Back to top

16 – 18 September 2026 · Universitat Politècnica de València

Conference programme

Provisional programme. Times and the fourth keynote are subject to change; the final version will be published before the conference.

Wednesday16 Sep 2026

09:00 – 09:20

Welcome and Opening

09:20 – 10:20
Keynote 1

Prof. Stephen Muggleton FREng (Imperial College London and Nanjing University)

Are AI's key challenges solved?

Abstract

Generative Pre-trained Transformer models (GPT) are a form of Large-Language-Model (LLM) which has attracted wide-scale interest based on general open-ended query-answering. In this talk I will look at remaining challenges for the field of Artificial Intelligence. In particular, I will argue that although widely available LLM systems partially address Alan Turing's “Imitation Game” [1950 paper in the Journal Mind], now called the “Turing Test”, they fall short of the “Super Criticality Challenge” which Turing provided within the same paper. While Turing's paper initiated modern discussions on these topics, it was John McCarthy [1956] who named the field “Artificial Intelligence”. In a 2006 keynote speech at the Inductive Logic Programming conference (Santiago de Compostela), McCarthy introduced a “Discovery Challenge” which is closely related to Turing's Supercriticality. I will exemplify a range of human discoveries in Science, Engineering and Mathematics, and argue that neither Turing's nor McCarthy's challenges are addressed by existing LLM techniques. By contrast, to enable progress on Discovery Systems, further work is required on development of methods for identifying and explaining rare phenomena. Some initial work and directions for further studies will be described.

Session 1
Explanation, Concepts and Comprehensibility
10:20 – 10:40

#8Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy

Lun Ai, Johannes Langer, Ute Schmid, Stephen Muggleton

EMBL-EBI; University of Bamberg; Imperial College London

10:40 – 11:10

Coffee break

11:10 – 11:30

#1Explainable Symbolic Constraint Reasoner

Dominique Bouthinon, Junkang Li, Véronique Ventos

LIPN, Université Sorbonne Paris Nord; NukkAI

11:30 – 11:50

#9Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach

Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker

SIMULA; LISN CNRS, Paris-Saclay University

11:50 – 12:10

#13Assessing Reliability of Symbol Detection in Concept Bottleneck Models

Javier Fumanal Idocin, Javier Andreu-Perez

Public University of Navarre; University of Essex

12:10 – 12:30

#20Enhancing Explainable AI: A Gaussian Mixture Approach to Numerical-Symbolic Reasoning

Daniel Cyrus, Alireza Tammaddoni Nezhad

University of Surrey

12:30 – 12:50

#18An Investigation into Interpretable Embeddings Resulting from Large Logical Rule Sets

Phuong Huynh, Johannes Fürnkranz, Florian Beck

Institute for Application-Oriented Knowledge Processing (FAW), JKU

13:00 – 14:30

Lunch

14:30 – 15:30
Keynote 2

Laurent Orseau (Google DeepMind)

Levin Tree Search: Search-and-Learn with Formal Guarantees via Time Sharing

Abstract

Solving complex combinatorial problems from scratch requires a tight integration between learning and search. This keynote presents the Levin Tree Search (LTS) family of algorithms and analyzes their performance guarantees using the simple yet fundamental concept of time-sharing. We show how allocating computational budgets based on policy and heuristic quality can be used to provide strict bounds on the number of node visits before finding a solution. We then describe how these algorithms operate within a search-and-learn bootstrap paradigm to solve combinatorial problems without prior knowledge, using only a training set of unsolved instances of varied difficulty. We introduce in particular the √LTS (root-LTS) algorithm, which extends the time-sharing perspective to all nodes in a search tree. By distributing the computational budget among multiple concurrent searches rooted at different nodes, √LTS implicitly decomposes the original problem into smaller subtasks. We present formal guarantees showing that this rerooting mechanism provides exponential speedups over standard LTS. Speaker bio

Session 2
Search and Efficiency in Rule Learning
15:30 – 15:50

#27Bottom-Clause Reduction Using Definitional Redundancy for Efficient Hypothesis Search

Dany Varghese, Alireza Tamaddoni-Nezhad

University of Surrey

15:50 – 16:10

#7FedPopper: Federated Learning Logic Programs from Aggregated Failures

Yasmine Akaichi, Jean-Marie Jacquet, Isabelle Linden, Wim Vanhoof

UNamur

16:30 – 17:00

Orxata

17:15 – 20:00

Guided visit

Full papers are allocated 20 minutes including questions. Short papers — late-breaking papers, recently published papers and demos — are allocated 15 minutes. Session chairs will be announced closer to the conference.