Germany

Semantic Harmonization of Noisy Medical Imaging Cohorts via Vision-Language Model

Xiaoliang Wang¹, Jiayi Wang¹, Ibrahim Ethem Hamamci^3,4,5, Suprosanna Shit^3,4, Sezgin Er^3,5, Hadrien Reynaud¹, Weitong Zhang², Bjoern Menze^3,4, Andreas Maier¹, Bernhard Kainz^1,2

1: Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany; 2: Imperial College London, UK; 3: University of Zurich, Switzerland; 4: ETH Zurich, Switzerland; 5: Istanbul Medipol University, Turkey

Enhancing Clinical Immunology and Disease Diagnostics with Global Swarm Learning

Stefanie Warnat-Herresthal¹, Ivan Savchuk¹, Lucas Secchim Ribeiro¹, Benedikt Clemens¹, Kilian Dahm¹, Maren Büttner², Hartmut Schultze^1,3, Matthias Becker¹, Lorenzo Bonaguro¹, Global Swarm Learning Group⁴, Anna Aschenbrenner¹, Joachim L. Schultze¹

1: DZNE, Germany; 2: Calico Life Sciences; 3: Hewlett Packard Enterprise, Houston, Texas, USA; 4: The Global Swarm Learning Group

Flow-aware Latent Diffusion for Synthetic Temporal Angiography

Qiwen Xu^1,2, Andreas Bender¹, Máté Maros², David Rügamer¹

1: LMU Munich, Germany; 2: Heidelberg University, Germany

MatBind: Probing the multimodality of materials science with contrastive learning

Le Yang¹, Anoop K. Chandran⁹, Jona Östreicher³, Adrian Mirza², Sebastien Bompas¹, Bashir Kazimi¹, Stefan Kesselheim^9,4, Pascal Friederich³, Kevin Maik Jablonka^2,6,7,8, Stefan Sandfeld^1,5

1: Institute for Advanced Simulations (IAS-9), Forschungszentrum Jülich GmbH, Germany; 2: Helmholtz Institute for Polymer in Energy Applications Jena, Germany; 3: Institute of Nanotechnology, Karlsruhe Institute of Technology, Germany; 4: University of Cologne, Germany; 5: RWTH Aachen University, Germany; 6: Friedrich Schiller University Jena, Germany; 7: Jena Center for Soft Matter, Germany; 8: Center for Energy and Environmental Chemistry Jena, Germany; 9: Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH, Germany

Creating a Benchmark Image Dataset for Reliable Quantification of Arctic Phytoplankton using AI

Anna Narberhaus¹, Natasha Bryan¹, Mar Fernández-Méndez^1,2

1: Alfred-Wegener-Institut, Germany; 2: University of Bremen, Germany

PromptGate: Federated Context Optimizationfor Dynamic VLM Gating in Open-Set MedicalImaging

Adea Nesturi, David Duenas Gaviria, Jiajun Zeng, Shadi Albarqouni

University of Bonn, University Hospital Bonn, Clinic for Diagnostic and Interventional Radiology, Bonn, Germany

Neural Posterior Estimation for Empirical Power System Time Series

Ulrich Oberhofer, Nicolas Weber, Veit Hagenmeyer, Benjamin Schäfer

Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology, Germany

Underconfident Predictions in MFVI

James Odgers, Vincent Fortuin

Helmholtz Munich, Germany

Differentiable Power-Flow Optimization

Muhammed Öz¹, Jasmin Hörter¹, Kaleb Phipps¹, Charlotte Debus¹, Achim Streit¹, Markus Götz^1,2

1: Karlsruhe Institute of Technology, Germany; 2: Helmholz AI, Karlsruhe

A generative model for dimensionality reduction with millions of features and few samples

Corrado Pancotti¹, Anders Krogh², Piero Fariselli³

1: Helmholtz AI, Helmholtz Zentrum Munchen, Ingolstadter Landstraße 1,Neuherberg, Germany; 2: Center for Health Data Science, Department of Public Health, University of Copenhagen, Copenhagen, Denmark; 3: Department of Medical Sciences, University of Torino, Italy

