جست‌وجوی استاد و پژوهشگر

Suryanarayana Sankagiriمشاهده پروفایل

پژوهشگر

• Discrete Choice Models
• Recommendation Systems
• Blockchain Security
• +۴ مورد دیگر

Suryanarayana Sankagiri is a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, affiliated with the Information and Network Dynamics (INDY1) group under Professor Matthias Grossglauser. Previously, he earned his Ph.D. in Electrical & Computer Engineering (2018-2022) from the University of Illinois at Urbana-Champaign , where he was supervised by Bruce Hajek and participated in the Coordinated Science Lab . He also holds an M.S. in Electrical & Computer Engineering from the University of Illinois (2016-2018) and a B.Tech. in Electrical Engineering from the Indian Institute of Technology Bombay (2012-2016). Education : Ph.D., Electrical & Computer Engineering, University of Illinois (2018-2022) M.S., Electrical & Computer Engineering, University of Illinois (2016-2018) B.Tech., Electrical Engineering, IIT Bombay (2012-2016) Suryanarayana's research focuses on discrete choice models and their application to recommendation systems , with a particular emphasis on learning from choice data and developing novel models for human decision-making. His broader interests include blockchain security under adverse network conditions, network dynamics , probabilistic modeling , and algorithm design . Recent work explores nonconvex matrix factorization and contextual dueling bandits for recommendation systems. His publications span theoretical and applied domains, including high-impact venues like ICML , Stochastic Systems , and IEEE Transactions on Networking . Themes include blockchain efficiency , hidden community detection in preferential attachment graphs, and temporal analysis of Indian classical music. Current projects involve refining recommendation systems through sparse comparison data and designing protocols for resilient blockchain networks. Scientific Awards : zkCapital Paper of the Week (2021) Rambus Fellowship (2021) Mavis Future Faculty Fellowship (2019) List of Teachers Ranked as Excellent (2019) Nomination for IIT Bombay Undergraduate Colloquium (2016) Best Poster Award, IIT Bombay Undergraduate Research Symposium (2013) Suryanarayana has advised no students listed in the provided materials. His work has been supported by fellowships such as the Mavis Future Faculty Fellowship and Rambus Fellowship . He contributes to the INDY1 group at EPFL, which investigates information and network dynamics through interdisciplinary approaches combining probability , network theory , and algorithmic design .

• Applied Analysis
• Numerical Analysis
• Data Science
• +۶ مورد دیگر

Leon Bungert is a Professor of Mathematics of Machine Learning at the University of Würzburg, working in applied analysis and numerics with a particular focus on data science and machine learning. His research investigates PDEs and variational models on graphs, adversarial robustness of machine learning, variational regularization, and nonlinear optimization. Dr. Bungert serves as a guest editor for the European Journal of Applied Mathematics, an associate editor for Advances in Continuous and Discrete Models: Theory and Applications, and is a member of the program committee at SSVM 2025. He is also an ELLIS member and actively organizes conferences and workshops, including "MIA'25" at IHP in Paris (January 13-15, 2025), "Synergies of Machine Learning and Numerics" in Osaka (March 11-13, 2025), and "Mathematical Analysis of Adversarial Machine Learning" in Oaxaca (August 17-22, 2025). Research Interests Dr. Bungert's primary research areas include: PDEs on graphs Adversarial robustness in machine learning Inverse problems Optimization Variational problems in L-infinity Nonlinear eigenvalue problems Image reconstruction with structural priors His work bridges theoretical mathematics with practical applications in machine learning, particularly focusing on the mathematical foundations of deep learning and developing robust algorithms that can withstand adversarial attacks. He has made significant contributions to understanding the connections between partial differential equations and machine learning algorithms. Research Trends Analysis of Dr. Bungert's recent publications reveals a strong focus on the intersection of machine learning and mathematical analysis. A key theme is the application of variational methods and partial differential equations to machine learning problems, particularly in understanding and improving the robustness of neural networks against adversarial examples. His work on Lipschitz learning on graphs has established important theoretical foundations for graph-based semi-supervised learning. Additionally, his research on the infinity Laplacian and p-Laplacian equations provides deep insights into the mathematical structure of machine learning algorithms. The development of Bregman learning frameworks for sparse neural networks represents a significant contribution to efficient deep learning model training. Professional Activities Dr. Bungert is actively involved in the academic community through editorial roles and conference organization. His current professional activities include: Guest editor for the European Journal of Applied Mathematics Associate editor for Advances in Continuous and Discrete Models: Theory and Applications Member of the program committee at SSVM 2025 ELLIS member Co-organizer of multiple international conferences and workshops Technical Contributions Dr. Bungert has developed several open-source software packages that implement his theoretical contributions, including: Code for convergence rates of Lipschitz learning on graphs A Bregman training framework for sparse neural networks CLIP: Cheap Lipschitz Training of Neural Networks Nonlinear Power Method for Proximal Operators and Neural Networks Robust Image Reconstruction with Misaligned Structural Information These implementations are primarily in Python and MATLAB, demonstrating his commitment to making theoretical advances accessible for practical applications.

