Schedule
Monday, September 8, 2025
|
08:00 - 09:30 |
Light breakfast/coffee and socializing
|
|
|
09:30 - 09:45 |
Welcome
|
Organizers
|
|
09:45 - 11:00 |
Keynote - Symbolic Reasoning in the Age of Large Language Models
Today, reasoning is commonly interpreted as large language models generating chains of thought. Yet historically, AI reasoning had a very different meaning: executing algorithms that manipulated symbols to perform logical or probabilistic deduction and derive definite answers to questions about knowledge. In this talk, I show that such old-fashioned ideas are very relevant to reasoning with large language models today. In particular, I will demonstrate that integrating symbolic reasoning algorithms directly into the architecture of language models enables state-of-the-art capabilities in controllable text generation, alignment, and mathematical reasoning. These capabilities are built on top of tractable probabilistic circuit models that approximate the distribution of the large language model’s future behavior, and allow for efficient reasoning on the GPU. I will further show that the same ideas naturally extend to neurosymbolic offline reinforcement learning and image diffusion. |
|
|
11:15 - 12:00 |
Oral presentations
|
Chair: Michael Cochez
|
|
12:00 - 13:30 |
Lunch
|
|
|
13:30 - 14:45 |
Keynote - Do World Models need Objects?
Objects in some sense are the “symbols” of the physical world. They play an important role in human cognition, perception, and in our interaction with the world. In the context of generative AI, this raises the question whether objects will need some special treatment when developing models that learn about the physical world. This talk will touch upon this question from multiple angles: from object representation learning, object-centric architectures to object-centric control of generative models. |
|
|
14:45 - 15:00 |
Break
|
|
|
15:00 - 17:00 |
Posters Session 1 and reception
See below for the list of posters. |
|
|
17:00 - 19:00 |
Buses to Dream Inn
|
|
|
18:30 - 21:00 |
Welcome reception at Dream Inn
|
|
Tuesday, September 9, 2025
|
08:00 - 09:30 |
Light breakfast/coffee and socializing
|
|
|
09:30 - 10:30 |
Oral presentations
|
Chair: Mena Leemhuis
|
|
10:30 - 10:45 |
Break
|
|
|
10:45 - 11:45 |
Oral presentations
|
Chair: Francesca Toni
|
|
11:45 - 12:00 |
Test of Time Award - Probabilistic Inference Modulo Theories
|
Rodrigo de Salvo Braz
|
|
12:00 - 13:30 |
Lunch
|
|
|
13:30 - 14:45 |
Keynote - Graph-powered Hybrid AI
|
|
|
14:45 - 15:00 |
Break
|
|
|
15:00 - 17:00 |
Poster Session 2 and reception
See below for the list of posters. |
|
|
15:00 - 17:00 |
OPTIMAS × NeSy 2025 Hackathon — Kickoff & Registration
Brief kickoff for the OPTIMAS × NeSy Hackathon. We’ll introduce three tracks and the two-phase timeline that runs beyond NeSy (Approach → finalists → Build), explain how to register, and answer general questions. Materials and rules will be available on the OPTIMAS site at launch: https://hackathon.optimas.ai. (No judging or submissions occur during this session.) |
|
|
17:00 - 18:00 |
Buses to Dream Inn
|
|
Wednesday, September 10, 2025
|
08:00 - 09:30 |
Light breakfast/coffee and socializing
|
|
|
09:30 - 10:30 |
Oral presentations
|
Chair: Roberto Confalonieri
|
|
10:45 - 11:00 |
Break
|
|
|
10:45 - 12:00 |
Oral presentations
|
Chair: Alessio Lomuscio
|
|
12:00 - 13:30 |
Lunch
|
|
|
13:30 - 14:20 |
Industry Session
|
Chair: Luis Lamb
|
|
14:20 - 16:00 |
Poster Session 3 and reception
See below for the list of posters. |
|
|
14:45 - 16:00 |
OPTIMAS × NeSy 2025 Hackathon — Technical Q&A / Office Hours
Deep-dive Q&A with the OPTIMAS team on datasets/APIs, ontology schema, example queries, evaluation, and the online submission process. Intended for attendees planning to participate after NeSy. (Project work and selection occur after the conference, per the published timeline.) |
|
|
16:00 - 17:00 |
Awards, announcements, and Townhall session
|
Organizers
|
|
17:00 - 18:00 |
Buses to Dream Inn
|
|
Poster Session Mon September 8th
Main Track
