E. Eisemann is a Professor at the Computer Graphics and Visualisation department within the Faculty of Electrical Engineering, Mathematics and Computer Science at Delft University of Technology (TU Delft). Their research focuses on computer graphics, virtual reality, and 3D modeling, with recent publications addressing ray-box intersections, neural scene representations, and interactive modeling systems. Current research trends include Advancements in real-time rendering algorithms Applications of neural networks for 3D scene reconstruction Innovative approaches to human-computer interaction in VR environments Optimization techniques for large-scale environment rendering Research output spans 164 publications, with recent work appearing in venues like Computer Graphics Forum and ACM SIGGRAPH conferences. Supervised work includes 18 formal advisees.
Prof. Dr. Alexander Ecker is Professor of Data Science at the Institute of Computer Science, University of Göttingen, and concurrently holds the prestigious Max Planck Fellow position at the Max Planck Institute for Dynamics and Self-Organization. Since 2020 he also serves on the Executive Board of the Campus Institute Data Science in Göttingen. He leads the Neural Data Science research group, comprising 14 PhD students and 2 postdoctoral researchers, focusing on the interface of machine learning and computational neuroscience. His educational background includes a Dr. rer. nat. in Neuroscience (2014) from the Graduate School of Neural and Behavioral Sciences/IMPRS, University of Tübingen, followed by post-doctoral and group-leader positions at the University of Tübingen and the Max Planck Institute for Biological Cybernetics. Research Interests Machine Learning & Deep Learning: developing novel algorithms for representation learning and generative modeling. Computational Neuroscience: large-scale data-driven modeling of visual cortical circuits. Visual Perception: bridging biological vision and computer vision via biologically inspired architectures. His work has produced a steady stream of influential publications (2019-2025) in leading journals such as Nature Communications , Nature , Nature Methods , PLOS Computational Biology , ICLR , NeurIPS , and CVPR . The publications trend toward integrating high-resolution neural recordings with state-of-the-art machine-learning models to uncover principles of sensory processing, neuron-type classification, and behavior. Scientific Awards & Honors Max Planck Fellow, Max Planck Institute for Dynamics and Self-Organization (ongoing) Executive Board Member, Campus Institute Data Science, Göttingen (since 2020) Teaching, Advising & Grants Regularly teaches advanced courses: “Deep Learning for Image Synthesis”, “Current Topics in Deep Learning”, and “Graph Machine Learning”. Supervises 14 current PhD students and 2 postdocs within the Neural Data Science Group. Offers numerous Bachelor’s and Master’s thesis projects, with topics ranging from neuronal morphology clustering to primate vocalization analysis. Leads or co-leads large collaborative consortia with labs in Göttingen, Tübingen, Baylor College of Medicine, and other institutions across the US and Germany. Labs & Teams The Neural Data Science Group operates at the Institute of Computer Science, University of Göttingen, and is tightly integrated with the Max Planck Institute for Dynamics and Self-Organization. The group maintains active collaborations with over a dozen partner laboratories, including groups led by Fabian Sinz, Andreas Tolias, Thomas Euler, Tim Gollisch, and Viola Priesemann, fostering an interdisciplinary environment that spans computer science, physics, biology, and psychology.
Huijuan Xu is an Assistant Professor in the Department of Computer Science and Engineering. Her research spans artificial intelligence, computer vision, and knowledge representation, with a focus on temporal modeling, semantic reasoning, and multimodal learning. She has contributed to advancements in virtual reality streaming, knowledge graph completion, and weakly-supervised video analysis. Research output: 32 publications (2015-2025), including 15 peer-reviewed articles and conference contributions Core research areas: Representation Learning (100% match), Knowledge Graph (100% match), Temporal Action Detection (86% match), and Motion Feature Learning (73% match) Her recent work explores: 2025 : Bandwidth-optimized VR streaming for edge devices 2024 : Neural concept reasoning for image retrieval and avatar generation from sparse data 2023 : Zero-shot scene graph generation and bias mitigation in visual QA
Tarik Kelestemur is a roboticist specializing in autonomous systems, with affiliations including Boston Dynamics AI Institute and Northeastern University. His work bridges robotics, artificial intelligence, and computer engineering, focusing on tactile manipulation, 3D semantic understanding, and policy learning frameworks. His research interests include: Robotics Artificial Intelligence Machine Learning Computer Engineering Autonomous Systems Human-Robot Interaction Recent publications highlight advancements in diffusion policies, vision foundation models, and 3D relational object graphs. Tarik received an Outstanding Paper Award Finalist at CoRL 2024 and contributes to open-source robotics projects like point_cloud_proc and icub_arm_imitator .