• Distributed Computing
• Parallel Algorithms
• Graph Theory
• +۳ مورد دیگر

Christoph Grunau is a Researcher at ETH Zürich's Theoretical Computer Science department, affiliated with the Professorship for Computer Science. His work focuses on distributed computing, parallel algorithms, graph theory, and network decomposition. He has contributed to advancements in scalable MPC (Massively Parallel Computing) algorithms, efficient parallel derandomization techniques, and deterministic network decomposition methods. His research emphasizes algorithmic efficiency, theoretical guarantees, and applications in distributed systems, quantum computing, and dynamic graph problems. Key contributions include work on graph orientation, dynamic coloring algorithms, and clustering techniques such as k-center and k-means++. His publications span topics like shortest path algorithms with negative edge weights, probabilistic methods for algorithm analysis, and distributed symmetry breaking in sparse graphs. Grunau's research bridges foundational theory with practical distributed computing challenges, addressing scalability and efficiency in both classical and emerging computational frameworks.

Xudong Jianمشاهده پروفایل

پژوهشگر

• Structural Health Monitoring
• Artificial Intelligence
• Computer Vision
• +۴ مورد دیگر

Xudong Jian is a Postdoctoral Researcher at the Singapore-ETH Centre (SEC) and the Chair of Structural Mechanics and Monitoring at ETH Zurich, advised by Prof. Eleni Chatzi. His research focuses on enhancing the resilience of civil infrastructure through mobile sensing and data-driven approaches, particularly for bridges and roads. He holds degrees in civil engineering from Tongji University, China, where his work emphasized structural health monitoring (SHM), bridge weigh-in-motion (BWIM), and AI applications. Education: Bachelor’s, Master’s, and Doctoral degrees in Civil Engineering from Tongji University, Shanghai, China. Research Interests: Xudong’s work integrates structural health monitoring with advanced AI techniques such as physics-informed deep learning, graph neural networks, and computer vision. He develops mobile sensing solutions for bridge assessment and has pioneered robotic systems for high-resolution modal analysis. His research also addresses BWIM problems using regularization algorithms and sparse sensor data. Awards & Honors: China National Scholarship Shanghai Municipal Scholarship The Distinguished Graduate of Shanghai Municipality Outstanding Master's Thesis Award, Tongji University Advising & Grants: Xudong collaborates on projects funded by Singapore’s Future Resilient Systems (FRS) initiative and ETH Zurich’s Structural Mechanics group. While no formal advisees are noted, his work involves interdisciplinary teams advancing SHM and AI applications. Labs & Teams: Key affiliations include the Future Resilient Systems (FRS) programme at SEC and the Chair of Structural Mechanics and Monitoring, working on cyber-physical systems resilience and automated structural diagnostics.

