KLR 2027 is honored to host a distinguished lineup of keynote and invited speakers who are leading experts at the intersection of knowledge representation, machine learning, and automated reasoning. Their talks will explore how symbolic knowledge and data-driven learning can be integrated—from probabilistic knowledge representation and neuro-symbolic learning to planning with large language models and knowledge-graph-based reasoning.
University of California, Berkeley, USA
FRS, OBE; co-author of Artificial Intelligence: A Modern Approach
Prof. Russell’s research spans machine learning, probabilistic reasoning, knowledge representation, and planning. This keynote will discuss how probabilistic programming and first-order probabilistic languages can unify logical knowledge representation with data-driven learning and reasoning under uncertainty.
Imperial College London, UK
Professor of Applied Computational Logic
Prof. Russo leads the SPIKE group and works on symbolic machine learning and neuro-symbolic AI. Her talk will present Learning from Answer Sets (LAS) and show how interpretable symbolic models can be combined with statistical learning for robust neuro-symbolic solutions.
The University of Melbourne, Australia
Automated Planning, LLM-Symbolic Reasoning
Prof. Lipovetzky’s work bridges automated planning and LLM reasoning. This talk will explore how planning abstractions and knowledge augmentation can help LLMs find structure in queries and enhance compositional reasoning beyond training data.
IBM, USA
VP of Foundations of AI, IBM; leads Neuro-Symbolic AI research
Dr. Gray leads IBM’s global neuro-symbolic AI program. His keynote will introduce Logical Neural Networks, a framework that establishes a one-to-one correspondence between neurons and logic gates in real-valued logic, enabling exact logical deduction and contradiction-aware learning within neural architectures.
Call for Speakers: We are actively seeking outstanding researchers to deliver invited talks at KLR 2027. If you are interested in presenting your work at the intersection of knowledge representation, learning, and reasoning, please submit an abstract via our online system or contact the secretariat at contact_klr@163.com for more details.