"Hello World": How to Have a Conversation with the Global Weather

Kaleb Phipps¹, Hannes Gaumann¹, Friedrich Oberreuter¹, Akshat Vyas¹, Christian Werner¹, Jonathan Winter¹, Charlotte Debus¹, Markus Götz^1,2, Paul Kieckhefen^1,2

1: Karlsruhe Institute of Technology, Germany; 2: Helmholtz AI

Segmentation of the intracranial cavity in T1-weighted MR images of the human head by a location-specific 3D U-Net

Peter Pieperhoff¹, Svenja Caspers^1,3, Katrin Amunts^1,2

1: Institute for Neuroscience and Medicine (INM-1), Forschungszentrum Jülich, Germany; 2: C. and O. Vogt Institute for Brain Research, Medical Faculty, University Hospital, Heinrich-Heine-University of Düsseldorf, Germany; 3: Institute for Anatomy I, Medical Faculty, University Hospital, Heinrich-Heine-University of Düsseldorf, Germany

BioCUDA: An Accessible AI Pipeline for Fast, Accurate 3D MRI Reconstruction Across Species

Stefan Pinkernell¹, Karsten Schimpf¹, Felizitas Wermter², Karol Szustakowski³, Marie Piraud³, Christian Bock², Sonja Hänzelmann¹

1: Data Science Group, Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research, Bremerhaven; 2: Integrative Ecophysiology, Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research, Bremerhaven; 3: Piraud Team, Helmholtz AI, Helmholtz Munich

Machine-Learned Interatomic Potentials for Fe–Ni Alloys: Benchmarking MACE Models for Magnetism and Phase Stability

Kushal Ramakrishna¹, Mani Lokamani¹, Attila Cangi^1,2

1: Helmholtz-Zentrum Dresden-Rossendorf (HZDR); 2: Center for Advanced Systems Understanding (CASUS)

Hybrid Multimodal Late Fusion Frameworks for Robust bvFTD Classification in Imbalanced Dementia Cohorts

Majid Ramedani¹, Devesh Singh^1,2, Stefan Teipel^1,3, Martin Dyrba¹

1: German Center for Neurodegenerative Diseases (DZNE), Germany; 2: Institute and Policlinic of Radiology, Pediatric Radiology and Neuroradiology, University Medical Center Rostock, Rostock, Germany; 3: Department of Psychosomatic Medicine, Rostock University Medical Center, Rostock, Germany

Amortising Inference and Meta-Learning Priors in Neural Networks

Tommy Rochussen^1,2,3, Vincent Fortuin^1,2,4

1: Helmholtz AI, Germany; 2: MCML, Germany; 3: TUM, Germany; 4: UTN, Germany

SCHEMA: profiling Spatial Cancer HEterogeneity across modalities to benchmark Metastasis risk prediction

Daria Romanovskaia^1,2, Nikita Moshkov¹, Niklas Binder³, Mohammed Zidane^1,3, Fabian Theis^1,5,6, Carsten Weiss⁴, Christian Schuerch³, Markus Diefenbacher², Malte Luecken^1,2

1: Institute of Computational Biology, Helmholtz Munich, Germany; 2: Institute of Lung Health and Immunity, Helmholtz Munich, Germany; 3: University Hospital Tübingen, Germany; 4: Karlsruhe Institute of Technology, Germany; 5: TUM School of Life Sciences Weihenstephan,Technical University of Munich, Germany; 6: TUM School of Computing, Information and Technology, Technical University of Munich, Munich, Germany

Machine Learning-Accelerated Prediction of Hydrogen Embrittlement fromTEM Microstructures

Karina Ruzaeva¹, Aravinth Ravikumar², Bashir Kazimi¹, Daniel Höche², Stefan Sandfeld¹

1: Forschungszentrum Juüich GmbH; 2: Helmholtz Zentrum Hereon, Germany

Multimodal Data-Driven Forecasting of Coastal Environmental Health in the Baltic Sea

Naina Said¹, Helmke Hepach², Olaf Landsiedel³, Laura Harms³

1: Christian-Albrechts-Universität zu Kiel (CAU), Germany; 2: GEOMAR Helmholtz Centre for Ocean Research Kiel, Germany; 3: Technische Universität Hamburg, Germany

