NeSy 2026 — Conference Program
September 1–4, 2026 Room 3.2.14
Tuesday, September 1
13:00 — Registration desk
Industry Session 1
14:00–14:10 — Intro
14:10–14:35 — Ontology-Grounded Project Memory for Coding Agents
James Adam
14:35–15:00 — Structural-Semantic Program Synthesis for Information Extraction
Oliver Robert Fox, Aare Puussaar, Jack Sharpe, Luke Hope
15:00–15:25 — Co-Evolving Neurosymbolic Conversation Graphs for Safety-Critical Human-AI Collaboration
Navneet Bhalla
15:25–15:50 — Understanding Before Optimising: A Neuro-Symbolic Benchmark for Multi-Cause Diagnosis in an Industrial Thermal Process
Diego Tuccillo
16:00–16:30 — Coffee break
Industry Session 2
16:30–16:55 — Neuro-Symbolic Industrial Configuration
Danilo Valerio, Philipp Kogler, Stefan Bischof, Thomas Hubauer, Huzefa Rangwala
16:55–17:20 — Neuro-Symbolic AI for Telecommunication: Opportunities and Challenges
Klaus Raizer, Swarup Kumar Mohalik, Marin Orlic, Jishnu Sadasivan, Ankita Likhyani, Konstantinos Vandikas, Aneta Vulgarakis Feljan
17:20–18:00 — NeSy Industry Panel Discussion
Leilani Gilpin (UC Santa Cruz), Martin Schaef (Amazon), Sebastian Monka (Bosch), Danilo Valerio (Siemens), Luke Hope (Onteric); moderated by Patrik Schneider (Siemens)
Wednesday, September 2
08:30–09:00 — Registration desk / poster setup
09:00–09:30 — Opening
Keynote
09:30–10:30 — Kanna Shimizu, Neural and Symbolic: Friend or Foe?
Amazon Web Services
10:30–11:30 — Coffee break + posters
Session 1 — Learning for Constrained Search and Optimization
11:30–11:50 — Sample-efficient Neurosymbolic Proximal Policy Optimization
Simone Murari, Celeste Veronese, Daniele Meli
11:50–12:10 — Learning to Assemble Novel Structures with Unfamiliar Parts under Semantic Constraints
Jonghyuk Park, Alex Lascarides, Subramanian Ramamoorthy
12:10–12:30 — LLM-Guided Graph Generation for Structure-Based Local Improvement Methods
Hai Xia, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider
12:30–14:30 — Lunch break
Session 2 — Neuro-Symbolic Reasoning under Constraints
14:30–14:50 — DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs
Saimun Habib, Vaishak Belle, Fengxiang He
14:50–15:10 — Learning Deep Generative Models under Hard Linear Equality Constraints
Ruoyan Li, Dipti Ranjan Sahu, Guy Van den Broeck, Zhe Zeng
15:10–15:30 — From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles
Paulius Skaisgiris, Thomas Pammer, Veronika Semmelrock, Mykyta Ielanskyi, Maximilian Heisinger, Erich Kobler
15:30–15:40 — SoftReason: A Fully Differentiable Deductive Reasoning Architecture over High-Dimensional Perceptual Data
Wael AbdAlmageed
15:40–15:50 — LLM-guided semantic vtrees for SDD compilation
Alexis de Colnet, Stefan Szeider
15:50–16:00 — NeSyCat Torch: A Differentiable Tensor Implementation of Neuro Symbolic Categories
Daniel Romero Schellhorn, Till Mossakowski, Björn Gehrke
16:00–16:10 — Neurosymbolic Constraint Learning: A Short Survey
Quinten Dewulf, Annegret Seibt, Simon Odense, Zsolt Zombori, Luc De Raedt
16:10-19:00 — Cocktails + posters
Posters — September 2
- Constraint-Satisfying Reinforcement Learning via a Neuro-Symbolic Projection Layer
Jacob Brand, Francesco Belardinelli, Eleonora Giunchiglia - Adaptive GR(1)-Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning
Tiberiu-Andrei Georgescu, Alex Goodall, Francesco Belardinelli, Dalal Alrajeh, Sebastian Uchitel - Abstraction and Knowledge in Reinforcement Learning: Evaluating Concept Grounding on Craftax
Max Adamski - Neurosymbolic Discovery of Algebraic Graph Constructions
David Seka, Stefan Szeider - A Neuro-symbolic Approach to Inverse Design of Thin-layer Metamaterials Under Layout Constraints
Carlo Adornetto, Marco Duca, Francesco Gallo, Gianluigi Greco, Antonio Ielo, Francesco Ricca, Simone Ventrici - Generate in the Chart, Not on the Boundary: Function-Symbol Grounding for Hard Constraints in LTN-GANs
Nijesh Upreti, Vaishak Belle - Polyhedral Rule Extraction from ReLU Classifiers
Sebastian Bader, Artur d’Avila Garcez - Improving Interpretability and Accuracy in Neuro-Symbolic Rule Extraction Using Class-Specific Sparse Filters
Parth Padalkar, Jaeseong Lee, Shiyi Wei, Gopal Gupta - Alternate Training Procedures for Neural Logic Networks