Fazl Barezمشاهده پروفایل

پژوهشگر ارشد

• AI Safety
• Mechanistic Interpretability
• Technical AI Governance
• +۳ مورد دیگر

Fazl Barez is a Senior Research Fellow at the University of Oxford leading research on Technical AI Safety and Governance. He is also affiliated with Cambridge's CSER, NTU's Digital Trust Centre, Edinburgh's Informatics, and is a member of ELLIS. Previously, he was a researcher at Amazon and Huawei, and Co-director and Head of Research at Apart Research. He currently serves as an advisor to Martian and has worked with Anthropic's Alignment team (2024-2025). University of Oxford: Senior Research Fellow Cambridge CSER: Affiliate NTU Digital Trust Centre: Affiliate Edinburgh Informatics: Affiliate ELLIS: Member Anthropic: Alignment Team Collaborator (2024-2025) Martian: Advisor Dr. Barez's research focuses on ensuring AI systems remain safe, interpretable, and beneficial as they grow in capability. His work spans four interconnected areas: Interpretability (developing methods to reveal how AI models process information internally), Safety and Alignment (creating tools to detect and address deceptive behaviors), Technical Governance (translating technical insights into governance frameworks), and Societal Impact (examining broader implications of AI on society). His research is funded by OpenAI, Anthropic, Schmidt Sciences, Future of Life Institute, and NVIDIA. The trends in Dr. Barez's publications show a consistent focus on making AI systems more transparent and safer. His recent work explores mechanistic interpretability techniques like sparse autoencoders, investigates how language models relearn removed concepts, examines machine unlearning for safety applications, and develops frameworks for value alignment measurement. His publications appear in top venues including NeurIPS, ICML, ICLR, ACL, and EMNLP, reflecting his significant contributions to both theoretical and practical aspects of AI safety. Future of Humanity Institute PhD Affiliate (2022-2024) EPSRC PhD Student Scholarship (2019-2023) MSc Scholarship (2017-2018) BA (Hons) Sports Performance Scholarship (2013-2017) Dr. Barez has mentored numerous students who have gone on to prominent positions at organizations like Microsoft Research, DeepMind, and Martian. His research is generously funded by major AI organizations including OpenAI, Anthropic, Schmidt Sciences, Future of Life Institute, and NVIDIA. He has served as an Area Chair for ACL 2025 and on program committees for major conferences including ECAI 2024. His work has practical impact, with algorithms like N2G adopted by OpenAI to evaluate sparse autoencoders for interpretability. Dr. Barez leads research at the intersection of technical AI safety and governance. His work connects with multiple research groups including the UK AI Security Institute, Alan Turing Institute, and various university centers. He has co-organized workshops such as the first Mechanistic Interpretability workshop at ICML 2024 and actively collaborates with researchers across the AI safety ecosystem. His research bridges the gap between theoretical safety research and practical implementation in real-world AI systems.

Andrea Ciniمشاهده پروفایل

پژوهشگر

• Machine Learning
• Graph Deep Learning
• Time Series Forecasting
• +۳ مورد دیگر

Andrea Cini is a postdoc researcher affiliated with the Graph Machine Learning Group and the Dalle Molle Institute for Artificial Intelligence (IDSIA USI-SUPSI) at the University of Lugano (USI). He also holds a position as a SNSF postdoc fellow at the University of Oxford under Prof. Michael Bronstein, focusing on machine learning for time series forecasting and graph processing. His research integrates graph deep learning methodologies with spatiotemporal dynamics, emphasizing applications in healthcare, energy systems, and intelligent systems. Education: PhD in Computer Science and Engineering (USI, 2020), supervised by Prof. Cesare Alippi MSc and BSc in Computer Science and Engineering (Politecnico di Milano) Visiting researcher at Imperial College London (Prof. Danilo Mandic) Research interests span graph neural networks , time series forecasting , and spatiotemporal data processing . His work has introduced influential methods such as the Torch Spatiotemporal library, and has been recognized with a best paper award. Recent publications emphasize applications in relational conformal prediction, hierarchical forecasting, and energy grid optimization. Awards include the Best Paper Award for contributions to graph-based forecasting methodologies. Current projects are funded by the Swiss National Science Foundation, exploring graph-based reinforcement learning and spatiotemporal modeling at the University of Oxford. Collaborations include affiliations with the Northernmost Graph Machine Learning group at UiT the Arctic University of Norway. His research bridges theoretical advancements and industrial applications in fields like healthcare dynamics prediction and smart grid optimization.

