Dr Tolga Birdal is an assistant professor (Lecturer) and a UKRI Future Leaders Fellow in the Department of Computing of Imperial College London. Previously, he was a senior Postdoctoral Research Fellow at Stanford University within the Geometric Computing Group of Prof. Leonidas Guibas. Tolga has defended his masters and Ph.D. theses at the Computer Vision Group under Chair for Computer Aided Medical Procedures, Technical University of Munich led by Prof. Nassir Navab. He was also a Doktorand at Siemens AG under supervision of Dr. Slobodan Ilic working on “Geometric Methods for 3D Reconstruction from Large Point Clouds”. His thesis was awarded the prestigious EMVA Young Professional Award. His current foci of interest involve topological / geometric machine learning and 3D computer vision. More theoretical work is aimed at investigating and interrogating limits in geometric computing and non-Euclidean inference as well as principles of deep learning. Tolga has several publications at the well-respected venues such as NeurIPS, CVPR, ICCV, ECCV, ICLR, ICML, T-PAMI, ICRA, IROS, etc. He is the AC for CVPR, ICCV, ICML, ECCV and has currently program-chaired 3DV 2025. Aside from his academic life, Tolga has co-founded multiple companies including Befunky, a widely used web-based image editing platform.
Alex M. Bronstein is a professor at the Institute of Science and Technology Austria with a secondary affiliation in the Department of Computer Science at the Technion — Israel Institute of Technology where he holds the Schmidt Chair in Artificial Intelligence and the Dan Broida Academic Chair, and directs the Center for Intelligent Systems. Bronstein’s work spans inverse problems, computational imaging, machine learning, and data-driven modeling for science and engineering. He is a Fellow of IEEE and ELLIS and the recipient of four ERC grants. Alongside academia, he is a technological entrepreneur, inventor, and investor, having co-founded and served in senior technical roles across ventures ranging from depth cameras and large-scale video search to medical devices, food tech, and quantitative finance. His group is known for turning principled models into deployable systems, bridging theory, instrumentation, and real-world impact.
Dr. Ioana Ciuclea holds degrees in both engineering and mathematics and is currently an Assistant Professor at the West University of Timișoara.
She completed her PhD, titled "Nonlinear Grassmannians and their generalizations" in 2024, at the West University of Timișoara. Her current research interests lie in shape analysis, infinite-dimensional differential geometry, Lie groups and symplectic geometry.
Marzieh Eidi is an early-career mathematician fascinated by the deep mathematical structures that shape data science and machine learning. She obtained her PhD from the Max Planck Institute for Mathematics in the Sciences in Leipzig under the supervision of prof. Juergen Jost and is currently a postdoctoral researcher at ScaDS.AI institute and MPI MiS in Leipzig. Her work explores the dynamic interplay between geometry, topology, spectral analysis, and stochastic processes, seeking to bridge abstract theory with real-world learning and analysis. At the heart of her research is a passion for building unified frameworks that connect discrete and generalized curvature notions (such as Ollivier and Forman Ricci curvature), homology theories (Morse, Floer, Conley, Forman), (smooth and discrete) Hodge Laplacian, and stochastic processes into a coherent and integrated perspective. Alongside this theoretical vision, she also enjoys applying these ideas to data analysis and learning methods, where mathematical insights can illuminate structure, improve performance, and reveal new patterns in complex systems such as biological networks.
Rita Fioresi is Full Professor at the FaBiT Department of the University of Bologna. Her research lies at the interface of pure mathematics, theoretical physics, and artificial intelligence, with expertise in Lie theory, supergeometry, quantum groups, and deep learning. After earning her PhD in Mathematics from UCLA, she held academic positions at UCLA and the University of Bologna, where she has served in roles ranging from researcher to associate professor, and since 2025, full professor. Her work bridges foundational mathematics—particularly Lie algebras, supergroups, and quantum geometry—with emerging developments in geometric deep learning, quantum computing, and mathematically grounded AI models. Professor Fioresi has led several major European research initiatives, including MSCA Doctoral Networks and Staff Exchange projects, and currently serves as Principal Investigator and Action Chair of multiple EU-funded programs. She is an active member of the international mathematical and AI communities, serving on editorial boards of leading journals such as Journal of Lie Theory, Communications in Mathematical Physics, and International Journal of Geometric Methods in Modern Physics, and is a member of the ELLIS Society.