Improvement of Whale Vocalization Detection with Temporal Context and Soft Labels

Alex Savchik¹, Stefan Pinkernell¹, Elena Schall², Sonja Haenzelmann¹

1: Data Science Group, Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research, Germany; 2: Ocean Acoustics Group, Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research

Learning Coarse-Grained Potentials for Intrinsically Disordered Proteins

Moritz Schäffler, Emile de Bruyn, Sebastian Schmidt, Stefan Kesselheim

Forschungszentrum Jülich, Germany

A modular Retrieval Augmented Generation (RAG) Toolbox for Building Transparent AI-Search Engines

Mascha Schmidt, Victor Haguet, Fritz Niesel

FZJ, Germany

Better Uncertainties Don’t Guarantee Better Decisions

Annika Schneider^1,2,3,4, Tommy Rochussen^1,2,4, Vincent Fortuin^1,2,3,4

1: HAI, Germany; 2: TUM; 3: relAI; 4: MCML

Attributing the effects of multiple line outages via Shapley values

Sarah Schreyer¹, Marc Hunkemöller¹, Jan Lange¹, Iva Bačić¹, Philipp C. Böttcher¹, Dirk Witthaut¹, Johannes Kruse²

1: Institute of Climate and Energy Systems (ICE-1), Forschungszentrum Jülich, Germany; 2: Amprion GmbH, Transmission System Operation, Germany

Can Uncertainty Quantification Benefit From Label Embeddings? A Case Study on Local Climate Zone Classification

Christoph Schweden¹, Katharina Hechinger², Göran Kauermann³, Xiao Xiang Zhu⁴

1: German Aerospace Center, Germany; 2: Interhyp; 3: LMU Munich; 4: TUM

Benchmarking Taxonomic Classifiers: Bridging 16S rRNA metabarcoding and Shotgun Metagenomics for AI-Driven Microbiome Decoding

Sakshi Singh^1,2, Florian Heininger^1,2, Xu Holtkotte^1,2, Sabine Schmidt⁴, Jens Puschhof⁵, Eran Elinav^6,4, Silke A. Grauling-Halama^1,2, Niels Halama^1,2,3

1: Department of Tumor Immunology and Tumor Immunotherapy, Helmholtz Center for Translational Oncology (HI-TRON), Mainz, Germany; 2: German Cancer Research Center (DKFZ), Heidelberg, Germany; 3: Department of Hematology, Medical Oncology and Pneumology, University Medical Center, Mainz, Germany; 4: Division of Microbiome and Cancer, German Cancer Research Center (DKFZ), Heidelberg, Germany; 5: Epithelium Microbiome lnteractions, German Cancer Research Center (DKFZ), Heidelberg, Germany; 6: Department of Systems Immunology, Weizmann Institute of Science, Rehovot, Israel

Toward Condition-Aware MOF Topology Prediction via Latent Generative Modeling

Evgenii Sovetkin¹, Gordan Prastalo², Stefan Kesselheim¹, Kevin Maik Jablonka²

1: Forschungszentrum Jülich GmbH, Germany; 2: Helmholtz Institute for Polymers in Energy Applications Jena (HIPOLE Jena), Jena, Germany

Blur-aware Single-cell Segmentation and Feature Extraction for Drug-activity Measurement in Brightfield Organoid Imaging

Serena Sritharan¹, Fatima Gutierrez Tenorio^2,3, Claudia Ball^2,3, Marie Piraud¹

1: Helmholtz Zentrum München GmbH, Germany; 2: Department for Translational Medical Oncology, NCT/UCC Dresden and DKFZ; 3: Translational Medical Oncology, Carl Gustav Carus Faculty of Medicine, Dresden

Decoding Values: Measuring Culture Embedded in Large Language Models

Anton Steuer^1,2, Carolin Schuster², Michael Banf¹

1: Perelyn GmbH, Germany; 2: Technical University Munich, Germany

Cytoarchitecture in Words: Weakly Supervised Vision–Language Modeling for Human Brain Microscopy

Matthew Sutton^1,2, Katrin Amunts^1,3, Timo Dickscheid^1,4, Christian Schiffer^1,2