- SymDQN: Symbolic Knowledge and Reasoning in Neural Network-based Reinforcement Learning (Ivo Amador, Nina Gierasimczuk). Long Paper, OpenReview link
- Neurosymbolic models based on hybrids of convolutional neural networks and decision trees (Rasul Kairgeldin, Miguel Á. Carreira-Perpiñán). Long Paper, OpenReview link
- High Quality Embeddings for Horn Logic Reasoning (Yifan Zhang, Yasir White, Dean Clark, Joseph Sanchez, Jevon Lipsey, Ashely Hirst, Jeff Heflin). Long Paper, OpenReview link
- mULLER: A Modular Monad-Based Semantics of the Neurosymbolic ULLER Framework (Daniel Romero Schellhorn, Till Mossakowski). Long Paper, OpenReview link
- Disentangling Neural Disjunctive Normal Form Models (Kexin Gu Baugh, Vincent Perreault, Matthew Baugh, Luke Dickens, Katsumi Inoue, Alessandra Russo). Long Paper, OpenReview link
- Hierarchical Neuro-Symbolic Decision Transformer (Ali Baheri, Cecilia Alm). Long Paper, OpenReview link
- Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty? (Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi). Long Paper, OpenReview link
- Neurosymbolic Reasoning Shortcuts under the Independence Assumption (Emile van Krieken, Pasquale Minervini, Edoardo Ponti, Antonio Vergari). Long Paper, OpenReview link
- Neural-Symbolic Architectural Axioms of Integration: A Manifesto (Connor Pryor, Lise Getoor). Long Paper, OpenReview link
- Which AI Do We Trust? NeuroSymbolic AI in Healthcare (Jans Aasman; Franz Inc.). Industry Abstract, Paper link
- Knowledge Augmented Graph Reasoner (KAGR): A Neuro-Symbolic Approach to Instruction Adherence in Healthcare AI (Ravi Bajracharya, Aniwaa Owusu-Obeng, Aris Saoulidis, Xeno Acharya, Chris Wai Hang Lo, Arun Bajracharya, Dhurba Bhandari; datum.md). Industry Abstract, Paper link
Neurosymbolic Generative Models
- SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query Routing (Safayat Bin Hakim, Muhammad Adil, Alvaro Velasquez, Houbing Herbert Song). Long Paper, OpenReview link
Knowledge Graphs, Ontologies and Neurosymbolic AI
- Talking to GDELT Through Knowledge Graphs (Audun D Myers, Max Vargas, Sinan Guven Aksoy, Cliff Joslyn, Benjamin Wilson, Lee Burke, Tom Grimes). Long Paper, OpenReview link
- Understanding the Expressive Capabilities of Knowledge Base Embeddings under Box Semantics (Mena Leemhuis, Oliver Kutz). Long Paper, OpenReview link
Neurosymbolic Methods for Trustworthy and Interpretable AI
- Object-Centric Neuro-Argumentative Learning (Abdul Rahman Jacob, Avinash Kori, Emanuele De Angelis, Ben Glocker, Maurizio Proietti, Francesca Toni). Long Paper, OpenReview link
- Towards Explainable Depression Detection: A Neurosymbolic Approach to Uncover Social Media Signals with Generative AI (Mohammad Saeid Mahdavinejad, Peyman Adibi, Amirhassan Monajemi, Pascal Hitzler). Long Paper, OpenReview link
- A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning (Michael K. Chen). Long Paper, OpenReview link
- Concept Probing: Where to Find Human-Defined Concepts (Manuel de Sousa Ribeiro, Afonso Leote, Joao Leite). Long Paper, OpenReview link
- Bridging Neural and Symbolic Computation: A Learnability Study of RNNs on Counter and Dyck Languages (Neisarg Dave, Daniel Kifer, C. Lee Giles, Ankur Mali). Long Paper, OpenReview link
- MC3G: Model Agnostic Causally Constrained Counterfactual Generation (Sopam Dasgupta, Sadaf MD Halim, Joaquín Arias, Elmer Salazar, Gopal Gupta). Long Paper, OpenReview link
- CRAFT: A Neuro-Symbolic Framework for Visual Functional Affordance Grounding (Zhou Chen, Joe Lin, Sathyanarayanan N. Aakur). Short Paper, OpenReview link
- Act-to-Ground: A Framework for Symbol Grounding in Planning Domains (Panagiotis Lymperopoulos, Liping Liu). Long Paper, OpenReview link
- KEA Explain: Explanations of Hallucinations using Graph Kernel Analysis (Reilly Haskins, Benjamin Adams). Long Paper, OpenReview link
Poster Session Tue September 9th
Main Track
- Understanding Boolean Function Learnability on Deep Neural Networks: PAC Learning Meets Neurosymbolic Models (Marcio Nicolau, Anderson R. Tavares, Zhiwei Zhang, Pedro H. C. Avelar, João Marcos Flach, Luis DC Lamb, Moshe Vardi). Long Paper, OpenReview link
