The workshop consists of a single half day of activities, including one keynote speech, and poster sessions. The workshop will be held on Sunday October 26th (2nd workshop day) in the afternoon starting at 14:00. The allocated room is “Aula 6.2” at the Engineering School of University of Bologna (notice that this is different from the main conference location). Authors should note that all accepted papers will be presented as posters.
Detailed Schedule
| 14:00 - 14:15 | Opening Session by Organizing Committee |
| 14:15 - 15:15 | Keynote Talk |
| Speaker: Dr. Daria Stepanova, Bosch Center for AI, Germany | |
| Title: "Towards Unlocking Industrial Potential with Neuro-Symbolic AI at Bosch: Opportunities and Challenges" | |
| Abstract: Neuro-symbolic AI combines the data-driven strengths of machine learning with the logical reasoning and transparency of symbolic systems, offering a transformative approach for industrial applications. While significant progress has been made in academic research, industrial adoption remains in its early stages. In this talk, I will present our journey at Bosch in trying to bridge the gap between research and real-world use cases, focusing on the combination of Answer Set Programming (ASP) and Knowledge Graphs with machine learning methods, e.g., large language models. I will present our attempts to apply these hybrid AI approaches in diverse domains such as conceptual system configuration, production optimization, and market analysis, while also highlighting key open research questions. Part of the work presented in this talk is the result of a collaboration between Bosch and the Vienna University of Technology. | |
| 15:15 - 15:30 | Keynote Q&A |
| 15:30 - 16:00 | Coffee Break ☕ |
| 16:00 - 16:40 | First Poster Session: |
| 3. "A Survey of Brain-Inspired Mechanisms for Neuro-Symbolic Reasoning" | |
| 4. "Neurosymbolic AI for GNN Explainability: A Survey" | |
| 5. "Logic Meets Attention: A Neuro-symbolic Approach to Vibration Fault Detection" | |
| 6. "Semantically Enriched Datasets for Link Prediction: DB100k+, NELL-995+ and YAGO3-10+" | |
| 7. "Neuro-symbolic Complex Event Recognition in Autonomous Driving" | |
| 8. "Neuro-Symbolic Logical Reasoning with Textual Entailment" | |
| 9. "Explaining CNN Classifications Using Small Patches" | |
| 10. "VectorGraphRAG: Automatic Knowledge Graph Construction and Memory Efficient Triplet Ranking for Medical Question Answering" | |
| 11. "Exploring Neuro-Symbolic AI for Facial Emotion Recognition" | |
| 12. "Towards Interpretable Concept Learning over Time Series via Temporal Logic Semantics" | |
| 13. "A Challenging Dataset of Jet Engine Fault Scenarios" | |
| 15. "Enhancing Large Language Models through Neuro-Symbolic Integration and Ontological Reasoning for Automotive Maintenance" | |
| 17. "Graph Against the Machine: a Neuro-Symbolic Approach for Enhanced Video Question Answering" | |
| 16:40 - 17:20 | Second Poster Session: |
| 18. "Neuro-Symbolic Learning from Temporal Sequences in Safety-Critical Systems" | |
| 19. "On Planning Through LLMs" | |
| 20. "Transparent Visual Reasoning via Object-Centric Agent Collaboration" | |
| 21. "A domain-specific language for NeSy focussing on symbolic knowledge injection" | |
| 22. "Neuro-Argumentative Machine Learning with Legal Text" | |
| 23. "R-PlanGPT: Neuro-Symbolic Plan Generation via Transformer-based Language Models" | |
| 25. "A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design" | |
| 26. "Discovering Association Rules in High-Dimensional Small Tabular Data" | |
| 28. "Single Domain Generalization in Diabetic Retinopathy: A Neuro-Symbolic Learning Approach" | |
| 29. "HyDRA: A Hybrid-Driven Reasoning Architecture for Verifiable Knowledge Graphs" | |
| 30. "Constraint-Guided PINNs: A Constrained Optimization Approach" | |
| 31. "Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning" | |
| 17:20 - 17:30 | Closing Remarks by Organizing Committee |
Note for papers’ authors: We request authors to adhere to the poster session schedule. Authors of the second poster session should read the posters and ask questions to the auhtors of the first poster session and vice-versa. We kindly ask all the authors to attach their posters during the opening session of the workshop. Late authors can attach their posters during the keynote Q&A. The boards used to attach posters will be made available by the workshop organizers.