Giona Casiraghiمشاهده پروفایل

پژوهشگر

• Network Science
• Complex Systems
• Data Science
• +۴ مورد دیگر

Giona Casiraghi is a Senior Researcher at ETH Zurich specializing in network science and complex systems, with a primary focus on resilience modeling in social organizations and data-driven network analysis. His work bridges theoretical advances in statistical network models with practical applications in supply chain management, open-source software ecosystems, and online social dynamics. His research interests center on developing quantitative methods for analyzing complex systems, particularly through the generalized hypergeometric ensemble of random graphs (gHypEG). Casiraghi's work spans multiple disciplines including network science, statistical physics, data science, and resilience theory, with particular expertise in temporal network analysis, multi-edge networks, and zero-inflation models for sparse networks. His research group develops the ghypernet R package , providing open-source tools for network regression and inference. Analysis of his recent publications reveals a strong trend toward applying network science to real-world resilience problems, particularly in pharmaceutical supply chains and social organizations. His 2025 Science paper on US tariffs threatening medicine supply chains exemplifies this practical turn, while his methodological work on zero-inflated network models (PNAS Nexus 2025) demonstrates continued theoretical innovation. Casiraghi frequently collaborates with Frank Schweitzer and others in the Systems Group at ETH Zurich, producing interdisciplinary work that bridges computer science, economics, and social science. Casiraghi's research has significant implications for understanding how social organizations withstand shocks and how supply chains can be made more resilient to disruptions. His work on the gHypEG framework provides foundational tools for network scientists across multiple disciplines, while his applied research offers concrete insights for policymakers and industry practitioners dealing with complex system failures. He has contributed to numerous projects examining online migration after community bans, developer productivity in open-source projects, and reconstruction of social relations from interaction data. His research methodology typically combines large-scale data analysis with advanced statistical modeling, often developing new network analysis techniques to address specific research questions.

• 3D Computer Vision
• Geometric Deep Learning
• Topological Deep Learning
• +۱۰ مورد دیگر

Tolga Birdal is an Assistant Professor (Lecturer) and UKRI Future Leaders Fellow in the Department of Computing at Imperial College London. As the Principal Investigator (PI) of the CIRCLE group , his research focuses on topological deep learning, geometric machine learning, and 3D computer vision, with theoretical interests in non-Euclidean inference and deep learning principles. Education: PhD and MSc in Computer Vision from Technical University of Munich (2018), BSc in Computer Science from Sabancı University (2008). Projects: PI for UKRI-EPSRC's UNTOLD (Topological Deep Learning), Royal Society's drug discovery initiative, and EPSRC's GNOMON (Generative Models in non-Euclidean Spaces). Leadership: Area Chair for CVPR, ICCV, and 3DV 2025 Publication Chair. His work bridges differential geometry, algebraic topology, and deep neural networks, with applications in quantum computer vision, 3D/4D generative priors, and medical imaging. Key contributions include novel frameworks for rotation forecasting, graph generation, and topological generalization bounds. Scientific Awards: UKRI Future Leaders Fellowship EMVA Young Professional Award

