Lecturers
Each Lecturer will hold up to four lectures on one or more research topics.
Topics
Artificial Intelligence, Autonomous Agents, Multi-Agent Systems, Reinforcement LearningBiography
Dr. Stefano V. Albrecht is Associate Professor in the College of Computing and Data Science at Nanyang Technological University (NTU) Singapore, where he leads the Autonomous Agents Research Group (https://agents-lab.org). His research in reinforcement learning and multi-agent interaction has been published in the leading venues for AI/ML/robotics, including NeurIPS, ICML, ICLR, AAAI, IJCAI, AAMAS, UAI, AIJ, JAIR, JMLR, TMLR, ICRA, IROS, Science Robotics. He has worked closely with industry partners to develop real-world AI applications, including in autonomous driving (with FiveAI/Bosch), multi-robot warehousing (with Dematic), and human-AI workflow automation (with DeepFlow). For his research, he received fellowships from the UK Royal Society, Royal Academy of Engineering, Alexander von Humboldt Foundation, and German Academic Scholarship Foundation. Previously, Dr. Albrecht was a Postdoctoral Fellow at the University of Texas at Austin working with Prof. Peter Stone. He obtained PhD & MSc degrees in Artificial Intelligence from the University of Edinburgh, and a BSc degree in Computer Science from Technical University of Darmstadt. He is co-author of the textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” (MIT Press 2024, https://marl-book.com), and author of the forthcoming book “Becoming an AI Researcher: Practical Advice for Graduate Students” (Cambridge University Press 2026, https://phd-in-ai.com).
Lectures
Topics
Computational neuroscience, Machine LearningBiography
Rafal Bogacz graduated in computer science at Wroclaw University of Technology in Poland. Then he did a PhD in computational neuroscience at the University of Bristol, and next he worked as a postdoctoral researcher at Princeton University, USA, jointly in the Departments of Applied Mathematics and Psychology. In 2004 he came back to Bristol where he worked as a Lecturer and then a Reader. He moved to the University of Oxford in 2013.
His research is in the area of computational neuroscience, which seeks to develop mathematical models describing computations in the brain giving raise to our mental abilities. He is particularly interested in modelling the learning processes in the brain, both in the cortex and in the subcortical regions underlying reinforcement learning. He also investigates how treatments involving brain stimulation can be refined to optimize their effectiveness and reduce side effects.
Lectures
Abstract TBA
Topics
Artificial Intelligence, Automated Planning, Strategic ReasoningBiography
Giuseppe De Giacomo is a Professor of Computer Science in the Department of Computer Science at the University of Oxford. He has previously been a Professor at the Department of Computer, Control, and Management Engineering of the University of Rome “La Sapienza”. His research spans theoretical, methodological, and practical aspects of Artificial Intelligence and Computer Science, with major contributions to Knowledge Representation, Reasoning about Actions, Generalized Planning, Autonomous Agents, Temporal Synthesis and Verification, Service Composition, Business Process Modeling, and Data Management and Integration. He is a Fellow of AAAI, ACM, and EurAI. He was awarded an ERC Advanced Grant for the project WhiteMech: White-box Self-Programming Mechanisms. He served as Program Chair of ECAI 2020 and KR 2014. He is a member of the Board of EurAI and chairs the steering committee of EurAI’s annual summer school ESSAI.
Lectures
ABSTRACT: This course presents temporal synthesis as a foundation for guardrailing agentic AI. Temporal synthesis studies the automatic synthesis of interactive programs (strategies) from declarative specifications expressed in temporal logic. In this course, we show how temporal synthesis provides a practical foundation for strategic reasoning in autonomous AI systems. The key to this research path lies in the rich body of concepts developed in reasoning about actions and planning, combined with a precise treatment of nondeterministic environments and temporal objectives. In such settings, plans must be treated as strategies rather than being blurred with individual execution traces, and goal satisfaction evolves during execution rather than being reducible to reaching states with fixed properties, as in classical planning. These features are naturally captured within the temporal synthesis framework. Technically, we study the structure of the entire space of strategies satisfying a specification. Rather than assuming strategies to be observable, we focus on characterizing the set of execution traces that are compliant with a given strategy space. This perspective provides formal support for guardrailing and responsibility attribution in systems composed of multiple, independently acting autonomous agents.