Prof. Dr. Didier Stricker is a leading academic in computer science, serving as Scientific Director at the German Research Center for Artificial Intelligence (DFKI) and Professor at the University of Kaiserslautern-Landau (RPTU). His career spans over two decades, including leadership roles at Fraunhofer IGD and founding the Augmented Vision research unit at DFKI/RPTU, which now includes ~30 researchers. Education: Electrical Engineering (Technical University of Grenoble, Karlsruhe) PhD: Computer Vision-based Calibration and Tracking Methods for Augmented Reality (2002, TU Darmstadt) His research focuses on virtual and augmented reality , computer vision , human-computer interaction , and on-body sensor networks . He leads major EU/national projects like LUMINOUS (Language-Augmented XR) and SHARESPACE (Ethical Hybrid Shared Spaces), with industrial partnerships including Sony, Google, and John Deere. Recent publications emphasize 3D reconstruction , neural network optimization , and XR systems . Key trends include event camera processing , scene flow estimation , and multimodal AI for industrial applications . He holds patents in AR tracking and has received the 2006 Innovation Prize from the German Society of Computer Science. Scientific Awards : Innovation Prize (2006) Best Paper/Demonstration Awards at ISMAR, EUSIPCO, CVPR, and ICRA As a reviewer for journals and conferences in VR/AR and computer vision, he contributes to shaping research standards. His lab ( AG Augmented Vision ) combines academic and industrial collaborations to advance cognitive interfaces and extended reality systems.
Dr. Jun Li is a Senior Lecturer at the School of Computer Science, Faculty of Engineering and Information Technology, University of Technology Sydney (UTS), Australia. He received his Ph.D. in Computer Science from Queen Mary University of London in 2009 and is affiliated with the Australian Artificial Intelligence Institute (AAII) at UTS. His research spans multiple domains within artificial intelligence, with primary focus on Machine Learning applications in computer vision and 3D geometry. Dr. Li has published extensively in high-impact journals including IEEE Transactions (TPAMI, TIP, TNNSLS) and Pattern Recognition, with recent work expanding into interdisciplinary research in earth science and marine applications. His research output demonstrates consistent productivity with numerous publications each year across diverse AI application areas. Dr. Li's work shows strong thematic progression from foundational computer vision techniques to applied interdisciplinary research. Early work focused on face hallucination and video super-resolution, while more recent publications address environmental applications using Graph Neural Networks for wave prediction and damage classification for disaster response. His research consistently bridges theoretical AI advances with practical real-world applications across healthcare, autonomous systems, and environmental science. AI to assist disaster emergency response (2023-2026) Applying Generative Adversarial Network in Medical Image Analysis (2020-2021) Big Massive Open Online Course (MOOC) Data Retrieval (2017-2020) As an educator, Dr. Li teaches core courses including '31005 Machine Learning' and '32513 Advanced Data Analytics Algorithms' at UTS, and is available for Masters Research and PhD student supervision, contributing to the development of next-generation AI researchers.
