Find Academic Supervisors

Ya ChenView profile

Researcher

• Virtual Screening
• Drug Discovery
• Cheminformatics
• +3 more

Ya Chen is affiliated with the Department of Pharmaceutical Sciences at the Faculty of Life Sciences. Their research focuses on computational approaches in drug discovery, including virtual screening, metabolic pathway analysis, and machine learning applications. Key areas include natural product-based drug design, receptor modulation, and enzyme inhibition mechanisms. Notable contributions involve developing predictive models for drug metabolism and exploring chemical spaces for therapeutic targets like the glucocorticoid receptor. Ya Chen has presented work at international conferences and contributed to interdisciplinary projects combining cheminformatics and biological systems. Research interests emphasize the intersection of artificial intelligence with pharmaceutical sciences, particularly in optimizing drug design workflows and understanding metabolic processes. Their work spans enzyme inhibition studies (e.g., CYP19A1, InsP3Kinase), nuclear receptor ligand discovery (RORγ, LXR), and the development of open-source tools for cheminformatics (e.g., Scikit-Mol). Collaborative efforts involve international teams and focus on advancing methodologies for natural product screening, site-of-metabolism prediction, and chemical library design. Ya Chen’s activities highlight a commitment to bridging computational techniques with experimental pharmacology to address challenges in drug development and toxicology.

• Machine Learning
• Computational Neuroscience
• Data Mining
• +3 more

Lena Bauer is a researcher affiliated with the Faculty of Computer Science at the University of Vienna, specifically within the Research Group Data Mining and Machine Learning . Her work bridges computational methods with neuroscience, focusing on applications in mental health. She holds degrees including DI Dr.techn. (PhD in Technical Sciences) and BSc. Research Interests: Bauer’s research integrates machine learning and data mining techniques to analyze complex biological systems, particularly brain networks. She explores multimodal data integration, clustering algorithms, and their application to neuroimaging (e.g., fMRI) for understanding disorders like Major Depressive Disorder. Key themes include quantifying neural synchronization, developing autoencoder-based models, and improving clustering methodologies. Collaborations: Bauer collaborates internationally on projects involving computational neuroscience and mental health. Recent activities include presenting work on Kuramoto model applications to fMRI data at conferences. Labs & Teams: She contributes to the University of Vienna’s Data Mining Group, which focuses on clustering, causality analysis, and big data applications.

Andreas FutschikView profile

Professor

• Applied Statistics
• Biostatistics
• Statistical Inference in High Dimensional Settings
• +2 more

Univ.-Prof. Dr. Andreas Futschik serves as Head of the Department and Head of the Division of Data Analysis and Econometrics at the Institute of Applied Statistics, Johannes Kepler University Linz, Austria. His academic leadership spans both administrative roles and active research contributions across multiple statistical disciplines. His institutional affiliations include the Kurt Rothschild School of Economics and Statistics (RoSES) where he maintains a prominent research and teaching presence. Professor Futschik's research focuses on Applied Statistics, Biostatistics, and Statistical Inference in High Dimensional Settings , with particular expertise in genomic statistics and population genetics. His work bridges theoretical statistical methodology with practical applications in biological and agricultural sciences. He has developed innovative approaches for analyzing complex genetic data, including methods for genomic selection, haplotype estimation, and detection of natural selection in population genetic data. His research demonstrates a consistent pattern of applying advanced statistical techniques to solve real-world problems in genomics and veterinary science. The analysis of his recent publications reveals a strong emphasis on methodological innovation in statistical genetics , particularly in genomic prediction models and population genetic inference. His work frequently employs Bayesian frameworks, time series analysis, and high-dimensional statistical techniques to address challenges in genomic data analysis. The interdisciplinary nature of his research connects statistics with evolutionary biology, veterinary medicine, and agricultural science, demonstrating the versatility of modern statistical approaches. Professor Futschik maintains active research collaborations through multiple ongoing projects including 'Statistische Modellierung zur Kartellschadensberechnung' (2023-2027), 'Statistical Literacy' (2019-2025), and 'Statistical Inference in Complex Situations' (2014-2025). His research group contributes significantly to both theoretical statistical development and practical applications across diverse scientific domains. He regularly presents at international conferences, with recent talks covering phase-type distributions in population genetics and statistical inference for time series allele frequency data.