Vincent Perreault, Richard Labib, Alain Hertz - Galois Connected Autoencoders as Learnable Adjunctions
Jacqueline Mitchell, Chao Wang - Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
Hai Xia, Carla P Gomes, Bart Selman, Stefan Szeider - Uncertainty Quantification Employing Evidence Theory and Temporal Reasoning for Video Scene Classification
Giulia Murtas, Veselka Boeva, Elena Tsiporkova - Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning
Sparsh Tiwari, Bettina Finzel, Gesina Schwalbe - Contrastive Learning with Paraphrasing and Negation
Kwun Ho Ngan, Saman Sadeghi Afgeh, Artur d’Avila Garcez, Joe Townsend - Neuro-Symbolic Temporal Question Answering for Explainable Prognostics and Health Management
Nirban Das, Rashmi Baruah
Thursday, September 3
08:30–09:00 — Registration desk / poster setup
Keynote
09:00–10:00 — Antonio Vergari, Things people don’t tell you about NeSy AI
University of Edinburgh
10:00–11:00 — Coffee break + posters
Session 1 — Formal Reasoning, Logic & LLMs
11:00–11:20 — Steering Aesop for Theorem Proving: Learning to Configure Symbolic Solvers via Multi-Source Neurosymbolic Feedback
Kai-Yuan Jeng, Ru-Jun Wang, Wen-Tsuen Chen
11:20–11:40 — Distilling Answer Set Programming Theories from Large Language Models
Nelson Higuera Ruiz, Markus Hofmarcher, Claudiu Leoveanu-Condrei
11:40–12:00 — Can Transformers Perform LTLf Strategic Reasoning? Sometimes
Giuseppe De Giacomo, Antonio Di Stasio, Eleonora Giunchiglia, Eleni Kougioumtzi
12:00–12:10 — Program Semantic Inequivalence Game with Large Language Models
Antonio Valerio Miceli Barone, Vaishak Belle, Ali Payani
12:10–12:20 — Converting Language to Logic: Pipeline Shape for Prover-Checked Commonsense Question Answering
Tanel Tammet, Otto Mättas, Enrico Vompa
12:20–12:30 — Reasoning with Tensor Networks: Solving with Local Contractions
Martin Eigel, Alex Goessmann, Janina Enrica Schütte
12:30–14:30 — Lunch break
Session 2 — Foundations, Capabilities & the State of Neuro-Symbolic AI
14:30–14:50 — ClosureBench: A Benchmark for Reasoning under Closure Assumptions
Francesco Belardinelli, Flavio Corradini, Matteo Leonesi
14:50–15:10 — From Hybrid Mechanistic–Data-Driven Modeling Toward Neuro-Symbolic AI: What, Why, and How
Moein E. Samadi, Andreas A. Schuppert
15:10–15:20 — Is Neurosymbolic AI Winning? Analysing Current Progress and Future Challenges
Martí Ejarque, Zoe Falomir
15:20–15:30 — Emergent Symbolic Structure in Boolean World Models: an Interpretability Analysis
Davide Bizzaro, Luciano Serafini
15:30–15:40 — Pretrain on Small Synthetic Data, Scale Large for Free: Symmetry-Aware Foundation Model for Logic Rule Induction
Yin Jun Phua
15:40–15:50 — Modal Logic Neural Networks
Antonin Sulc, Noor Naddour
15:50–16:10 — Hybrid Neurosymbolic Knowledge Enforcement: Integrating Ontologies, Statistics, and LLM Agents for Industrial Data Validation
Nicolai Schoch, Mohamed Elsheikh, Sebastian Palacio, Thilo Braun
16:10-18:00 — Coffee break + posters
Posters — September 3
- Exploring Retrieval-Augmented Neurosymbolic Generation of HTN Domain Models Using LLMs
Varun Rajesh Bhat, Ilche Georgievski - Neurosymbolic Program Synthesis for the Abstraction and Reasoning Corpus using Vector Symbolic Algebras
Isaac Joffe, Chris Eliasmith - Symbolic Constraints Improve Metacognitive Efficiency in Neuro-Symbolic AI
Michael Clopton, Sven Thijssen - AWARD: Encoding Text Guidelines as ASP Code using LLM Agents
Abhiramon Rajasekharan, Gopal Gupta - G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
Timo Bertram, Sidhant Bhavnani, Richard Freinschlag, Erich Kobler, Andreas Mayr, Günter Klambauer - Distilling Formal Logic into Neural Spaces: A Kernel Alignment Approach for Signal Temporal Logic
Sara Candussio, Gabriele Sarti, Gaia Saveri, Luca Bortolussi - PASTA-G: Tractable Grammar Control of Large Language Models
Max Scribner, Antonio Vergari, Vaishak Belle - A homotopy-type-theoretic generalization of neurosymbolic inference
Fernando Zhapa-Camacho, Robert Hoehndorf - Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming
Zirong Chen, Meiyi Ma
19:00 — Downtown walking tour (details soon)
Friday, September 4
08:30–09:00 — Registration desk / poster setup