- Linearithmic Clean-up for Vector-Symbolic Key-Value Memory with Kroneker Rotation Products (Ruipeng Liu, Qinru Qiu, Simon Khan, Garrett Ethan Katz). Long Paper, OpenReview link
- Generating Safety-Critical Automotive C-programs using LLMs with Formal Verification (Merlijn Sevenhuijsen, Minal Suresh Patil, Mattias Nyberg, Gustav Ung). Long Paper, OpenReview link
- An evidence-based neuro-symbolic framework for ambiguous image scene classification (Giulia Murtas, Veselka Boeva, Elena Tsiporkova). Long Paper, OpenReview link
- A Neurosymbolic Approach to Counterfactual Fairness (Xenia Heilmann, Chiara Manganini, Mattia Cerrato, Vaishak Belle). Long Paper, OpenReview link
- T-ILR: a Neurosymbolic Integration for LTLf (Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Chiara Ghidini, Marco Montali, Massimiliano Ronzani). Long Paper, OpenReview link
- Neuro-Argumentative Learning with Case-Based Reasoning (Adam Gould, Francesca Toni). Long Paper, OpenReview link
- Neuro-Symbolic Inverse Constrained Reinforcement Learning (Oliver Deane, Oliver Ray). Long Paper, OpenReview link
- LUT Based Neural Networks as Neuro-Symbolic Systems (Lizy Kurian John, Priscila Machado Vieira Lima, Alan T. L. Bacellar, Shashank Nag, Eugene John, Felipe M.G. França). Extended Abstract, OpenReview link
- Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints (Mihaela C. Stoian, Eleonora Giunchiglia). Extended Abstract, OpenReview link.
- Neuro‑Symbolic Data Collection Automata for Training Language Models on Edge Devices (Jake Ryland Williams, August Lilley, Ankur Mali). Industry Abstract, OpenReview link
- Validating Free Text Against N-Ary Knowledge Graphs (Jayavanth Shenoy, Jin-Ching Lim, Guha Jayachandran; Onai Inc). Industry Abstract, Paper link
Neurosymbolic Generative Models
- Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations (Bradley P. Allen, Prateek Chhikara, Thomas Macaulay Ferguson, Filip Ilievski, Paul Groth). Long Paper, OpenReview link
- Learning and Reasoning with Model-Grounded Symbolic Artificial Intelligence Systems (Aniruddha Chattopadhyay, Raj Dandekar, Kaushik Roy). Long Paper, OpenReview link
Knowledge Graphs, Ontologies and Neurosymbolic AI
- Grounding Terms from an Ontology for use in Autoformalization: Tokenization is All You Need (Richard Thompson, Adam Pease, Mathias Kölsch, Angelos Toutsios). Short Paper, OpenReview link
- A Comparative Analysis of Neurosymbolic Methods for Link Prediction (Guillaume Delplanque, Luisa Werner, Nabil Layaïda, Pierre Geneves). Long Paper, OpenReview link
- Ontology-based box embeddings and knowledge graphs for predicting phenotypic traits in Saccharomyces cerevisiae (Filip Kronström, Daniel Brunnsåker, Ievgeniia A. Tiukova, Ross D. King). Long Paper, OpenReview link
- Uncertainty Quantification of Knowledge Graph Embedding with Statistical Guarantees (Yuqicheng Zhu, Nico Potyka, Daniel Hernández, Jiarong Pan, Bo Xiong, Yunjie He, Yuan He, Zifeng Ding, Evgeny Kharlamov, Steffen Staab). Extended Abstract, OpenReview link
- DAGE: DAG Query Answering via Relational Combinator with Logical Constraints (Yunjie He, Bo Xiong, Daniel Hernández, Yuqicheng Zhu, Evgeny Kharlamov, Steffen Staab). Extended Abstract, OpenReview link
Neurosymbolic Methods for Trustworthy and Interpretable AI
- Extracting PAC Decision Trees from Black Box Binary Classifiers (Ana Ozaki, Roberto Confalonieri, Ricardo Guimarães, Anders Imenes). Extended Abstract, OpenReview link
- Exploring Verification Frameworks for Social Choice Alignment (Jessica Ciupa, Vaishak Belle, Ekaterina Komendantskaya). Short Paper, OpenReview link
- Explainable Zero-Shot Visual Question Answering via Logic-Based Reasoning (Thomas Eiter, Jan Hadl, Nelson Higuera Ruiz, Lukas Lange, Johannes Oetsch, Bileam Scheuvens, Jannik Strötgen). Long Paper, OpenReview link
- ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation (Yuqicheng Zhu, Nico Potyka, Daniel Hernández, Yuan He, Zifeng Ding, Bo Xiong, Dongzhuoran Zhou, Evgeny Kharlamov, Steffen Staab). Long Paper, OpenReview link
- Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond CoT and ICL (Rushitha Santhoshi Mamidala, Anshuman Chhabra, Ankur Mali). Long Paper, OpenReview link
Poster Session Wed September 10th
Main Track
- Gestalt Vision: A Dataset for Evaluating Gestalt Principles in Visual Perception (Jingyuan Sha, Hikaru Shindo, Kristian Kersting, Devendra Singh Dhami). Long Paper, OpenReview link
- JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents (Kaizhi Zheng, Kaiwen Zhou, Jing Gu, Yue Fan, Jialu Wang, Zonglin Di, Xuehai He, Xin Eric Wang). Long Paper, OpenReview link
- Description Logic Concept Learning using Large Language Models (Adrita Barua, Pascal Hitzler). Long Paper, OpenReview link
- Neurosymbolic Learning in Structured Probability Spaces: A Case Study (Ole Fenske, Sebastian Bader, Thomas Kirste). Long Paper, OpenReview link
- Evolutionary Surrogate-Assisted Prescription: Neuro-Symbolic Framework for Trustworthy Decisioning (Hormoz Shahrzad, Risto Miikkulainen, Cognizant). Industry Abstract, OpenReview link
- Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations (François Olivier, Zied Bouraoui). Long Paper, OpenReview link
- Do Graph Neural Network States Contain Graph Properties? (Tom Pelletreau-Duris, Ruud van Bakel, Michael Cochez). Long Paper, OpenReview link
- Learning Symbolic Persistent Macro-Actions for POMDP Solving Over Time (Celeste Veronese, Daniele Meli, Alessandro Farinelli). Long Paper, OpenReview link
- A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verification (Vasileios Manginas, Nikolaos Manginas, Edward Stevinson, Sherwin Varghese, Nikos Katzouris, Georgios Paliouras, Alessio Lomuscio). Long Paper, OpenReview link
- Bayesian Inverse Physics for Neuro-Symbolic Robot Learning (Octavio Arriaga, Rebecca Carrie Adam, Melvin Laux, Lisa Gutzeit, Marco Ragni, Jan Peters, Frank Kirchner). Long Paper, OpenReview link
- Recent Advances in Resonator Networks for Neurosymbolic Computing (Alpha Renner, Christopher Kymn, Edward Paxon Frady, Friedrich Sommer). Extended Abstract, OpenReview link
- Practical Lessons on Vector-Symbolic Architectures in Deep Learning-Inspired Environments (Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler, Abbas Rahimi). Long Paper, OpenReview link
- Neurosymbolic Tag-Based Annotation for Interpretable Avatar Creation (Minghao Liu, Zeyu Cheng, Shen Sang, Jing Liu, James Davis). Long Paper, OpenReview link
- A Comparative Analysis of NeSy Frameworks and What’s Next? (Sania Sinha, Tanawan Premsri, Parisa Kordjamshidi). Long Paper, OpenReview link
- DeepDFA: Learning and Integration of Regular Languages with Deep Learning (Elena Umili). Extended Abstract, OpenReview link
Neurosymbolic Generative Models
- Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks (Sina Bagheri Nezhad, Ameeta Agrawal). Long Paper, OpenReview link
- Neural Theorem Proving: Generating and Structuring Proofs for Formal Verification (Balaji Rao, William Eiers, Carlo Lipizzi). Long Paper, OpenReview link
Knowledge Graphs, Ontologies and Neurosymbolic AI
- The ART of Link Prediction with KGEs (Yannick Brunink, Michael Cochez, Jacopo Urbani). Long Paper, OpenReview link
- Bridging Bots: from Perception to Action via Multimodal-LMs and Knowledge Graphs (Margherita Martorana, Francesca Urgese, Mark Adamik, Ilaria Tiddi). Long Paper, OpenReview link
- Evaluating Neuro-Symbolic AI Architectures: Design Principles, Qualitative Benchmark, Comparative Analysis and Results (Oualid BOUGZIME, Samir JABBAR, Christophe Cruz, Frédéric DEMOLY). Long Paper, OpenReview link
Neurosymbolic Methods for Trustworthy and Interpretable AI
- Neurosymbolic Association Rule Mining from Tabular Data (Erkan Karabulut, Paul Groth, Victoria Degeler). Long Paper, OpenReview link
- Distilling KGE black boxes into interpretable NeSy models (Rodrigo Castellano Ontiveros, Francesco Giannini, Michelangelo Diligenti). Long Paper, OpenReview link
- Adapting Graph-Based Analysis for Knowledge Extraction from Transformer Models (Alexandre Monnier Weil, Vitor A. C. Horta, Hamza Qadeer, Alessandra Mileo). Long Paper, OpenReview link