Logic Tensor Networks

Also known as LTN

Follow this topic Ask about this topic

Latest papers

9 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks
Sep 4, 2026Homayoun Afshari, Pietro Basci, Alessandro Russo +1Logic Tensor Networks Visual Reasoning
Politecnico di Torino Department of Control and Computer Engineering Turin, Italy
Generate in the Chart, Not on the Boundary: Function-Symbol Grounding for Hard Constraints in LTN-GANs
Aug 21, 2026Nijesh Upreti, Vaishak BelleLogic Tensor Networks Constrained Generative Modeling
The University of Edinburgh, 10 Crichton Street, Edinburgh, EH8 9AB, UK
sLTN: Structural Logic Tensor Networks
Aug 11, 2026Davide Rinaldi, Luciano SerafiniTensor Networks Logic Tensor Networks
Nokia Bell Labs · Fondazione Bruno Kessler
First-Order Temporal Logic Tensor Networks
Jun 29, 2026Luca Boscarato, Ivan Donadello, Alessandro Artale +2Tensor Networks Logic Tensor Networks
Free University of Bozen-Bolzano
Grounding vs. Compositionality: On the Non-Complementarity of Reasoning in Neuro-Symbolic Systems
Apr 29, 2026Mahnoor Shahid, Hannes RotheTensor Networks Logical Reasoning
Universität Duisburg Essen, Germany
From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
Apr 7, 2026Cedric Haufe, Frieder StolzenburgLogic Tensor Networks Neuro-Symbolic Reasoning
Harz University of Applied Sciences, Wernigerode, Germany · Merseburg University of Applied Sciences, Merseburg, Germany · Senior Visiting Fellow, University of New South Wales (UNSW), School of Computer Science and Engineering, Sydney, Australia
Compliance-Aware Predictive Process Monitoring: A Neuro-Symbolic Approach
Mar 27, 2026Fabrizio De Santis, Gyunam Park, Wil M. P. van der Aalst +1Logic Tensor Networks Predictive Process Monitoring
University of Parma, Parma, Italy · Eindhoven University of Technology, Eindhoven, Netherlands · RWTH Aachen University, Aachen, Germany
Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning
Mar 27, 2026Fabrizio De Santis, Gyunam Park, Francesco ZanichelliLogic Tensor Networks Predictive Process Monitoring
University of Parma, Parma, Italy · Eindhoven University of Technology, Eindhoven, Netherlands
Neuro-Symbolic Process Anomaly Detection
Mar 27, 2026Devashish Gaikwad, Wil M. P. van der Aalst, Gyunam ParkLogic Tensor Networks Anomaly Detection
RWTH Aachen University, Aachen, Germany · Eindhoven University of Technology, Eindhoven, The Netherlands

Sep 4, 2026J/K move · Enter open · S save

Think-Verify-Revise: Neuro-Symbolic Visual Reasoning with Vision-Language Models and Dynamic Logic Tensor Networks

Homayoun Afshari, Pietro Basci, Alessandro Russo, Lia Morra

Politecnico di Torino Department of Control and Computer Engineering Turin, Italy

Logic Tensor Networks Visual Reasoning Neuro-Symbolic Reasoning Visually Grounded Reasoning VLM Reasoning

Open paper AskPDF arXiv

Visual reasoning tasks require a system to jointly perceive visual content and apply formal relational constraints---a combination that neither pure neural nor purely symbolic approaches handle well in isolation. This paper proposes a Neuro-Symbolic (NeSy) framework that closes this gap by tightly coupling a Vision-Language Model (VLM) for automatic First-Order Logic (FOL) rule induction with a Dynamic Logic Tensor Network (D-LTN) for differentiable rule verification, in a closed iterative feedback loop. The VLM receives a small set of labelled visual examples and proposes candidate FOL rules conforming to a strict grammar (Think); the D-LTN is automatically assembled from these rules at runtime and evaluates them grounding on CNN-produced visual embeddings (Verify); and verification failures are fed back to guide the VLM's next hypothesis (Revise). Evaluated on the ViSudo-PC benchmark across four visual domains (MNIST, EMNIST, KMNIST, FMNIST), the system induces valid Sudoku constraint rules using only three training examples as visual context. The proposed method achieves AUC scores matching or outperforming previous methods (NeuPSL, LTN), showing the potential for automatic rule discovery through VLM. Code is available at https://github.com/homayoun-afshari/nesy.