Find Academic Supervisors

• Radiopharmaceutical Sciences
• Positron Emission Tomography (PET)
• Drug Delivery Systems
• +4 more

Verena Pichler is an Assistant Professor in the Department of Pharmaceutical Sciences at the Faculty of Life Sciences. Her research focuses on radiopharmaceutical sciences, particularly in the development of PET radiotracers for neurological and oncological applications, and the environmental impact of medical imaging agents. She has pioneered work on blood-brain barrier penetration prediction using machine learning, microplastic interactions with drugs, and sustainable radiopharmaceutical practices. Key research areas include: Radiopharmaceutical design, nano/microplastic toxicology, and predictive modeling in drug delivery systems Recipient of the Förderpreis der Stadt Wien (2023) and Inorganics 2018 Best Paper Awards (2020) Her lab integrates computational methods with experimental techniques to address challenges in molecular imaging and green chemistry. Recent studies investigate the ecological implications of medical imaging waste and the development of biodegradable materials for pharmaceutical applications. Public engagement activities include media contributions on microplastic health risks and public lectures on radiopharmaceutical innovations.

• Artificial Intelligence
• Machine Learning
• Explainable Artificial Intelligence
• +3 more

Sebastian Tschiatschek is an Associate Professor at the Faculty of Computer Science, affiliated with the Research Group Data Mining and Machine Learning. His work contributes to UN Sustainable Development Goals through research in artificial intelligence, machine learning, and deep generative models. Key themes include explainable AI, forest ecology applications, and data clustering optimization. His recent publications focus on: (1) information needs for algorithmic decision-making (2025), (2) centroid-based deep clustering challenges (2024), and (3) drone-assisted forest ecology management (2024). Research spans interdisciplinary applications in environmental monitoring, stakeholder engagement, and democratic AI systems. Active projects include Interpretability and Explainability as Drivers to Democracy (2021-2025). Notable collaborations involve Austrian Computer Science Day organization (2024) and contributions to web survey methodologies (2024). His academic fingerprint includes 100% expertise in artificial intelligence, with secondary concentrations in training data, deep generative models, and forest management.

Elisabeth LexView profile

Associate Professor

• Recommender Systems
• User Modeling
• Information Retrieval
• +3 more

Assoc. Prof. Dr. Elisabeth Lex is a tenured Associate Professor at Graz University of Technology (TUG) and PI of the Recommender Systems and Social Computing Lab. She serves as Dean of Study for the master's program in Computational Social Systems. With a habilitation in Applied Computer Science, her research focuses on psychology-informed recommender systems, user modeling, and computational social science. She has published over 100 articles in venues like WebConf, HT, and RecSys, and led major projects like the trans-university 'Polarization in Public Opinion.' Education : PhD in Computer Science (2011), TU Graz Postdoc at Universidad Nacional de San Luis (Argentina) and RWTH Aachen (Germany) Research Interests : Her work integrates cognitive science principles into AI systems, addressing fairness, privacy, and transparency in recommendations. She explores how human behavior and social dynamics influence algorithmic systems, with applications in music recommendation, misinformation detection, and polarization analysis. Article Trends : Recent work emphasizes trustworthy AI, including privacy-aware recommendation systems (e.g., differential privacy), bias mitigation in music recommendations, and computational framing analysis for political narratives. She bridges technical innovation with societal impacts, such as analyzing polarization in public health policies via social media. Scientific Awards & Grants : Outstanding Paper Award (ISSI 2015) EU H2020 grants (TRIPLE, AI4EU, OpenUP) Transuniversity Research Project on Polarization (€325k funding) Advising & Labs : Supervised over 20 PhD/Master students on topics like conspiracy narratives, privacy in recommendations, and job recommendation systems. Her lab develops open-source frameworks (e.g., TagRec, AFEL-REC) and collaborates with industry partners through the Know-Center. Labs/Teams : Leads the Recommender Systems and Social Computing Lab at TUG, part of the interdisciplinary Social Computing area at the Know-Center. Collaborates with global initiatives like OpenAire and Open Knowledge Maps.