1: Institute of Neuroscience and Medicine (INM-1), Research Centre Jülich, Germany; 2: Helmholtz AI, Research Centre Jülich, Germany; 3: Cécile & Oskar Vogt Institute for Brain Research, University Hospital Düsseldorf, Germamny; 4: Computer Vision, Institute for Computational Visualistics, University of Koblenz, Germany

The (AI)^2 Consultant - A Co-consultant for AI Consultants

Karol Szustakowski, Haider Khan, Marie Piraud

Helmholtz Zentrum Munich, Germany

Accessible pipeline for open set dermatological captioning with scarce data

Karol Szustakowski¹, Sebastian Sitaru², Paola Buedo¹, Marie Piraud¹

1: Helmholtz AI, Helmholtz Zentrum München, Germany; 2: Technical University of Munich, Klinikum rechts der Isar, Germany

Machine Learning for Rogue Wave Prediction in the Southern North Sea

Salika Thilakarathne¹, Ina Teutsch², Lisa Barros de Andrade e Sousa³, Paul Keil^1,3, Marie Piraud³, Ralf Weisse¹

1: Helmholtz-Zentrum Hereon, Germany; 2: Federal Waterways Engineering and Research Institute (BAW); 3: Helmholtz AI

Nanopore- and AI-Empowered Microbial Viability Inference

Harika Muazzez Ürel

Helmholtz Munich, Germany

Counterfactual Ship Attribution in Cloud Fields Using Deep Learning and Satellite Observations

Rikard Vinge, Athina Argyrouli, Daniela Espinoza-Molina, Pascal Hedelt

German Aerospace Center (DLR), Germany

RenewBench: Real Energy Data You Can Actually Use

Elena Vollmer^1,3, Andreas Beckert^2,3, Hadeer El Ashhab^1,3, Paul Keil^2,3, Benjamin Schäfer^1,3, Beate Geyer^2,3, Markus Götz^1,3, Tobias Weigel^2,3, Kaleb Phipps¹

1: Karlsruhe Institute of Technology (KIT), Germany; 2: Helmholtz-Center Hereon, Germany; 3: Helmholtz AI, Germany

An AI System for Robust Plain Language Translation of Clinical Trials

Raeesa Yousaf^1,2, Stephanie Stapfer², Sebastian Lobentanzer^1,2

1: Institute of Computational Biology, Computational Health Center, Helmholtz Munich, Germany; 2: German Center for Diabetes Research, Germany

K-MaT: Knowledge-Anchored Manifold Transport For Cross-Modal Prompt Learning In Medical Imaging

Jiajun Zeng, Shadi Albarqouni

University of Bonn, University Hospital Bonn, Clinic for Diagnostic and Interventional Radiology, 53127 Bonn, Germany

Analysis of immune responses in renal cell carcinoma with synergistic ex vivo and in silico simulation tumor models

Xin-Wen Zhang^1,2, Alexandra Poechmann^1,3, Elena Sofia Rießle¹, Stefanie Zschäbitz⁴, Matthias Gaida⁵, Niels Halama^1,6

1: German Cancer Research Center (DKFZ), Helmholtz Institute for Translational Oncology (HI-TRON), Tumor Immunology and Tumor Immunotherapy, Mainz, Germany; 2: University Medical Center Mainz, Department of Hematology and Medical Oncology, Mainz, Germany; 3: Faculty of Biosciences, Ruprecht Karls University, Heidelberg, Germany; 4: National Center for Tumor Diseases, Department of Medical Oncology, Heidelberg, Germany; 5: University Medical Center Mainz, Institute for Pathology, Mainz, Germany; 6: University Medical Center Mainz, University Cancer Center (UCT), Mainz, Germany

Bad Data Detection and Signal Recovery in Large-Scale ICT-Platforms

Marcel Zimmer¹, Maximilian Büchel¹, Daniele Carta¹, Andrea Benigni^1,2,3

1: ICE-1, Institute of Climate and Energy Systems, Forschungszentrum Jülich, 52428 Jülich, Germany; 2: RWTH Aachen University, Aachen 52056, Germany; 3: JARA-Energy, Jülich 52425, Germany