Narly GolestaniView profile

Associate Professor

• Brain and Language Processing
• Auditory Cortex Anatomy
• Multilingualism and Language Control
• +7 more

Narly Golestani is Associate Professor at the Vienna Cognitive Science Hub and at the Department of Behavioral and Cognitive Biology at the Faculty of Life Sciences, University of Vienna. She simultaneously holds an Associate Professor position at the University of Geneva's Department of Psychology, where she has been affiliated since April 2018. She heads the Brain and Language Lab, which operates across both institutions. Dr. Golestani earned her PhD in Clinical Psychology from McGill University (Montreal, Canada), followed by post-doctoral work at INSERM (Orsay, France) and the Institute for Cognitive Neuroscience at UCL (London, UK). Her research focuses on understanding the neural mechanisms underlying language processing across multiple levels, from auditory and phonetic processing to multilingualism and language control. Her methodological approach integrates: Functional and structural neuroimaging Computational modeling of brain function Computational morphometry Machine learning techniques Advanced statistical procedures Neuropsychological assessments Experimental psycholinguistics Psychophysics methods Dr. Golestani's primary research themes include: Auditory cortex anatomy and its relationships with auditory, language, and music processing Multilingualism and language control mechanisms in the brain Language aptitude and individual differences in language learning Computational modeling approaches for understanding language processing at different levels Her significant research initiatives include the Evolving Language NCCR-funded work package on 'Aptitude' and the 'ProsodyToMeaning' project. Her work contributes to Sustainable Development Goals related to quality education and reduced inequalities. Dr. Golestani has presented her research internationally at institutions including the Basque Center on Cognition, Brain and Language, St Jude Research Hospital, and the University of Reading. Dr. Golestani teaches advanced seminars on Clinical Psychology, Speech and Language Pathology, Bilingualism, and The Neuroscience of Language at both undergraduate and graduate levels. Her teaching emphasizes the intersection of cognitive science, neuroscience, and language processing, with courses including 'Speech and Language Pathology,' 'Bilingualism: Neural bases and Socio-cognitive aspects,' and 'The Neuroscience of Language.'

Christoph FlammView profile

Researcher

• Theoretical Chemistry
• RNA Folding Kinetics
• Chemical Graph Theory
• +5 more

Christoph Flamm is a researcher in the Department of Theoretical Chemistry at the Faculty of Chemistry, University of Vienna. His work spans theoretical chemistry, bioinformatics, and computational biology with a particular focus on RNA structure prediction, chemical graph theory, and reaction network analysis. He maintains an active research profile with numerous publications in high-impact journals and has been involved in several collaborative research projects. Flamm's research interests include RNA folding kinetics, chemical graph rewriting, barrier trees, discrete landscapes, and systems chemistry. His work bridges theoretical approaches with practical applications in biochemistry and molecular biology, particularly focusing on the computational aspects of chemical and biological systems. He has made significant contributions to RNA secondary structure prediction algorithms and the theoretical foundations of chemical reaction networks. His publication record demonstrates consistent output across multiple disciplines, with recent work focusing on graph-based approaches to chemical reaction networks, RNA folding kinetics using machine learning techniques, and theoretical frameworks for chemical systems. The research shows a clear trajectory from fundamental theoretical work on RNA folding landscapes to more recent applications involving graph theory, hypergraphs, and computational approaches to chemical systems. Flamm has been actively involved in teaching activities related to theoretical chemistry and computational methods, as indicated by his website's teaching section. While specific grant information isn't detailed in the provided content, his extensive publication record suggests successful funding of research projects. His work appears to be conducted within the Theoretical Biochemistry group at the University of Vienna, collaborating with researchers in bioinformatics, chemistry, and computer science.