• Positional games
• Discrete geometry
• Computational geometry
• +۳ مورد دیگر

Miloš Stojaković is a Full Professor at the Department of Mathematics and Informatics, Faculty of Sciences, University of Novi Sad, Serbia. He has been with the university since 1999, progressing from student to Assistant Professor (2006-2011), Associate Professor (2011-2016), and Full Professor (2016-present). He leads the Foundations of Computer Science group and serves as an editor for Discrete Mathematics & Theoretical Computer Science and the Novi Sad Journal of Mathematics. Ph.D. in Computer Science, ETH Zurich (2005), advisors: Emo Welzl and Tibor Szabó M.Sc. in Computer Science, University of Novi Sad (2001), advisor: Joviša Žunić B.Sc. in Mathematics and Computer Science, University of Novi Sad (1999) Stojaković's research centers on positional games, discrete and computational geometry, discrete random structures, combinatorial algorithms, and graph theory. His work explores theoretical aspects of combinatorial games, particularly Maker-Breaker type games on graphs and other structures. He investigates geometric properties of discrete structures and develops algorithms for geometric problems. His research has applications in theoretical computer science and combinatorics, with significant contributions to understanding game strategies, structural properties, and computational complexity in discrete settings. Stojaković's recent publications (2016-2025) primarily focus on positional games, extending classical results to new settings like posets, generalized saturation, and constructor-blocker variants. He examines computational complexity aspects and structural properties of game outcomes. His work often involves collaborations with leading researchers including Dan Hefetz, Michael Krivelevich, and Tibor Szabó, demonstrating the ongoing vitality of combinatorial game theory and its connections to other areas of discrete mathematics. "Dr Z. Đinđić Award" for the best young scientist in Vojvodina (2008) "Best Student of University of Novi Sad Award" (1998/99) Stojaković has supervised three PhD students to completion: Mirjana Mikalački (2014), Marko Savić (2018), and Jelena Stratijev (2023). His research has been supported by various grants, including the 1 million RSD grant accompanying the Dr Z. Đinđić Award. He has organized multiple workshops including the Novi Sad Workshop on Foundations of Computer Science series (2015, 2017, 2024) and co-organized the Mini-Workshop on Positional Games at Oberwolfach Research Institute (2018) and the Positional Games workshop within A Sparse (Graphs) Coalition (2021). Since 2018, Stojaković has led the Foundations of Computer Science group at the University of Novi Sad. He maintains active international collaborations, having taught courses at Eötvös Loránd University Budapest, University of Buenos Aires, University of Szeged, University of Banja Luka, University of Groningen, and Graz University of Technology. His research group focuses on theoretical aspects of combinatorial games, discrete geometry, and related computational problems, contributing significantly to these fields through publications, workshops, and academic leadership.

Jan S. Hesthavenمشاهده پروفایل

استاد

• Computational Mathematics
• Numerical Analysis
• Scientific Computing
• +۶ مورد دیگر

Jan S. Hesthaven is a Professor and Provost at EPFL, leading academic affairs. He holds a Master's from the Technical University of Denmark (DTU) and a PhD in Numerical Analysis, followed by an honorary dr.techn degree from DTU. His research focuses on high-order computational methods for wave problems, reduced order models, and machine learning integration. He has co-authored over 175 papers and 4 monographs. Previously, he served as Dean of the School of Basic Sciences at EPFL and held roles at Brown University, including Director of the Center for Computation and Visualization. Awards include the Alfred P. Sloan Fellowship and the Philip J. Bray Award. Education: Master of Science in Computational Physics, DTU (1991) PhD in Numerical Analysis, DTU (1995) dr.techn in Computational Mathematics, DTU (2009) Research Interests: Development of high-order numerical methods, computational wave propagation, geophysical flows, and machine learning applications in scientific computing. His work bridges traditional methods with AI-driven approaches for real-time modeling and structural health monitoring. Recent Work: His 2023–2025 publications emphasize machine learning-enhanced models, reduced order methods, and seismic data analysis for environmental applications. Key techniques include physics-informed neural networks and graph-based operator learning. Awards: Alfred P. Sloan Fellowship (2000) NSF Career Award (2002) Philip J. Bray Award (2004) Dr.techn from DTU (2009) Grants & Leadership: Led the Center for Computation and Visualization (CCV) at Brown (2006–2013) and co-directed the NSF Institute ICERM (2010–2013). Current roles include Provost at EPFL and leadership in MATHICSE. Collaborates with industry and applied scientists on computational challenges. Labs & Teams: Active in the MATHICSE lab, focusing on numerical methods and high-performance computing. Involved in interdisciplinary projects combining AI with traditional computational science.