System Characterization by Affine Operators in Physics-Informed Gaussian Processes

Marcel Zimmer¹, Edoardo De Din¹, Daniele Carta¹, Andrea Benigni^1,2,3

1: ICE-1, Institute of Climate and Energy Systems, Forschungszentrum Jülich, 52428 Jülich, Germany; 2: RWTH Aachen University, Aachen 52056, Germany; 3: JARA-Energy, Jülich 52425, Germany

NEOPIC: A Neural Operator Framework for Particle-based Kinetic Plasma Simulations

Sriramkrishnan Muralikrishnan¹, Chelsea John¹, Jeffrey Kelling², Paul Gibbon¹, Michael Bussmann²

1: Forschungszentrum Jülich GmbH, Germany; 2: Helmholtz Zentrum Dresden-Rossendorf, Germany

Learning PDE Dynamics from Small Data: Out-of-Distribution Generalization of Deep Learning Surrogates

Binh Duong Nguyen¹, Stefan Sandfeld^1,2

1: Institute for Advanced Simulations -- Materials Data Science and Informatics (IAS-9), Forschungszentrum Juelich GmbH, Juelich 52425, Germany; 2: Chair of Materials Data Science and Materials Informatics, Faculty 5 -- Georesources and Materials Engineering, RWTH Aachen University, Aachen 52056, Germany

Human-Explainable, Compact, Clustering-based Latents for Fast Proton Energy Spectra Estimation

Vedhas Pandit¹, Jeyhun Rustamov¹, Martin Rehwald¹, Stefan Assenbaum^1,3, Vidisha Rana¹, Hans-Peter Schlenvoigt¹, Michael Bussmann^1,2, Ulrich Schramm^1,3, Thomas Kluge¹, Jeffrey Kelling^1,4

1: Helmholtz-Zentrum Dresden-Rossendorf e.V., Germany; 2: Center for Advance Systems Understanding (CASUS), Görlitz, Saxony, Germany; 3: TUD Dresden University of Technology, 01062 Dresden, Germany; 4: Technische Universität Chemnitz, Institute of Physics, Chemnitz, Saxony, Germany

Collaborative Research Data Management for AI

René Peinl, Vincent Tischler

Hof University of Applied Sciences, Germany

From FAIR Multimodal Data Infrastructure to AI-Driven Clinical Interpretation: The MINDset Platform for Precision Psychiatry

Ravichandran Rajkumar^1,2, Syed Muhammad Ali^1,2, Edward Kempa^1,3, Markus Zimmermann^1,4, N Jon Shah^1,5, Irene Neuner^1,2,6

1: Institute of Neuroscience and Medicine 4 (INM-4), Forschungszentrum Jülich GmbH, Jülich, Germany; 2: Department of Psychiatry, Psychotherapy and Psychosomatics, University Hospital Aachen,RWTH Aachen University, Aachen, Germany; 3: Department of Computer and Information Science and Engineering, University of Florida, USA; 4: Faculty of Medical Engineering and Technomathematics, FH Aachen University Applied Sciences, Aachen, Germany; 5: Department of Neurology, RWTH Aachen University, Aachen, Germany; 6: Department of Psychiatry II, Ulm University and BKH Günzburg, Germany.

Measuring Diversity in Multi-Agent Motion Generation

Christian Schlauch^1,2, Nadja Klein¹

1: Karlsruhe Institute of Technology, Germany; 2: Aumovio SE

GEOMAGFOR - Geomagnetic Core Field Forecasting: Excursions and Polarity Reversals

Jan Simkanin¹, Martin Rother², Andre Giesecke¹, Ingo Michaelis², Monika Korte², Frank Stefani¹

1: Institute of Fluid Dynamics, Helmholtz-Zentrum Dresden-Rossendorf (HZDR), Germany; 2: Geomagnetism, GFZ Helmholtz Centre for Geosciences, Potsdam, Germany

Clinical Evidence to Individualized Care: AI Powered Clinical Decision Support Based on Predicted Individual Treatment Effect (PITE)

Pamela Solano¹, Thomas Jaki^1,2

1: Faculty for Informatics and Data Science, Regensburg University, Germany; 2: MRC Biostatistics Unit, University of Cambridge, UK