• Answer Set Programming
• Artificial Intelligence
• Cybersecurity
• +12 more

Prof. Martin Gebser is a University Professor and Deputy Director at the Institute for Artificial Intelligence and Cybersecurity, University of Klagenfurt. His work bridges theoretical advancements in Answer Set Programming (ASP) with practical applications in industrial scheduling, semiconductor manufacturing, and explainable AI systems. Institute for Artificial Intelligence and Cybersecurity, University of Klagenfurt His research focuses on Answer Set Programming and its extensions for complex scheduling problems, particularly in semiconductor production. Key areas include: Multi-shot ASP solving for job-shop decomposition Hybrid AI systems integrating reinforcement learning and logic programming Explainable AI for battery health monitoring and semiconductor dispatching Recent publications emphasize temporal planning, constraint learning, and real-world data integration. He has developed customizable simulators and optimization frameworks for industrial applications.

Friedrich LeischView profile

Professor

• Statistical Computing
• Cluster Analysis
• Bioprocess Modeling
• +3 more

Friedrich Leisch was a Professor at the Institute of Statistics, University of Natural Resources and Life Sciences, Vienna. He held leadership positions including Head of the Department of Landscape, Spatial and Infrastructure Sciences and was a core developer for the R programming language. His career included positions at Ludwig-Maximilians-Universität München and Vienna University of Technology, where he earned his doctorate and habilitation. Education includes: PhD in Applied Mathematics, Vienna University of Technology (1999) Habilitation in Statistics, Vienna University of Technology (2005) Leisch's research focused on statistical computing methodologies with applications across diverse scientific domains. His primary interests included: Development of resampling methods for cluster analysis and validation Bioprocess modeling for pharmaceutical manufacturing Causal modeling frameworks for scientific inference Statistical computing and R package development His recent publications demonstrate a strong focus on biotechnological applications of statistical learning, developing methods for real-time process monitoring in pharmaceutical production. Articles frequently address machine learning explainability, temporal clustering, and environmental impact assessment of agricultural practices. Scientific awards include: Peter Keller Award for tourism research Supervised numerous doctoral and master's students across statistics and biotechnology domains. Led multiple research projects including: Mobile Field Phenotyping for Agronomy and Breeding Statistical evaluation of downstream processing data Market Segmentation Methodology projects Collaborated extensively with bioprocessing research groups including the Austrian Centre of Industrial Biotechnology (ACIB), focusing on statistical modeling of fermentation processes and purification systems.

Alexander KovacsView profile

Researcher

• Materials Science
• Magnetism
• Machine Learning Applications
• +3 more

Dr. Alexander Kovacs is a researcher at the Center for Modelling and Simulation at the University for Continuing Education Krems. His work focuses on advancing computational and experimental methods in magnetism, particularly leveraging machine learning and micromagnetic simulations. Key areas include optimizing permanent magnets, studying magnetic materials' microstructure, and developing physics-informed models for material design. Research Interests: Kovacs specializes in materials informatics, micromagnetic simulations, and machine learning applications in magnetism. His projects emphasize reducing critical elements in permanent magnets, improving coercivity through defect manipulation, and integrating sensor data for real-time magnetic field control. His interdisciplinary approach bridges computational methods with experimental validations, contributing to sustainable materials innovation. Publications and Talks: His recent studies highlight the use of deep learning for predicting hysteresis properties and optimizing magnet designs. He frequently presents at conferences like HMM, IEEE Magnetics, and JEMS, discussing topics such as magnetization reversal mechanisms and machine learning-driven optimization frameworks. His work addresses challenges in energy-efficient magnet design and advanced material discovery. Labs/Teams: As part of the Center for Modelling and Simulation, Kovacs collaborates on projects requiring high-performance computing and interdisciplinary research, contributing to the development of novel magnetic materials and computational tools.

