@inproceedings{6898, abstract = {The labeling process for supervised learning is costly and time-consuming, and is often impractical to scale due to real-world constraints. Active learning (AL) addresses this challenge by strategically selecting representative and informative data points to reduce labeling efforts. This paper focuses on an AL scenario in which only a very limited number of labels can be acquired. We propose an algorithm operating in two phases: (1) an exploration phase that prioritizes representative and diverse data points using density-driven criteria, and (2) an exploitation phase that combines predictive uncertainty with density weighting to select informative samples from densely populated regions. This enhances both representativeness and informativeness. Our results demonstrate significant improvements in model quality compared to other algorithms typically employed for this scenario, across various scenarios involving imbalanced data in classification tasks and skewness in regression tasks. Through this work, we aim to provide a new algorithm for this scenario and investigate general principles for AL. While most AL studies focus on either classification or regression, our work applies the algorithms to both. Therefore, we can analyze the differences between classification and regression problems and their effects on AL strategies. Furthermore, we explore different categories of AL criteria and their effectiveness in the low-budget regime. These results also provide insight into the cold-start problem, which involves selecting an initial labeled set and is faced by many model-based AL methods.}, author = {Jaster, Bjarne and Tharwat, Alaa and Sheikh, Eiram Mahera and Kohlhase, Martin and Schenck, Wolfram}, booktitle = {Machine Learning and Principles and Practice of Knowledge Discovery in Databases. International Workshops of ECML PKDD 2025, Porto, Portugal, September 15–19, 2025, Revised Selected Papers, Part IV}, editor = {Koprinska, Irena and Mendes-Moreira, João and Branco, Paula}, isbn = {978-3-032-19104-5}, issn = {1865-0937}, location = {Porto, Portugal}, pages = {5--21}, publisher = {Springer Nature Switzerland}, title = {{Low Query Budget Active Learning for Classification and Regression}}, doi = {10.1007/978-3-032-19105-2_1}, year = {2026}, } @article{6655, author = {Tharwat, Alaa and Jaster, Bjarne and Schenck, Wolfram and Kohlhase, Martin}, issn = {09521976}, journal = {Engineering Applications of Artificial Intelligence}, publisher = {Elsevier BV}, title = {{Active learning evaluation metrics for classification and regression frameworks}}, doi = {10.1016/j.engappai.2026.114295}, volume = {171}, year = {2026}, } @inproceedings{6904, abstract = {Der Berufsstand der Wirtschaftsprüfer und das Rechnungswesen von Unternehmen kämpfen aktuell mit einem sinkenden Image sowie einem massiven Fachkräftemangel. Als zentrale Antwort darauf gilt die fortschreitende Digitalisierung und der Einsatz von KI, die bereits heute zu einer weitgehenden Automatisierung operativer Kernprozesse wie dem „Purchase-to-Pay“-Porzess führen. Während das Institut für Arbeitsmarkt- und Berufsforschung (IAB) für Buchhaltungstätigkeiten ein Automatisierungspotenzial von 100 % sieht, liegt dieses in der Wirtschaftsprüfung bei etwa 57 %. In der Prüfungspraxis verschiebt sich der Fokus von Routineaufgaben hin zu risikoorientierten Datenanalysen, IT-Systemprüfungen und der Nachhaltigkeitsberichterstattung, wobei das finale Urteil weiterhin beim Menschen verbleibt („Human-in-the-Loop“). Für die Hochschulausbildung bedeutet diese Transformation, dass neben den klassischen Basiskompetenzen vermehrt Spezialwissen in der Datenanalyse sowie übergreifende Meta-Kompetenzen wie „Data Literacy“ und grundlegendes KI-Verständnis vermittelt werden müssen. Hochschulen sind daher gefordert, diesen Wandel durch neue Lehrformate und Kooperationen mit der Praxis aktiv mitzugestalten, um den steigenden qualitativen Anforderungen an künftige Mitarbeitende gerecht zu werden.