Emmanouil KarystinaiosView profile

Researcher

• Artificial Intelligence
• Music Information Retrieval
• Graph Neural Networks
• +3 more

Emmanouil Karystinaios is a Post-Doctoral Researcher at the Institute of Computational Perception, Johannes Kepler University Linz, Austria, and holds concurrent Lecturer roles at Kunstuniversität Linz and Universität für Musik und darstellende Kunst Wien. His research focuses on AI applications in music, particularly leveraging graph neural networks (GNNs) for symbolic music analysis, optical music recognition, and generative music medicine. He leads projects such as GraphMuse, a Python library for symbolic music graph processing, and SMUG-Explain, an explainability framework for music data. Education includes a PhD in Computational Perception (JKU Linz, ongoing since 2020), MSc in Mathematical Logic (Université Paris Diderot), and MA in Musical Programming/Composition (Université Paris Vincennes). His work bridges computational methods with music theory, emphasizing explainable AI and music perception tasks. Recent publications highlight contributions to voice separation via GNNs, score engraving optimization, and music medicine using language models. His research also addresses expressive performance evaluation and symbolic music representation challenges, with applications in automated accompaniment systems like the ACCompanion.

Raphaël TinarrageView profile

Research Fellow

• Topological Data Analysis
• Combinatorial Topology
• Medical Image Analysis
• +3 more

Raphaël Tinarrage is a Research Fellow at the Institute of Science and Technology Austria (ISTA), part of the Wagner group. Previously, he held a postdoctoral position at FGV EMAp (Brazil) and was an Assistant Professor at Université Paris-Saclay (2017–2020). His research focuses on Topological Data Analysis (TDA), including theoretical advancements and practical applications in medical imaging, legal document analysis, and equivariant neural networks. Education: He earned his PhD from Université Paris-Saclay and Inria, advised by Fred Chazal and Marc Glisse (2017–2020). His dissertation, Topological Inference from Measures and Vector Bundles , introduced novel methods for topological data analysis. Research Interests: Tinarrage explores topological inference (e.g., stability of persistent homology), combinatorial topology (triangulation, Lusternik–Schnirelmann category), and applications like medical image segmentation and legal text analysis. His work bridges theoretical mathematics with computational tools, emphasizing practical implementations. Key Publications (2021–2025): Recent articles include LieDetect (2025) for Lie group symmetry detection, Empirical Analysis of Brazilian Supreme Court Precedents (2025), and ZigzagNetVis (2025) for dynamic graph visualization. Preprints include Train-Free Segmentation in MRI (2024). Teaching & Advising: He taught courses on topology and TDA at FGV EMAp and Université Paris-Saclay. He advised multiple students on projects involving legal NLP and TDA applications. Labs & Tools: His PhD work is implemented in the velour Python package. Code for other projects is available on his GitHub repository.

• Operations Research
• Logistics and Supply Chain Management
• Transportation Engineering
• +3 more

Christian Truden is a Researcher at the Alpen-Adria-Universität Klagenfurt, affiliated with the Department of Production Management and Logistics and the Institute for Production, Energy and Environmental Management. He holds roles as Deputy Director of the Institute and Member of the Curricular Commission for Information Management (TEWI and WIWI). His work focuses on optimizing logistics, transportation systems, and emergency management through computational methods and GIS applications. Truden's research interests span operations research, vehicle routing algorithms, sustainability in transportation, and the integration of UAVs in civilian emergency services. He has contributed to solving complex problems such as emergency contact point allocation during power outages, fleet management optimization, and microtransit scheduling in rural areas. His methodologies include Bayesian modeling, heuristic decomposition, and nearest neighbor Gaussian processes for predictive analytics. His recent publications (2020–2025) emphasize practical applications like defibrillator drone deployment in mountainous regions, grocery home delivery systems, and time-window constrained vehicle routing. These studies address real-world challenges in logistics efficiency, environmental impact reduction, and accessibility improvements. Truden's work bridges theoretical optimization with operational feasibility, often leveraging geographic and computational tools. He is reachable at christian.truden@aau.at and located in room p.2.45 of the Main building's South Wing East.