• Medical Informatics
• Healthcare Analytics
• Machine Learning in Healthcare
• +3 more

Gerhard Halmerbauer is a Researcher at the Medical Engineering/TIMed Center of Steyr University of Applied Sciences. He leads research in applying machine learning to optimize clinical processes, focusing on postoperative care and healthcare quality improvement. His work integrates AI models to predict patient outcomes and streamline medical decision-making. Research interests include healthcare analytics, medical informatics, and the application of machine learning in clinical settings. His projects emphasize predictive modeling for postoperative stay durations, complication detection, and benchmarking surgical outcomes. Key contributions include developing AI-driven systems to reduce postoperative complication identification time and enhancing transparency in healthcare quality metrics. Halmerbauer has collaborated with institutions on benchmarking systems for surgical departments and has presented at conferences like ISQua and EUROCAST. He has supervised 5 academic works and led two research projects (2011-2013 and 2021-2022), serving as Principal Investigator (PI) to advance medical engineering solutions.

• Ionic Liquid Chemistry
• Solvation Chemistry
• Computational Chemistry
• +5 more

Christian Schröder is a University Professor in the Faculty of Chemistry at the Department of Computational Biological Chemistry. With over 100 publications spanning from 2005 to the present, his research has significantly contributed to computational chemistry, molecular simulations, and physical chemistry, particularly in the areas of ionic liquids and solvation phenomena. Dr. Schröder's research program demonstrates exceptional depth in ionic liquid chemistry , where he investigates solvation properties, polarizability effects, and fundamental molecular behavior. His pioneering work on polarizable force fields has advanced computational methodology by incorporating electronic polarization effects that traditional models neglect. More recently, he has expanded his research to include machine learning applications for predicting blood-brain barrier penetration in drug discovery, bridging computational chemistry with pharmaceutical sciences. His fingerprint analysis reveals expertise in Ionic Liquid Chemistry (100%), Solvation Chemistry (38%), and 1-Ethyl-3-Methylimidazolium Chemistry (24%). An analysis of Dr. Schröder's publication trends shows a clear evolution from fundamental studies of ionic liquid properties toward increasingly interdisciplinary applications. The most recent publications demonstrate integration of computational chemistry with machine learning and pharmaceutical research, while maintaining strong foundations in physical chemistry principles. His work consistently addresses complex problems requiring sophisticated computational approaches and molecular-level understanding. Among his professional recognitions, Dr. Schröder received the Preis für gute Lehre 2022 (Teaching Award 2022) on April 27, 2023, highlighting his excellence in academic instruction alongside his research achievements. Dr. Schröder has supervised numerous students and early-career researchers, with Christian Fellinger appearing as a frequent collaborator on recent projects including GRADE-ing Protein-Ligand Interactions and Blood-Brain Barrier Penetration Prediction. His research has been supported by multiple substantial projects including Proton transfer in protic ionic liquids (2020-2023), Ionenaggreg. von chir.ion.Flüss (2017-2021), and Simulationsanalyse zur Solventd (2015-2018), demonstrating sustained funding success across diverse research areas. He maintains an active research group focused on computational chemistry methods development and their application to challenging problems in physical chemistry and pharmaceutical sciences. His collaborative network spans multiple disciplines, with recent activities showing strong connections between computational chemistry, toxicology, and cancer research, particularly through collaborations with researchers studying xenoestrogens and breast cancer cell behavior.