}, author = {Kampe, Tim}, booktitle = {46. Tagung des Arbeitskreises „Steuern und Wirtschaftsprüfung“ der Professorinnen und Professoren an Hochschulen für angewandte Wissenschaften, Bad Mergentheim, 11.-13.05.}, keywords = {Wirtschaftsprüfung, Rechnungswesen, Künstliche Intelligenz, Fachkräftemangel, Hochschullehre, Data Literacy, Automatisierung}, location = {Bad Mergentheim}, title = {{Digitalisierung und KI in der Abschlussprüfung: Änderungen in Rechnungslegung und Wirtschaftsprüfung und ihre Auswirkungen auf die Hochschulausbildung}}, year = {2026}, } @inproceedings{6797, author = {Schipper, Lennart and Schwede, Christian}, booktitle = {Simulation in Produktion und Logistik 2025}, editor = {Rank , Sebastian and Kühn , Mathias and Schmidt, Thorsten }, isbn = {978-3-86780-806-4}, location = {Dresden}, publisher = {Technische Universität Dresden, Professur für Technische Logistik }, title = {{Automated Adaptation of Digital Twins for Production Line Design by Adapting Existing Models Through LLM-Guided Expert Interviews}}, doi = {10.25368/2025.247}, year = {2025}, } @inproceedings{6796, author = {Farwick, Patrick and Schwede, Christian}, booktitle = {2025 Winter Simulation Conference (WSC)}, location = {Seattle, WA, USA}, pages = {1466--1477}, publisher = {IEEE}, title = {{Reinforcement Learning in Production Planning and Control: a Review on State, Action and Reward Design in Order Release and Production Scheduling}}, doi = {10.1109/WSC68292.2025.11338874}, year = {2025}, } @book{6439, author = {Köhler, Gerhard and Roth, Werner and Schmidtmann, Achim}, isbn = {978-3-658-49725-5}, issn = {2192-810X}, publisher = {Springer Nature}, title = {{Adaptive IT Service Tendering. The Path to Agile and Effective IT Outsourcing}}, doi = {10.1007/978-3-658-49726-2}, year = {2025}, } @inbook{6349, author = {Schmidtmann, Achim and Babić, Marina and Chlopek-Duljević, Sonia Anna and Kunasegaram, Theepika}, booktitle = {Disrupt or Be Disrupted: How does AI shape the Future of Business and Politics?}, editor = {Öztürk, Riza and Auschner, Eika}, location = {Bielefeld}, pages = {32}, publisher = {Shaker Verlag}, title = {{Artificial Intelligence in Recruiting: A Balancing Act Between Innovation and Ethics}}, year = {2025}, } @inproceedings{5972, author = {Döring, Lina and Trojahn, Sebastian and Reusch, Pascal}, booktitle = {18th International Doctoral Students Workshop on Logistics, Supply Chain and Production Management}, keywords = {Digital Twin, Small and medium sized companies, SME, production optimization}, location = {Magdeburg}, publisher = {Otto von Guericke University Library, Magdeburg, Germany}, title = {{Partial Twin – Pragmatic Digital Twin Adoption for SMEs}}, doi = {10.57720/5972}, volume = {18}, year = {2025}, } @inproceedings{6037, author = {Döring, Lina and Trojahn, Sebastian and Reusch, Pascal}, booktitle = {18th International Doctoral Students Workshop on Logistics, Supply Chain and Production Management}, keywords = {Digital Twin, Small and medium sized companies, SME, production optimization}, location = {Magdeburg}, publisher = {Otto von Guericke University Library, Magdeburg, Germany}, title = {{Partial Twin – Pragmatic Digital Twin Adoption for SMEs}}, doi = {10.57720/6037}, volume = {18}, year = {2025}, } @article{5871, author = {Beese, Nils O. and Dümke, Lennart and Döll, Yannic N. and Reinhard, René and Spilski, Jan and Lachmann, Thomas and Müller, Kerstin}, issn = {1362-3001}, journal = {Behaviour & Information Technology}, number = {6}, pages = {1124--1135 }, publisher = {Informa UK Limited}, title = {{Feel me, hear me: vibrotactile and auditory feedback cues in an invisible object search in virtual reality}}, doi = {10.1080/0144929X.2025.2459248}, volume = {44}, year = {2025}, } @inproceedings{5775, author = {Behrens, Grit and Ribouh, Yassine and El Atmioui, Naoufal and Kruse, Alexander}, location = {Thessaloniki }, title = {{Cloud Classification and Solar Irradiance Forecasting Using All-Sky Images and based on Machine Learning Techniques }}, year = {2025}, } @inproceedings{5774, author = {Behrens, Grit and Ribouh, Yassine and El Atmioui, Naoufal}, location = {Rosenheim}, title = {{Cloud Classification and Solar Irradiance