Dr. Stavros Nousias is a researcher at the Chair of Computing in Civil and Building Engineering at the Technical University of Munich , focusing on applications of Artificial Intelligence in the Built Environment . His work bridges Knowledge Representation and Reasoning , Geometry Processing , and Machine Learning to advance construction informatics and digital twinning. Research Interests: AI for building evacuation prediction, technical drawing segmentation, BIM optimization, and respiratory disease modeling. Publications: 15+ peer-reviewed articles on topics including graph neural networks for construction simulations, pulmonary airflow analysis, and heritage site monitoring. Supervised Theses: Guided projects on AI-based BIM command prediction and robotized construction simulation . Labs: Active in the BIM-Lab and Robotic Fabrication Lab . Teaching: Co-instructor for courses like Artificial Intelligence in Engineering and Computation in Engineering 1 .
Ville Valtteri Lehtola is an Assistant Professor in the Department of Earth Observation Science, affiliated with the Digital Society Institute. His research bridges geosciences and artificial intelligence, focusing on sensor technologies and autonomous systems. Academic Rank: Assistant Professor Department: Earth Observation Science Key Affiliations: Digital Society Institute Lehtola's work spans several interconnected domains: Artificial Intelligence : Edge AI, deep learning, graph neural networks Geospatial Research : Point cloud analysis, 3D mapping, indoor navigation Autonomous Systems : Sensor fusion, real-time computing, robotic perception Urban Sustainability : Digital twin applications for city planning His recent publications highlight trends in AI-enhanced geospatial analysis and autonomous navigation technologies. Notably, he has contributed to indoor environment mapping using advanced machine learning techniques and explored digital twin implementations for urban sustainability. Lehtola actively participates in academic collaboration, organizing the ISPRS Workshop Indoor 3D in 2019. His research outputs demonstrate consistent engagement with geospatial AI, sensor technologies, and their applications in real-world environments.
Filip Biljecki is an Assistant Professor at the National University of Singapore, jointly appointed in the Department of Architecture (College of Design and Engineering) and the Department of Real Estate (NUS Business School). He founded and leads the NUS Urban Analytics Lab, which serves as a research hub for urban data science and geospatial AI applications. His work bridges architecture, geomatics, and data science to create smarter, more sustainable urban environments. Dr. Biljecki earned his PhD in 3D GIS from Delft University of Technology with highest honors (top 5%) and completed his MSc in Geomatics at the same institution. His educational background in geospatial science forms the foundation for his innovative research in urban analytics. His research focuses on leveraging emerging urban data sources, particularly street view imagery and other visual data, to advance 3D city modeling, urban digital twins, and GeoAI applications. He investigates spatial data quality, crowdsourcing through platforms like OpenStreetMap, and develops methods to assess urban form and human perception of built environments. His work integrates computer vision, machine learning, and geospatial analysis to address pressing urban challenges related to sustainability, comfort, and equity. Analysis of his recent publications reveals a strong trend toward integrating AI with urban analytics, with particular emphasis on using street view imagery to understand urban environments. His work spans from technical aspects of 3D modeling and digital twins to human-centered applications assessing walkability, thermal comfort, and visual perception. A significant portion of his research addresses sustainability challenges through carbon analysis, urban heat island mitigation, and sustainable urban design. Presidential Young Professorship (NUS), 2020 Top 2% scientists worldwide (Stanford University), 2021 Multiple teaching excellence awards (2021-2025) Best paper awards at 3D GeoInfo (2017, 2023) EuroSDR award for best PhD thesis related to GIS in Europe, 2017 Dr. Biljecki actively supervises PhD students and research fellows through his Urban Analytics Lab, with research supported by various grants and collaborations. He serves as Associate Editor for Computers, Environment and Urban Systems and holds editorial positions with several other leading journals in geography and urban studies. His work bridges academia and practice through collaborations with industry and government agencies focused on urban development. As founder of the NUS Urban Analytics Lab, he leads a vibrant research team exploring the intersection of cities and AI. He also chairs the 3D Information Management Domain Working Group at the Open Geospatial Consortium and serves as Chair of WG IV/1 at the International Society for Photogrammetry and Remote Sensing. His leadership extends to the Future Cities Lab Global at the Singapore-ETH Centre where he serves as Principal Investigator.