ABSTRACT: This course presents temporal synthesis as a foundation for guardrailing agentic AI. Temporal synthesis studies the automatic synthesis of interactive programs (strategies) from declarative specifications expressed in temporal logic. In this course, we show how temporal synthesis provides a practical foundation for strategic reasoning in autonomous AI systems. The key to this research path lies in the rich body of concepts developed in reasoning about actions and planning, combined with a precise treatment of nondeterministic environments and temporal objectives. In such settings, plans must be treated as strategies rather than being blurred with individual execution traces, and goal satisfaction evolves during execution rather than being reducible to reaching states with fixed properties, as in classical planning. These features are naturally captured within the temporal synthesis framework. Technically, we study the structure of the entire space of strategies satisfying a specification. Rather than assuming strategies to be observable, we focus on characterizing the set of execution traces that are compliant with a given strategy space. This perspective provides formal support for guardrailing and responsibility attribution in systems composed of multiple, independently acting autonomous agents.
ABSTRACT: This course presents temporal synthesis as a foundation for guardrailing agentic AI. Temporal synthesis studies the automatic synthesis of interactive programs (strategies) from declarative specifications expressed in temporal logic. In this course, we show how temporal synthesis provides a practical foundation for strategic reasoning in autonomous AI systems. The key to this research path lies in the rich body of concepts developed in reasoning about actions and planning, combined with a precise treatment of nondeterministic environments and temporal objectives. In such settings, plans must be treated as strategies rather than being blurred with individual execution traces, and goal satisfaction evolves during execution rather than being reducible to reaching states with fixed properties, as in classical planning. These features are naturally captured within the temporal synthesis framework. Technically, we study the structure of the entire space of strategies satisfying a specification. Rather than assuming strategies to be observable, we focus on characterizing the set of execution traces that are compliant with a given strategy space. This perspective provides formal support for guardrailing and responsibility attribution in systems composed of multiple, independently acting autonomous agents.
Topics
Artificial Intelligence, Machine Learning, Computer VisionBiography
Director, Research Scientist Meta Superintelligence Labs.Prior to joining Facebook in Spring 2018, he received the PhD degree in computer science from TU Graz, and spent time as a visiting researcher at the York University Toronto and the University of Oxford. He is the recipient of a DOC Fellowship of the Austrian Academy of Sciences and his PhD thesis was awarded with the Award of Excellence for outstanding doctoral thesis in Austria. His main areas of research include the development of effective representations for video understanding. He aims to find solutions for problems that are grounded in applications such as recognition and detection from video.
https://scholar.google.com/citations?user=UxuqG1EAAAAJ&hl=de
Lectures
Topics
Foundation Models, Large Language Models, Natural Language Understanding, Deep Learning,Biography
Sven Giesselbach is the leader of the Natural Language Understanding (NLU) team at the Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS). His team develops solutions in the areas of medical, legal and general document understanding which in their core build upon (large) pre-trained language models. Sven Giesselbach is also part of the Lamarr Institute and the OpenGPT-X project in which he investigates various aspects of Foundation Models. Based on his project experience of more than 25 natural language understanding projects he studies the effect of Foundation Models on the execution of Natural Language Understanding projects and the novel challenges and requirements which arise with them. He has published several papers on Natural Language Processing and Understanding, which focus on the creation of application-ready NLU systems and the integration of expert knowledge in various stages of the solution design. Most recently he co-authored a book on “Foundation Models for Natural Language Processing – Pre-trained Language Models Integrating Media” which will be published by Springer Nature.
Gerhard Paaß, Sven Giesselbach, Foundation Models for Natural Language Processing – Pre-trained Language Models Integrating Media, Springer, May, 2023
Lectures
Abstract TBA
Abstract TBA
Abstract TBA
Topics
Gemini, Gemini’s adversarial security, privacy evaluations, post-trainingBiography
Hi, I am a staff research scientist at Google DeepMind. I am the research lead for a team of 10+ technical staff working on Gemini’s adversarial security and privacy evaluations and post-training. My research interests lie at the intersection of AI, Security and Privacy. See my Google Scholar profile for a list of recent publications, my CV, or feel free to reach out to me.
Lectures
Topics
Artificial IntelligenceBiography
Abdelsalam Helal (aka: Sumi Helal) is a full Professor in the Computer Science and Engineering Department at the University of Bologna. Prior to joining UNIBO, he spent 26 years as associate and then full processor in the Computer & Information Science and Engineering Department at the University of Florida. At UF, he directed the Mobile and Pervasive Computing Laboratory and co-founded and directed the Gator Tech Smart House –a real-world deployment project. His active areas of research focus on architectural and programmability aspects of the Internet of Things (IoT), service-oriented IoT architectures, IoT edge intelligence, and pervasive/ubiquitous systems and their human-centric applications, especially in the Digital Health area. Helal is also a technologist at heart who founded several successful ventures in the areas of IoT and Digital Health. His research was licensed by the top multinational tech industry including Google, Apple, Samsung, Bosch, Siemens, Nokia, Ericsson, AMAZON, T-Mobile, Verizon, others. Prof. Helal is a Fellow of the ACM, IEEE, AAAS, AAIA, and IET. He is member of Academia Europaea, and the US National Academy of Inventors NAI. Go to the Curriculum vitae
Lectures
Abstract TBA
Abstract TBA
Topics
AI, Reasoning, LLMs, Reinforcement LearningBiography
Since June 2023, Albert Q. Jiang has been a Research Scientist at Mistral AI, where his team focuses on the science and infrastructure of reasoning. His long-term research objective is the development of a mathematical superintelligence that is safe and aligned by construction. In pursuit of this goal, Albert has contributed to several frontier projects in large language models and reasoning systems, including pretraining data initiatives such as Mixtral of Experts and Mistral 7B in 2023, mid- and post-training research with Mathstral in 2024, and large-scale reinforcement learning efforts through Magistral in 2025.