Milosh JovanovikjView profile

Associate Professor

• Knowledge Graphs
• Data Engineering
• Semantic Web
• +8 more

Dr. Milosh Jovanovikj holds the role of Associate Professor at the Faculty of Computer Science and Engineering in Skopje, North Macedonia, and concurrently serves as a PostDoc Researcher at TU Wien in Vienna, Austria. He is also a Senior R&D Knowledge Graphs Engineer at OpenLink Software in London. His primary research focuses on Knowledge Graphs (KGs), including their lifecycle processes such as modeling, enrichment, and analytics-driven AI applications. He has contributed to over 10 international and 25 national research projects, authored 60+ publications, and co-authored 3 books. His expertise spans Data Engineering, Semantic Web technologies, Linked Data, and Applied AI. Significant contributions include developing frameworks like RDFGraphGen for RDF graph generation and PharmKE for pharmaceutical text analysis. He has led initiatives in geospatial semantic web standards (GeoSPARQL) and healthcare informatics, including predictive analytics for nephrology data. Education: PhD in Computer Science and Engineering His work bridges academia and industry, with projects like the 3DFed federation engine and Semantic Sky (a Gmail plugin). He has extensive experience in ontology development (e.g., SEOntology, VEO for CO2 emissions) and open data initiatives, including LinkedDrugs for global drug data consolidation. Active in dissemination, his articles span knowledge graph applications in music recommendation, finance sentiment analysis, and drug-disease relation discovery. He has collaborated on benchmarks like the GeoSPARQL Compliance Benchmark and Mighty Storage Challenge (MOCHA). Grants/Projects: HOBBIT, SAGE, 3DFed, LinkedDrugs He leads teams in advancing semantic web integration, cloud service platforms (Semantic Sky), and educational materials like Web Programming Basics . His labs and teams focus on AI-driven solutions for healthcare, geospatial analytics, and enterprise systems.

Stefan OhrhallingerView profile

Researcher

• Computer Graphics
• Geometry Processing
• Surface Reconstruction
• +3 more

Stefan Ohrhallinger is a Senior Researcher at TU Wien's Institute of Visual Computing and Human-Centered Technology. He holds a PhD from Concordia University (2013) and a Master's in Business Informatics from Johannes Kepler University Linz (1997). His research focuses on surface reconstruction, point-based graphics, and geometry processing with applications in computer graphics and virtual/augmented reality. Education: PhD in Computer Science, Concordia University (2013) Master of Business Informatics, Johannes Kepler University Linz (1997) Affiliations: Principal Investigator for grants totaling €1.7M+ (e.g., WWTF Modeling the World at Scale, FWF Superhumans) Teaching: 'Modeling in Computer Graphics' and 'Scientific Writing' courses His work emphasizes robust algorithms for reconstructing curves/surfaces from sparse/noisy data, with contributions to occlusion-aware processing and large-scale point cloud handling. Notable achievements include the Best Poster Award at Eurographics 2012 and over 30 peer-reviewed publications. Grants & Projects: WWTF 'Modeling the World at Scale' (2020–2026, €578k) FWF 'Superhumans: Walking Through Walls' (2019–2023, €333k) IPA 'Photogrammetry made easy' (2020–2022, €50k)

• Machine Learning
• Graph Neural Networks
• Recommender Systems
• +3 more

David Penz is a PreDoc Researcher at Technische Universität Wien (TU Wien), affiliated with the Faculty of Informatics and the Department of Machine Learning. He teaches courses such as Introduction to Machine Learning , Machine Learning Algorithms and Applications , and Theoretical Foundations and Research Topics in Machine Learning . His research focuses on advancing Graph Neural Networks (GNNs), particularly for outerplanar graphs, and developing ethical AI systems in recommendation engines. His work emphasizes data privacy, fairness in AI, and music information retrieval. Key projects include the StruDL initiative (2023–2027), exploring maximally expressive GNN architectures. He has supervised a diploma thesis on antibody-antigen binding affinity prediction using geometric deep learning. Recent publications highlight contributions to unlearning sensitive user attributes in recommendations and emotion-aware music recommendation systems. His academic output spans conferences like NeurIPS, SIGIR, and ICMR, demonstrating expertise in both theoretical and applied machine learning domains. He actively participates in academic challenges, such as the ACM Recommender Systems Challenge 2021, showcasing lightweight XGBoost approaches.