Keynote
09:00–10:00 — Francesca Toni, Neuro-argumentative learning
Imperial College London
10:00–11:00 — Coffee break + posters
Session 1 — Ontologies, Knowledge Graphs & Semantic Representation
11:00–11:20 — Soft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning
Tengwei Song, Robert Hoehndorf
11:20–11:40 — Neuro-symbolic learning over OWL 2 DL via consequence-based compilation to differentiable circuits
Olga Mashkova, Asaad Mohammedsaleh, Fernando Zhapa-Camacho, Robert Hoehndorf
11:40–12:00 — CORE-LLM-Bench: A Benchmark Dataset for Evaluating Complex Ontological Reasoning Capabilities of Large Language Models
Julie Loesch, Sara Falahatkar, Nicole Makayla Kilk, Rishabh Jakhar, Raghava Mutharaju, Michel Dumontier, Remzi Celebi
12:00–12:10 — A hierarchy of faithfulness criteria for knowledge base completion
Olga Mashkova, Robert Hoehndorf
12:10–12:20 — Hierarchy-Aware Semantic Losses for Knowledge Graph Link Prediction
Filip Kronström, Ross D. King
12:20–12:30 — Faithful Box Embeddings for Linear Temporal EL+
Daniel Hernández, Jiaxin Pan, Osama Mohammed, Ratan Bahadur Thapa, Steffen Staab
12:30–14:30 — Lunch break
Session 2 — Neuro-Symbolic AI for Knowledge-Rich Applications
14:30–14:50 — A Neurosymbolic Approach for Explainable Early Diagnosis of Alzheimer’s Disease
Ranveer Singh, Pranuthi Tenali, Saurabh Mathur, Ameet Soni, Vaishali Phatak, Karla Lynch, Daniel Murman, Matthew Rizzo, Sriraam Natarajan
14:50–15:00 — The Bigger Picture: Neuro-Symbolic Knowledge Graph Enrichment and Anticipatory Inference from Multimodal Content
Stefano De Giorgis, Guendalina Righetti, Mihai Pomarlan, Nikolaos Tsiogkas, Maria M Hedblom, Mena Leemhuis, Oliver Kutz
15:10–15:20 — Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP
Jann Pfeifer, Debayan Banerjee, Ricardo Usbeck
15:20–15:30 — Noema: A Neuro-Symbolic Framework for Accountable Conversational AI through Semantic Invariance
Jose F Quesada
15:30–15:40 — Interpretable Moral Decision-Making under Epistemic Uncertainty
Jessica Ciupa, Vaishak Belle, Antonia Sewell
15:30–15:40 — Town Hall
16:00-17:30 — Coffee break + posters
Posters — September 4
- Soft Symbol Grounding for Prototypical Concepts
Marcos Galván-López, Nijesh Upreti, Vaishak Belle, Carlos Aguilar-Ibáñez, Hiram Calvo - NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
Jonas Gann, Michael Gertz - The Question Is a Region: A Neurosymbolic Retrofit for Categorical Question Answering over Rule Engines
Martin Schaef, Tancrède Lepoint, Willem Visser, Liana Hadarean - Dynamic Evidential Routing: A Neurosymbolic Transformer Interface for Calibrated Clinical Prediction Under Extreme Missingness
Arjun Vijay Prakash - Constraint-Guided Enterprise Data Mapping with Large Language Models
Sebastian Monka, Pramod Anantharam, Vo Minh Thien, Lavdim Halilaj - Lightweight Neurosymbolic Edge AI for Wearable Health Monitoring — A Case Study in Intoxication Detection
Manuel E. Segura, Richard Ky, Hamza Errahmouni Barkam, Raj Mohanty, Sergio Gago-Masague, Mohsen Imani - CASSANDRA: Programmatic and Probabilistic Reasoning and Inference for Stochastic World Modeling
Panagiotis Lymperopoulos, Abhiramon Rajasekharan, Ian Berlot-Attwell, Stéphane Aroca-Ouellette, Kaheer Suleman - An Agentic Framework for Neuro-Symbolic Programming
Aliakbar Nafar, Chetan Chigurupati, Danial Kamali, Hamid Reza Karimian, Parisa Kordjamshidi
17:30-18:00 — Awards & Closing
Online Presentations
- How Compliant Is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generating Clinical Compliance Insights
HIMANSHU TRIPATHI, Kaushik Roy, Subash Neupane, Shahram Rahimi - SWP: Repairing Neuro-Symbolic Reasoning Shortcuts via Satisfaction-Witness Propagation
ZhengYi Ma, Ji Wang - Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis
Moumita Sen Sarma, Pascal Hitzler, Eugene Vasserman - SymAlign-UAST: Neuro-Symbolic Code Understanding via Hyperbolic Geometry and Structural Invariance
Kwangje Baeg, Hoyeob Kim, Janaina Villacis - ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming
Iman Sharifi, Peng Wei, Saber Fallah
Tips
Lunch is not included in the conference, but there are several closeby lunch options. 20+ options less than 30min. walk/5min. taxi/uber in this map.