Albert completed his PhD at the University of Cambridge Computer Laboratory under the supervision of Mateja Jamnik and Wenda Li. His thesis was examined by Jeremy Avigad and Ferenc Huszár in October 2024, and he successfully passed with no corrections required.
His doctoral research focused on learning abstract mathematical reasoning with language models. His work explored the autoformalization of theorems and proofs, including the development of large parallel datasets for statement autoformalization such as Multilingual Mathematical Autoformalization (MMA). Albert also worked on integrating and improving premise selection tools using language models, studied human–AI interaction in mathematical problem-solving, and investigated mathematical conjecturing as a step toward more advanced forms of machine reasoning.
https://albertqjiang.github.io/
https://scholar.google.com/citations?user=Fe_RBHMAAAAJ&hl=en
Lectures
Abstract TBA
Abstract TBA
Topics
Tabular foundation models, foundation modelsBiography
I am a Research Scientist (Chargée de Recherche) in Machine Learning at INRIA, within the SODA team. My research lies at the intersection of statistical learning and trustworthy AI, with a focus on:
- Tabular foundation models, which unlock new possibilities through large-scale pretraining.
- Model auditing, to enhance the trustworthiness and reliability of machine learning systems.
- Learning from incomplete data, a challenge pervasive in fields like healthcare and social sciences.
I am passionate about using AI to tackle complex scientific and healthcare problems, ensuring that machine learning models are both powerful and reliable.
Lectures
Abstract TBA
Abstract TBA
Topics
Generative AI, LLMsBiography
Bruno Lepri is a senior researcher at Fondazione Bruno Kessler, where he leads the Mobile and Social Computing (MobS) Lab within the Augmented Intelligence Center. He is also Chief Scientific Officer of Ipazia Spa, a startup focused on generative AI. He currently serves as co-director of the ELLIS Unit Trento—a joint research unit between FBK and the University of Trento dedicated to machine learning—and of the Center for Computational Social Sciences, also in collaboration with the University of Trento.
Since May 2024, he has been a member of the Scientific Committee of the National Tourism Observatory.
Previously, he was Chief AI Scientist at ManpowerGroup and a senior researcher affiliated with Data-Pop Alliance, a think tank on big data and sustainable development founded by the MIT Media Lab and the Harvard Humanitarian Initiative. In 2010, he received a Marie Curie Fellowship, which enabled him to work as a postdoctoral researcher at the MIT Media Lab for three years.
He holds a PhD in Computer Science from the University of Trento.
He also founded Profilio, a startup specializing in computational personality analysis with applications in marketing, human resources, and related fields.
His research interests include computational social sciences, cooperative AI and generative social agents, machine learning, urban computing, and new models for personal data sharing.
Lectures
Topics
Artificial Intelligence, Neural Networks, NeuroevolutionBiography
I am an Artificial Intelligence researcher that aims to make machines more adaptive and creative. My research is focused on computational evolution, deep learning, and crowdsourcing, with applications in robotics, video games, design, and art. I have recently been awarded an ERC Consolidator grant for my project GROW-AI: Growing Machines Capable of Rapid Learning in Unknown Environments.
My research asks questions such as: Can we create lifelong learning machines that continuously acquire new knowledge and skills? Can we grow machines that learn from and work together with humans to solve tasks that neither humans nor machines can solve by themselves?
I am a Professor at the IT University of Copenhagen and a Research Scientist at Sakana AI. I am also a co-founder of modl.ai, a company that develops AI techniques for game development. Our research has been covered in different news outlets such as Science, New Scientist, Wired, Popular Mechanics, The Register, and Popular Science.
https://scholar.google.com/citations?user=Tf8winBIYUsC&hl=en
Lectures
Topics
machine learning, knowledge discovery, artificial intelligenceBiography
Acting director of the Institute of Informatics and Telecommunications, NCSR Demokritos in Athens, Greece.