• Cultural Heritage
• Document Analysis
• Medical Data Analysis
• +5 more

Florian Kleber is a senior scientist at the Computer Vision Lab within the Institute of Visual Computing and Human-Centered Technology at Vienna University of Technology (TU Wien), Austria. His research spans two primary domains: document analysis for cultural heritage preservation and medical data analysis. He has been actively involved in lecturing at TU Wien, particularly in Document Analysis courses, and has served as a substitute member of the Curriculum Commission for Informatics. Dr. Kleber's research focuses on the intersection of computer vision and practical applications. His work in cultural heritage includes multi-spectral acquisition and restoration of ancient manuscripts, development of tools for historical document analysis, and work on writer identification and retrieval systems. In medical data analysis, he has specialized in flow cytometry analysis, particularly for minimal residual disease assessment in acute lymphoblastic leukemia. His research demonstrates a consistent pattern of applying advanced computer vision techniques to solve domain-specific challenges in both humanities and medical fields. His recent publications reveal a strong trend toward synthetic data generation for training document analysis systems, self-supervised learning approaches for writer retrieval, and explainable AI techniques for medical data analysis. The publications show increasing sophistication in transformer-based architectures applied to both document analysis and medical imaging domains. His work bridges theoretical computer vision advances with practical applications in cultural heritage institutions and medical settings. Dr. Kleber has supervised multiple diploma theses at TU Wien, including work on automated analysis of herbarium collections, transparency techniques for neural networks, synthetic data for document analysis, and physical layout analysis of newspaper images. He has been involved in numerous research projects including the Vienna City Library poster collection analysis, digitization of museum holdings in Lower Austria, and the AutoFlow project for medical data analysis. His laboratory work centers around the Computer Vision Lab (E193-01) at TU Wien, where he collaborates on projects involving document image analysis, cultural heritage preservation, and medical data processing. His team has developed tools for manuscript analysis, document reconstruction, and flow cytometry data interpretation, often in collaboration with cultural institutions and medical facilities.

• Computer Science Education
• K-12 Computing Education
• Machine Learning Education
• +4 more

Martina Landman is a PreDoc Researcher at the Department of Software Engineering within the Faculty of Informatics at Technische Universität Wien . She actively contributes to K-12 Computing Education through innovative teaching methods and outreach programs.

• Artificial Intelligence
• Explainable AI
• Logic
• +5 more

Xinghan Liu is a PostDoc Researcher at the Knowledge-Based Systems group within Vienna University of Technology. Their work bridges Artificial Intelligence , Logic , and Environmental Engineering , as evidenced by their publications in both computer science and hydrology journals. Contact: xinghan.liu@tuwien.ac.at . Research Interests: Explainable AI and logic-based classifier modeling Counterfactual and intuitionistic conditional logics Legal case-based reasoning in computational frameworks Hydrodynamic and environmental adaptation to infrastructure projects Recent Work Trends: Recent articles focus on classifiers (2021–2024), explainable AI (2023–2024), and legal reasoning (2022–2023). A 2023 hydrology publication highlights interdisciplinary research on river systems affected by damming.

• Machine Learning
• Computational Linguistics
• Natural Language Processing
• +3 more

Bayar Ilhan Menzat is a PostDoc Researcher at the Department of Artificial Intelligence Techniques, Vienna University of Technology (TU Wien). His work focuses on bridging machine learning, natural language processing, and clinical decision-support systems, emphasizing explainability and human-AI collaboration. Research Interests Menzat’s research explores the intersection of artificial intelligence and healthcare, with a focus on multimodal explanations for clinical applications. He also investigates neuroscience-inspired AI frameworks, as seen in his teaching of 'Neuroscience-based Artificial Intelligence' seminars. Publications & Awards In 2024, he co-authored a paper on contrasting textual and visual explanations in clinical decision-support systems at the EMNLP conference, earning the Outstanding Paper Award. His recent work highlights explainable AI, trust calibration, and cross-modal reasoning in medical contexts. Scientific Recognition Outstanding Paper Award at EMNLP 2024 for contributions to clinical AI explainability

• Data Management
• Reproducibility in Science
• Semantic Web Technologies
• +3 more