Simone Foti is a Postdoctoral Researcher at Imperial College London, having completed a PhD at University College London and held research internships at Disney Research Studios and Adobe Research. His research lies at the intersection of geometric deep learning, computer graphics, and computer vision. Through his work, he solves problems in non-Euclidean domains, such as Riemannian surfaces and general geometries represented as meshes. Simone's primary focus is building machine learning models that respect the geometry of the space in which they operate, with applications ranging from AR/VR and movie production to plastic surgery and AI for Earth Science.
F. Gay-Balmaz is an Associate Professor in Mathematics at NTU Singapore since 2023. Previously he was a researcher at the Centre National de la Recherche Scientifique (CNRS, France) at Ecole Normale Supérieure de Paris (ENS). He received his Master (2004) and Ph.D. degrees (2009) from the Swiss Federal Institute of Technology (EPFL, Switzerland) and his Habilitation (2018) at Sorbonne University. He was also a PostDoc at EPFL and at the California Institute of Technology (2009-2010). His research focuses on the development of structure-preserving methods for the modeling and discretization of partial differential equations arising in fluid dynamics and nonlinear elasticity. His approach is based on tools derived from differential geometry, symplectic and Poisson geometry, and geometric mechanics. His recent interests include geophysical fluid dynamics and nonequilibrium thermodynamics.
Minh Ha Quang received his PhD in Mathematics from Brown University (USA) under the supervision of Stephen Smale. He is currently Senior Research Scientist at the RIKEN Center for Advanced Intelligence Project (RIKEN-AIP) in Tokyo, Japan.
Before joining RIKEN in June 2018, he was a researcher at the Pattern Analysis and Computer Vision (PAVIS) group at the Italian Institute of Technology (IIT) in Genova, Italy. His current research interests are Machine Learning and Statistical Methodologies using Functional Analysis, Information Geometry, and Optimal Transport.
Simone Melzi is an Associate Professor at the University of Milano-Bicocca. He received his PhD in Computer Science from the University of Verona (2018) after graduating in Mathematics at the University of Milan (2013). He held postdoctoral positions at Sapienza University of Rome, École Polytechnique, and the University of Verona. His research focuses on geometry processing, 3D shape analysis, and Geometric deep learning. He was awarded the Eurographics Young Researcher Award , the EG-Italy PhD Thesis Award, a Marie-Curie Individual Fellowship (Seal of Excellence), and the BE-FOR-ERC grant. He is a Eurographics Junior Fellow and an ELLIS Scholar.
Shirin Salehi received her PhD in Electrical Engineering from IUT, Iran, in collaboration with UPC, Spain. Since 2022, she has been a postdoc researcher at RWTH Aachen University, Germany, where she explores how to make modern AI models faster, lighter, and more sustainable. Her habilitation topic focuses on resource-efficient deep learning and large AI models for edge intelligence, with the goal of reducing the cost of training and inference while maintaining high performance. By rethinking how data, memory, models, and computation are used across fine-tuning, pre-training, and inference, we aim to develop techniques that enable powerful AI systems to run efficiently on edge devices. This talk will highlight why resource efficiency is becoming essential for the future of scalable and accessible AI.
Hông Vân Lê is a senior scientist of the Institute of Mathematics of the Czech Academy of Sciences. She was the recipient of the Prize of the Moscow Mathematical Society in 1990, and the recipient of ICTP’s Majorana Prize in 1991. She works on Riemannian Geometry, Symplectic Topology, Representation Theory, Algebraic Topology, Information Geometry, and Mathematical Foundations of Machine Learning.