• Distributed Computing
• Algorithms
• Parallel Processing
• +۳ مورد دیگر

Dr. Manuela Fischer is a Lecturer at the Department of Computer Science at ETH Zürich. Her research focuses on distributed computing, algorithms, and parallel processing, with a particular emphasis on graph theory and massively parallel computation. She has contributed to advancements in algorithms for sparse graphs, approximation techniques in semi-streaming models, and distributed systems optimization. Her work often explores theoretical computer science challenges, including algorithm design and computational complexity. Dr. Fischer’s publications span topics such as exponential speedups in MPC frameworks, deterministic symmetry breaking in graphs, and efficient connectivity algorithms in distributed environments. These contributions highlight her expertise in leveraging parallel and distributed computing paradigms to solve complex computational problems. No scientific awards or grants are explicitly mentioned in the provided information. She is affiliated with ETH Zürich and contributes to teaching and research in computer science, though specific educational qualifications or lab affiliations are not detailed in the text.

• Numerical Analysis
• Mathematical Modeling
• Thermal Stability
• +۳ مورد دیگر

Richard Baltensperger is a Full Professor at the University of Applied Sciences and Arts Western Switzerland (HES-SO) , affiliated with the Fribourg School of Engineering and Architecture and the HumanTech - Technology for Human Wellbeing Institute . His research spans numerical analysis, thermal kinetics, and ecological network modeling. Key research areas include: Thermal stability prediction using kinetic models Remote teaching methodologies in chemistry IoT-enabled material shelf-life monitoring Optimization of acoustic sensor networks Thermal hazard analysis for reactive chemicals Complex systems in ecology His work on merging DSC and large-scale testing data has improved safety temperature predictions for materials, while recent publications explore AI-driven sensor placement optimization. He employs advanced statistical methods (AIC/BIC) for model selection and has developed applications for smartphone-based deterioration tracking via data loggers. Current research at the HumanTech Institute focuses on technology applications for environmental and materials safety. Publications show collaborations with institutions like the Federal Institute for Materials Research and Testing (BAM) in Germany.

• Machine Learning
• Optimization
• Explainable AI
• +۱۲ مورد دیگر

Giovanni Iacca is an Associate Professor at the Department of Information Engineering and Computer Science (DISI) of the University of Trento, Italy, where he leads the Distributed Intelligence and Optimization Lab (DIOL). He serves as Coordinator of the Master's Degree in Computer Science and Deputy Director of the Information Engineering and Computer Science Doctoral School. Dr. Iacca has over 15 years of industrial experience in mechatronics and optimization applied to engineering, logistics, and scheduling. Dr. Iacca received his PhD in 2011 from the University of Jyväskylä, Finland, and his MSc in 2006 from the Technical University of Bari, Italy. His academic career includes: 2021-present: Associate Professor, University of Trento 2018-2021: Tenure-track Assistant Professor, University of Trento 2017-2018: Postdoc, RWTH Aachen University, Germany 2013-2016: Postdoc, EPFL and University of Lausanne, Switzerland 2012-2016: Postdoc, INCAS³, The Netherlands Dr. Iacca's research bridges fundamental and applied aspects of artificial intelligence with particular emphasis on evolutionary computation and explainable AI. His work spans machine learning, optimization techniques, distributed systems, and their practical implementations. Recent research directions include federated learning, interpretable reinforcement learning, neural architecture search, and optimization for resource-constrained environments. He teaches courses on Computer Architectures, Introduction to Machine Learning, Bio-Inspired Artificial Intelligence, Optimization Techniques, and AI in Medicine. His publication record demonstrates a strong trend toward developing transparent and efficient AI systems. Recent papers focus on making complex AI models more interpretable while maintaining performance across diverse domains from healthcare to supply chain management. His work on evolutionary approaches to explainable AI has gained significant recognition in the computational intelligence community. Scientific Awards and Editorial Roles EvoApplications Best Paper Award (2017) UKCI AWARENESS Best Paper Award (2012) IEEE CIS Outstanding Student-Paper Award (2011) IEEE Senior Member (2023) Associate Editor, Evolutionary Intelligence (2024) Editorial Board Member, Memetic Computing (2024) Associate Editor, IEEE Transactions on Evolutionary Computation (2023) Dr. Iacca has successfully supervised multiple PhD students including Andrea Ferigo, Hyunho Mo, and Leonardo Lucio Custode. His research is supported by various grants and collaborations with industry partners like MyAv. He serves as chair for PPSN 2026 and has organized workshops including the Workshop on Awareness and Consciousness in Artificial Intelligence (ACAI). As leader of the Distributed Intelligence and Optimization Lab (DIOL), Dr. Iacca oversees a research team working at the intersection of evolutionary computation, machine learning, and distributed systems. The lab focuses on developing novel algorithms that balance computational efficiency with interpretability, with applications spanning from embedded systems to large-scale distributed computing environments. Current projects include interpretable reinforcement learning, federated neuroevolution, and optimization for edge computing.