Voluntary chairman of the board of the Duchenne Data Foundation. Board member & Machine Learning advisor of Langaware Inc. Action editor of the Machine Learning journal.
Area Chair of ECAI 2025.
Lectures
Complex Event Recognition (CER) aims to identify complex, time-evolving situations of interest by detecting temporal and relational patterns in continuously arriving event streams, while Complex Event Forecasting (CEF) seeks to anticipate whether and when such situations will unfold, from early signs. In this talk we introduce the fundamental concepts and challenges of CER/F and present formal approaches based on computational logic and temporal formalisms, such as the Event Calculus and symbolic automata. We will examine how complex event patterns are represented, how they are efficiently matched against high-volume streams, and how they can be combined with probabilistic sequence models to produce forecasts and estimates of their expected occurrence time. The methods will be illustrated through applications such as maritime situational awareness, human activity recognition, transport/mobility monitoring and personalized medicine, demonstrating how CER/F transforms heterogeneous streaming data into timely, actionable knowledge.
Real-world event streams are characterized by noisy perception and epistimic uncertainty, making purely crisp event inference insufficient. In this talk we will present probabilistic approaches to CER/F that associate confidence values with both incoming events and the complex situations inferred from them. We will discuss probabilistic extensions of logical temporal models and explain how possible-world inference can be implemented efficiently through knowledge compilation and weighted model counting. By compiling recurring reasoning structures into reusable computational circuits and by expressing temporal inference through parallel tensor operations, these approaches retain declarative temporal semantics while supporting scalable online data processing under uncertainty. We will also present probabilistic forecasting methods that combine symbolic event patterns with learned stochastic sequence models to estimate both the likelihood and the expected timing of future complex events.
In the last part of the course we will explore how symbolic temporal reasoning and neural learning can be combined to develop CER/F systems that learn from raw data while retaining structured, interpretable models of complex situations. First, we will consider architectures in which neural perception modules detect low-level events from video or sensor streams, while differentiable temporal logic models compose them into complex events. In this setting, the symbolic model acts as a “teacher” for neural perception: supervision available only for high-level complex events can propagate through temporal reasoning to train the underlying perception modules. We will then move beyond predefined event patterns and present neuro-symbolic methods for learning their structure from labelled sequences, including the induction of executable temporal rules and symbolic automata. These approaches combine the adaptability of neural learning with the compositionality, explainability and formal semantics of symbolic CER/F. Finally, we will discuss neuro-symbolic formal verification: establishing whether perturbations of the raw input can propagate through both the neural and symbolic components and alter system-level conclusions or violate safety properties. We will present scalable relaxation and bound-propagation techniques that can provide sound robustness certificates for the complete perception-reasoning pipeline.
Topics
Artificial Intelligence, Data Science, Optimization, Mathematical ModelingBiography
Distinguished Emeritus Professor Panos Pardalos
University of Florida
Panos Pardalos was born in Drosato (Mezilo) Argitheas GR in 1954 and graduated from Athens University (Department of Mathematics). He received his PhD (Computes and Information Sciences) from the University of Minnesota. He is an Emeritus Distinguished Professor in the Department of Industrial and Systems Engineering at the University of Florida, and an affiliated faculty of Biomedical Engineering and Computer Science & Information & Engineering departments. Since 2011 has been the academic advisor at LATNA, HSE.
Panos Pardalos is a world-renowned leader in Global Optimization, Mathematical Modeling, Energy Systems, Financial applications, and Data Sciences. He is a Fellow of AAAS, AAIA, AIMBE, EUROPT, and INFORMS and was awarded the 2013 Constantin Caratheodory Prize of the International Society of Global Optimization. In addition, Panos Pardalos has been awarded the 2013 EURO Gold Medal prize bestowed by the Association for European Operational Research Societies. This medal is the preeminent European award given to Operations Research (OR) professionals for “scientific contributions that stand the test of time.”
Panos Pardalos has been awarded a prestigious Humboldt Research Award (2018-2019). The Humboldt Research Award is granted in recognition of a researcher’s entire achievements to date – fundamental discoveries, new theories, insights that have had significant impact on their discipline.
Panos Pardalos is also a Member of several Academies of Sciences, and he holds several honorary PhD degrees and affiliations. He is the Founding Editor of Optimization Letters, Energy Systems, and Co-Founder of the International Journal of Global Optimization, Computational Management Science, and Springer Nature Operations Research Forum. He has published over 900 papers, and edited/authored over 300 books. He is one of the most cited authors and has graduated 71 PhD students so far. Details can be found in https://faculty.eng.ufl.
Lectures
Tutorial Speakers
Each Tutorial Speaker will hold more than four lessons on one or more research topics.
(TBA)