• Information Retrieval
• Data Science
• Medical Informatics
• +3 more

Florina Piroi is a Senior Researcher at the Technische Universität Wien (TU Wien), affiliated with the Faculty of Informatics and the Department of Data Science. She holds the role of Senior Scientist in Data Science and is a Substitute Member of the Curriculum Commission for Business Informatics. Her primary research focuses on information retrieval, medical informatics, natural language processing, and patent text mining. She leads projects such as the CLEF-IP evaluation lab and contributes to initiatives like the DoSSIER and OS Trails research programs. Key research interests include longitudinal evaluation of machine learning models, reproducibility in NLP tasks, and knowledge graph applications in manufacturing. She has supervised PhD student Anindita M. Ningtyas, whose work addresses medical terminology accessibility for laypeople. Piroi collaborates on interdisciplinary projects, such as designing health datasets from medical forums and improving search systems for evolving corpora. Her notable contributions include benchmarking frameworks for IR systems, semantic translation tools for industry, and methods for analyzing electrical systems. She has published over 50 peer-reviewed articles in venues like SIGIR, CLEF, and ECIR, emphasizing practical applications in both academic and industrial contexts.

• Parameterized Complexity
• Graph Theory
• Artificial Intelligence
• +3 more

Mathis Teva Rocton is a PreDoc Researcher at the Department of Algorithms and Complexity, Technische Universität Wien (TU Wien). He holds an MSc and the title of Univ.Ass. His research focuses on parameterized complexity, graph theory, and theoretical computer science with applications in artificial intelligence. Rocton is involved in projects such as 'Parameterisierte Analyse in der Künstlichen Intelligenz' (2021–2026) and 'Parameterized Graph Drawing' (2023–2027). His recent work explores twin-width concepts, feedback edge parameters, and neural network training complexity. Notable publications include contributions to IPEC 2024, STACS 2024, and NeurIPS 2023. He has supervised diploma theses, including David Jäger's work on 'Turbocharging twin-width heuristics with SAT' (2024). Rocton's research bridges algorithmic theory and practical applications in AI.

• Algorithms
• Graph Theory
• Computational Complexity
• +2 more

Manuel Sorge is a Research Fellow in the Faculty of Informatics at Vienna University of Technology, affiliated with the Algorithms and Complexity group (E192-01). His research focuses on parameterized algorithms, graph theory, and computational complexity, with particular emphasis on graph modification problems, clustering algorithms, and combinatorial optimization. His work spans several areas including graph drawing, algorithmic game theory, and machine learning. Research interests include: Parameterized complexity and kernelization Graph algorithms and combinatorial optimization Algorithmic graph theory and discrete mathematics Computational geometry and graph drawing Supervises master's students in algorithm design and complexity theory. Current projects include Parameterized Graph Drawing (2023–2027).

• Machine Learning
• Chemical Informatics
• Graph Theory
• +3 more

Klaus Weinbauer is a Researcher at Technische Universität Wien (TU Wien) affiliated with the Department of Informatics . His work focuses on applying machine learning techniques to diverse domains including chemical reaction analysis, software engineering education, and data-driven research. Research Interests : Machine learning applications in chemical informatics Graph-based modeling and algorithm development Improving software engineering education through data analysis Computational methods for reaction database curation Recent Publication Trends : His 2024-2025 work shows a strong focus on combining graph theory with chemical reaction analysis, particularly for database curation and transition state modeling. He also contributes to educational research in embedded software development pedagogy.