Forecasting Using All-Sky Images}}, year = {2025}, } @inproceedings{5772, author = {Behrens, Grit and Marten, Daniel and Koch, Levent and Gaj, Marcel}, booktitle = {Umweltinformationssysteme - Digitalisierung für eine nachhaltige Planetare Zukunft/ Tagungsband des 31. Workshops "Umweltinformationssysteme (UIS 2024)" der Fachgruppe "Umweltinformationssysteme" der Gesellschaft für Informatik (GI)}, editor = {Fuchs-Kittkowski, Frank and Abecker, Andreas and Hosenfeld, Friedhelm and Reineke, Anja and Möller, Matthias}, isbn = {978-3-658-46393-9}, location = {Uni Bamberg}, publisher = {Springer Fachmedien Wiesbaden; Springer Vieweg }, title = {{Prognose von Pegelständen mit Methoden des Maschinellen Lernens und frei verfügbaren Daten}}, year = {2025}, } @inproceedings{6449, author = {Casella, Francesco and Bachmann, Bernhard and Abdelhak, Karim and Hannebohm, Philip and Van der Stelt, Teus}, booktitle = {Proceedings of the 16th International Modelica&FMI Conference, September 8 – 10, 2025, Lucerne University of Applied Sciences and Arts (HSLU)}, publisher = {Linköping University Electronic Press}, title = {{Diagnosing Newton’s Solver Convergence Failures in the Initialization of Modelica Models}}, doi = {10.3384/ecp218109}, volume = {218}, year = {2025}, } @inproceedings{6446, author = {Abdelhak, Karim and Bachmann, Bernhard}, booktitle = {Proceedings of the 16th International Modelica&FMI Conference, September 8 – 10, 2025, Lucerne University of Applied Sciences and Arts (HSLU)}, publisher = {Linköping University Electronic Press}, title = {{Constant Time Causalization using Resizable Arrays}}, doi = {10.3384/ecp218203}, volume = {218}, year = {2025}, } @article{6445, author = {Bachmann, Bernhard and Bonaventura, Luca and Casella, Francesco and Fernández-García, Soledad and Gómez-Mármol, Macarena and Hannebohm, Philip}, issn = {1573-7691}, journal = {Journal of Scientific Computing}, number = {1}, publisher = {Springer Science and Business Media LLC}, title = {{Self-Adjusting Multi-Rate Runge-Kutta Methods: Analysis and Efficient Implementation in An Open Source Framework}}, doi = {10.1007/s10915-025-03049-y}, volume = {105}, year = {2025}, } @inproceedings{6361, author = {Langenkamp, Linus and Bachmann, Bernhard}, booktitle = {Proceedings of the 16th International Modelica&FMI Conference}, editor = {Zimmer, Dirk and Müller, Ulf Christian}, keywords = {Dynamic Optimization, Direct Collocation, Adaptive Mesh Refinement, Nonlinear Programming}, location = {Luzern}, pages = {127 -- 138}, publisher = {Linköping University Electronic Press}, title = {{Enhancing Collocation-Based Dynamic Optimization through Adaptive Mesh Refinement}}, doi = {10.3384/ecp218127}, volume = {218}, year = {2025}, } @inproceedings{6359, author = {Langenkamp, Linus and Hannebohm, Philip and Bachmann, Bernhard}, booktitle = {Proceedings of the 16th International Modelica&FMI Conference}, editor = {Zimmer, Dirk and Müller, Ulf Christian}, keywords = {Physics-enhanced Neural ODEs, Dynamic Optimization, Nonlinear Programming, Modelica, NeuralODEs, Universal Differential Equations}, location = {Luzern}, pages = {445 -- 457}, publisher = {Linköping University Electronic Press}, title = {{Efficient Training of Physics-enhanced Neural ODEs via Direct Collocation and Nonlinear Programming}}, doi = {10.3384/ecp218445}, volume = {218}, year = {2025}, } @unpublished{6448, author = {Brandt, Felix and Heuermann, Andreas and Hannebohm, Philip and Bachmann, Bernhard}, booktitle = {arXiv:2510.09317}, title = {{Residual-Informed Learning of Solutions to Algebraic Loops}}, year = {2025}, } @inproceedings{6357, author = {Hannebohm, Philip and Bachmann, Bernhard}, booktitle = {Proceedings of the 16th International Modelica&FMI Conference}, editor = {Zimmer, Dirk and Müller, Ulf Christian}, keywords = {Equation-based modelling, Multi-rate simulation, Structural analysis}, location = {Lucerne}, pages = {943–947}, publisher = {Linköping University Electronic Press}, title = {{Selective Evaluation of RHS during Multi-Rate Simulation}}, doi = {10.3384/ecp218943}, volume = {218}, year = {2025}, }