• Reinforcement Learning
• Machine Learning
• Artificial Intelligence
• +۳ مورد دیگر

Marco Bagatella is a doctoral researcher at the Institute of Machine Learning (ETH Zürich), focusing on advanced machine learning and artificial intelligence research. His work spans reinforcement learning, behavioral cloning, and causal inference, often addressing challenges in generalization, exploration, and policy adaptation. Contact: marco.bagatella@inf.ethz.ch Specializes in Reinforcement Learning (including offline and multi-task settings) Expertise in causal modeling and counterfactual data augmentation Investigates graph neural networks for biological systems Active contributor to AI/ML publications (15+ recent works) His research explores problem space transformations, optimal transport for zero-shot imitation learning, and temporal logic-based exploration. Current projects focus on improving policy robustness and adaptability across diverse domains. Scientific awards: No formal honors listed yet. Collaborates with ETH Zurich's machine learning teams on cutting-edge algorithm development and theoretical analysis.

Dorina Thanouمشاهده پروفایل

پژوهشگر

• Data Science
• Machine Learning
• Graph Signal Processing
• +۳ مورد دیگر

Dorina Thanou is a senior researcher and lecturer at École Polytechnique Fédérale de Lausanne (EPFL), leading strategic research initiatives on AI for Health and Science under the EPFL AI Center. Her work spans graph signal processing , machine learning , and AI for biomedical applications . She holds affiliations with multiple EPFL units, including the Signal Processing Laboratory 4 (STI IEM LTS4), the Chair of Mathematical Data Science (SB MATH MDS1), and the AI Center (VPA-AVP-CP AICENTER). Education: Diploma in Electrical and Computer Engineering (2008), University of Patras, Greece M.Sc. in Communication Systems (2010), EPFL Ph.D. in Electrical Engineering (2016), EPFL Her research focuses on interpretable and robust machine learning models for biomedicine , leveraging graph-based signal processing to analyze complex data in healthcare. Her publication trends emphasize graph representation learning , dynamic 3D data compression , and biomedical applications , particularly in cardiology and neuropathology. Scientific Awards: ELLIS Scholar in Geometric Deep Learning (2021) Best Student Paper Award, IEEE ICASSP (2015) Top 10% Paper Award, IEEE ICIP (2015) Best Paper Award, Picture Coding Symposium (2016) IEEE Senior Member (2023) She mentors PhD students Monteiro Lança Madeira Manuel and Ögüt Sevda and has led interdisciplinary collaborations through the Swiss Data Science Center (2016-2020) and Center for Intelligent Systems (2020-2024). Her labs include the Signal Processing Laboratory 4 , Mathematical Data Science Lab , and the AI Center .