Documents

Actions Registration Registration Fees Deadlines and Policies Submit Abstract Submit Paper Guidelines Preparing your Presentation Templates Glossary AI Tools Author's Login Reviewer's Login Ethics of Review Information Conference Details Important Dates Technical Program Social Event Call for Papers Program Committee Event Chairs Keynote Lectures Best Paper Awards Satellite Events Workshops Special Sessions Tutorials Demos Panels Travel and Accommodation Conference Venue About the Region Reaching the City Visa Information Hotel Reservation Partners Academic Partners Industrial Partners Institutional Partners Media Partners Partner Events Publication Partners Previous Conferences Websites Abstracts Invited Speakers Awards Books Published

Keynote Lectures

Available Soon
Sarit Kraus, Bar-Ilan University, Israel, Israel

Loosely Coupled Architectures for Neuro-symbolic Systems: Combining Learning and Reasoning
Frank van Harmelen, Vrije Universiteit Amsterdam, Netherlands, Netherlands

Alter3’s Inner Voices. Identity and Self-Awareness in Embodied AI.
Luc Steels, Free University of Brussels, VUB AI Lab, Brussels, Belgium, Belgium

Available Soon

Sarit Kraus
Bar-Ilan University, Israel
https://www.cs.biu.ac.il/~sarit

Brief Bio
Sarit Kraus is a Professor of Computer Science at Bar-Ilan University. Her research focuses on intelligent agents and multi-agent systems that integrate machine learning (including LLMs) with optimization, logic, and game theory. She develops agents capable of interacting effectively with people and robots. She has received many honors, including the IJCAI Computers and Thought and Research Excellence Awards, ACM SIGART and Athena Lecturer Awards, the EMET Prize, and two IFAAMAS Influential Paper Awards. A Fellow of ACM, AAAI, and EurAI, she also received an ERC Advanced Grant and a commendation from LA for the ARMOR system. Kraus has published over 400 papers, co-authored five books, chaired IJCAI-2019, will chair IJCAI-2027, and is a member of the Israel Academy of Sciences.

Abstract
Available Soon

Loosely Coupled Architectures for Neuro-symbolic Systems: Combining Learning and Reasoning

Frank van Harmelen
Vrije Universiteit Amsterdam, Netherlands

Brief Bio
Frank van Harmelen has a PhD in Artificial Intelligence from Edinburgh University, and has been professor of AI at the Vrije Universiteit since 2001, where he leads the research group on Knowledge Representation. He was one of the designers of the knowledge representation language OWL, which is now in use by companies such as Google, the BBC, New York Times, Amazon, Uber, Airbnb, Elsevier, Springer Nature, XMP, and Renault among others. He co-edited the standard reference work in his field (The Handbook of Knowledge Representation), and received the Semantic Web 10-year impact award ifor his work on the open source software Sesame (over 200.000 downloads). He is a Fellow of the European Association for Artificial Intelligence, member of the the Dutch Royal Academy of Sciences (KNAW), of The Royal Holland Society of Sciences and Humanities (KHWM) and of the Academia Europaea, and is adjunct professor at Wuhan University and Wuhan University of Science and Technology in China.

Abstract
It is becoming increasingly clear that a proper understanding of computational forms of intelligence will not come from either purely data-driven learning systems, or from purely knowledge-based reasoning systems. The former are overly data hungry, not transparent, they generalize poorly and are not designed for online learning; while the latter are difficult to scale and not robust to noise. Neuro-symbolic AI is promising to combine the best of these two worlds, and research into this approach is booming. I will discuss how to build neuro-symbolic systems out of loosely coupled components that are configured in repeatable design patterns.

Alter3’s Inner Voices. Identity and Self-Awareness in Embodied AI.

Luc Steels
Free University of Brussels, VUB AI Lab, Brussels, Belgium

Brief Bio
Luc Steels studied computer science and AI at MIT (USA) and became a professor of Artificial Intelligence (AI) at the University of Brussels (VUB) in 1983. He founded the VUB AI Lab. In 1996, Steels founded the Sony Computer Science Laboratory in Paris. From 2011, he became an ICREA research fellow at the Institute for Evolutionary Biology (UPF-CSIC) in Barcelona. From 2022, he worked in Venice at Ca’Foscari University and Venice International University. He is now prof. emeritus at the University of Brussels (VUB). Steels pursued his interests in many areas of AI, including knowledge-based systems, behavior-based robotics, Artificial Life, computational linguistics, and music. Most recently, he has been focusing on self-awareness in embodied AI and on the history of AI. His recent book is on the latter topic (https://zenodo.org/records/18205480).

Abstract
Given the advances in chatbots and embodied AI, many observers wonder whether it is possible for AI-enhanced robots to achieve a form of awareness and even self-awareness, and why that might be useful. This talk introduces a concrete experiment that explores this possibility. It has been carried out with Takashi Ikegami and his team from the University of Tokyo, featuring the android robot Alter3. Alter3 has been installed in a major exhibition (the Venice biennale 2025) where people could interact about any topic and in any language with the robot. The cognitive architecture of Alter3 implements internally a Minskyan ’Society of Mind’ model in which modules operate autonomously and in parallel to achieve the many functions that are needed (vision, motor control, speech, memory, task planning, etc.) without a central pre-determined control flow. The talk argues that awareness is crucial for achieving and maintaining coherence between these concurrent distributed modules, both in the short-term (for example, to keep focused on the topic of a conversation) and in the long-term (for maintaining a persistent personal identity). The critical breakthrough of this experiment has come from using natural language not only for communication with the viewer but also internally as Interlingua for the communication between the modules and for the construction and usage of an episodic memory. This has become possible today by the use of LLMs. Awareness is realized as a self-organized process through a shared blackboard. Because all messaging is through language, we are able to understand the ‘inner voices’ of Alter3 and follow what is going on. The outcome of the experiment is unexpected and fascinating.