Integrating an LLM Chatbot into an Existing Web Frontend via DASF and MCP

Philipp S. Sommer, Naseem Ali, Beate Geyer, Harsh Grover, Johannes Schulz-Stellenfleth

Helmholtz-Zentrum Hereon, Germany

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

Lukas Thede^1,2,3, Stefan Winzeck¹, Zeynep Akata^3,4, Jonathan Richard Schwarz^1,5

1: Thomson Reuters Foundational Research; 2: Tübingen AI Center, University of Tübingen; 3: Helmholtz Munich; 4: MCML, Technical University of Munich; 5: Imperial College London

Patch-MLP-Based Predictive Control: Simulation of Upstream Pointing Stabilization for PHELIX Laser System

Jiaying Wang¹, Jonas Benjamin Ohland², Yen-Yu Chang³, Vedhas Pandit¹, Stefan Bock¹, Andrew-Hiroaki Okukura^4,5,6, Udo Eisenbarth², Arie Irman¹, Michael Bussmann¹, Ulrich Schramm^1,7, Jeffrey Kelling^1,8

1: Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany; 2: GSI Helmholtzzentrum für Schwerionenforschung, Darmstadt, Germany; 3: Amplitude laser group—Dresden operations, Dresden, Germany; 4: Extreme Light Infrastructure—Nuclear Physics, National Institute for Physics and Nuclear Engineering, Ilfov, Romania; 5: University of Bucharest, Ilfov, Romania; 6: Engineering and Applications of Lasers and Accelerators Doctoral School (SDIALA), National University of Science and Technology Politehnica of Bucharest, Bucharest RO-060042, Romania; 7: Technische Universität Dresden, Dresden, Germany; 8: Chemnitz University of Technology, Chemnitz, Germany

Evaluating 3D Molecular Representation Learning with Multipolar Atom Types

Jan Olszewski¹, Marta Kulik¹, Anna Gambin¹, Ewa Szczurek^1,2

1: University of Warsaw; 2: Helmholtz Munich

LIVR: Learnable Implicit Volumetric Representations for High-resolution 3D Images

Constantin Ulrich¹, Yannick Kirchhoff¹, Tak Ming Wong^2,3, Julian Moosmann², Klaus H. Maier-Hein¹

1: Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany; 2: Institute of Materials Physics, Helmholtz-Zentrum Hereon, Geesthacht, Germany; 3: Institute of Metallic Biomaterials, Helmholtz-Zentrum Hereon, Geesthacht, Germany

The AEON-UP Helmholtz AI Project - Adaptive Environmental Prediction System using Neural Processes for Urban Air Quality Prediction

Martin Otto Paul Ramacher¹, Erika von Schneidemesser², Narendran Sobanapuram Muruganandam², Paul Keil¹, Tobias Weigel¹, Volker Matthias¹

1: Helmholtz-Zentrum Hereon, Germany; 2: RIFS Forschungsinstitut für Nachhaltigkeit, Germany

SCALE.FM: Multi-Scale Foundation Models for Precision Neuroimaging

David Kügler¹, Kersten Diers¹, Santiago Estrada¹, Stephanie Kullmann², Martin Reuter¹

1: Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Bonn, Germany; 2: Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (HMGU), Munich, Germany

Machine Learning Green Functions for Magnetic Materials and Spintronics (MLGREEN)

Lokamani Lokamani¹, Adamantia Kosma², Stefan Blügel², Attila Cangi¹

1: Helmholtz-Zentrum Dresden-Rossendorf, Germany; 2: Forschungszentrum Jülich, Germany

Generative AI Framework for Steered Protein Structure Prediction via NMR Chemical Shift Inputs

Sandro Kuppel^1,2, T. Reid Alderson^1,2, Michael Heinzinger^1,2, Michael Sattler^1,2, Iva Pritišanac^1,2

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

A decentralized Swarm Learning framework for 90-Day outcome prediction for acute ischaemic stroke

Arnab Bandyopadhyay¹, Omid Shirvani¹, Jilles Vreeken², Anna Aschenbrenner¹, Joachim Schultze¹

1: DZNE, Germany; 2: CISPA, Germany