Dr. Tomasz Miksa is a Senior Scientist at TU Wien's Department of Data Science, specializing in machine-actionable data management plans (maDMPs), reproducibility frameworks, and data stewardship. His work bridges semantic web technologies, automated workflows, and interdisciplinary data governance. He leads projects like OS Trails (2024–2027) and FAIR-AI , focusing on synchronizing research data services and ensuring FAIR (Findable, Accessible, Interoperable, Reusable) principles. Miksa holds a PhD in Computer Science from TU Wien (2016) and has supervised numerous theses on topics like reproducible query processing and DMP integration. He actively contributes to initiatives such as FAIR Data Austria and openEO API standardization, emphasizing sustainable data practices across disciplines. Research interests include semantic representation of DMPs, automated validation tools, and frameworks for auditable privacy-preserving data analysis. His work on data citation mechanisms and evolving database schemas ensures long-term reproducibility in fields like environmental science and earth observation. Miksa collaborates internationally, co-editing special collections on data management planning and publishing in journals like ACM Transactions on Management Information Systems and IEEE eScience . Key contributions include the DCSO ontology for DMPs, the WellFort platform for privacy-aware data analysis, and frameworks for identifying software dependencies in biomedical workflows. His teaching focuses on data stewardship, with courses like Data Stewardship VO/UE addressing national and institutional strategies. Ongoing efforts aim to integrate machine-actionable DMPs with institutional repositories and cloud-based research infrastructures.

Maath MuslehView profile

Researcher

• Visual Analytics
• Medical Visualization
• Uncertainty Visualization
• +3 more

Maath Musleh is a Researcher and PhD candidate at the Vienna University of Technology (TU Wien), affiliated with the Faculty of Informatics and the Department of Computer Graphics. His academic roles include serving as a University Assistant and teaching courses such as Methods for Data Generation and Analytics in Medicine and Information Visualization . He holds a BSc and MSc, with his Master’s thesis focusing on industrial multivariate time series analysis. Research interests center on Visual Analytics , Medical Visualization , and Uncertainty Visualization , with applications in healthcare, manufacturing, and agriculture. His work emphasizes explainable AI, user confidence measurement, and decision-support systems. Notable contributions include the TrustME model for explainable guidance and the ConAn framework for quantifying user confidence in uncertain analysis scenarios. Key achievements include the Best Short Paper Award at VINCI 2021 for industrial time-series visualization research. His ongoing PhD, supervised by Prof. Renata Raidou, explores Guided Visual Analytics for Decision-Making under Uncertainty . He collaborates on projects like Agritology , a multilingual decision-support system for farmers, and has developed dashboards for industrial and medical data analysis. Maath’s interdisciplinary approach integrates visualization, machine learning, and human-centered design to address challenges in complex decision-making environments.

• Natural Language Processing
• Computational Linguistics
• Information Extraction
• +3 more

Gábor Recski is a computational linguist and postdoctoral researcher at TU Wien's Faculty of Informatics, affiliated with the Data Science Research Unit. He holds a PhD and previously served as an assistant professor at the Budapest University of Technology. His research focuses on natural language processing (NLP), particularly computational semantics and transparent information extraction. He teaches courses such as Natural Language Processing and Information Extraction, and supervises students at BSc, MSc, and PhD levels. His work includes over 50 peer-reviewed publications and projects like BRISE-Vienna (2019–2025) and Honeypot LLM: Creation of a Scam Conversation Dataset. Roles: PostDoc Researcher, Substitute Member of Faculty Council, Substitute Member of Curriculum Commission for Business Informatics Education: PhD (previous role at Budapest University of Technology) Research Interests: Transparent information extraction, semantic modeling, legal text analysis, and explainable AI His research projects span legal corpus construction (e.g., BRISE-plandok), offensive text detection, and AI applications in legal research. He actively contributes to conferences like ACL, EMNLP, and SIGIR. Supervised students have explored topics ranging from explainable prediction models to graph-based relation extraction.