IKONA
Integrating Knowledge Graphs and Neurosymbolic AI for Rare Oro-Dental Anomaly Diagnosis
IKONA aims to develop multimodal and explainable LLM models for diagnosing rare oro-dental diseases.
Latest announcements and updates.
Our paper on interpretable battery state estimation has been accepted at the ICAART Conference!
Our paper "Ontology Guided Large Language Model Pipeline for Structured Information Extraction from Battery Cell Datasheets" has been accepted at the NeuroSym4MLLM workshop at EGC 2026!
Our paper "Ontology-Aligned Prompting for Semantic RDF Extraction: A Case Study in Rare Oro-Dental Diseases" has been accepted at the NeuroSym4MLLM workshop at EGC 2026!
Our paper "BPO - A battery production ontology for traceable, transparent, and sustainable electric vehicle batteries" has been accepted for publication in the Journal of Web Semantics!
Our paper "Spiking Neural Networks for Accurate and Efficient State of Health Estimation of Lithium-Ion Batteries Across Varying Temperatures" has been accepted for publication in the IEEE Open Journal of Vehicular Technology!
Working on IKONA — Integrating Knowledge Graphs and Neurosymbolic AI for Rare Oro-Dental Anomaly Diagnosis, co-funded by ITI HealthTech / Cluster ENACT AI.
Working on GREATNESS — Generative Reasoning and Explainable AI for Transition to Next-gen Energy Systems and Security, co-funded by Région Grand Est / INSA Strasbourg.
Our workshop "on neuro-symbolic & knowledge-guided MLLMs" has been officially accepted as part of the EGC 2026 conference (Anglet). More info
Working on Vers des Transformers transparents : modéliser et simuler pour expliquer, funded by a France Excellence Scholarship.
Our paper « Ontology-Guided Prompting for Reasoning in Multimodal Vision-Language Models: An Application to Rare Dental Disease » has been officially accepted for publication in the MKLM-IJCAI 2025 workshop conference.
Our paper "Towards a neurosymbolic approach based on Anticipatory Learning Classifier Systems and Ontologies" has been accepted for publication in the 29th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2025).
I am an Associate Professor of Computer Science at the University of Strasbourg, teaching at the IUT Robert Schuman and conducting research within the Data Science and Knowledge team (SDC) of the ICube laboratory (since 09/2023).
My work focuses on neuro-symbolic AI and XAI, knowledge-guided multimodal LLMs (integrating ontologies, rules, and knowledge graphs with text, vision, and time-series), and discrete-event simulation for analyzing and explaining AI pipelines. I am interested in knowledge modeling and qualitative reasoning to make models more robust, grounded, and interpretable, with applications in Industry 4.0 and the medical domain.
Previously, I served as an Associate Professor in the CSTB team (09/2021–08/2023), a postdoctoral researcher in the MOFED team at LIS, Aix-Marseille University (09/2020–08/2021), and in the CEREGE Sustainable Environment team (09/2019–08/2020) in collaboration with CEINT, Duke University. I was a Teaching & Research Assistant (ATER) at the UFR of Mathematics and Computer Science, University of Strasbourg (09/2017–08/2019), and completed my Ph.D. in the SDC team at ICube (05/2015–09/2018).
The research topics I am currently working on, or have recently worked on, include:
These research areas have been applied in various fields, including Industry 4.0 and Medical domains, improving automation, diagnostics, and decision-making.
I am involved (and I have been involved) in different research projects related to knowledge modeling and representation, knowledge-driven approaches for XAI, neurosymbolic (hybrid) AI, and multimodal LLMs:
Integrating Knowledge Graphs and Neurosymbolic AI for Rare Oro-Dental Anomaly Diagnosis
IKONA aims to develop multimodal and explainable LLM models for diagnosing rare oro-dental diseases.
Generative Reasoning and Explainable AI for Transition to Next-gen Energy Systems and Security
GREATNESS aims to develop hybrid, explainable, and multimodal LLM-based approaches to detect battery thermal runaway.
Development of explainable artificial intelligence tools for the identification and classification of oro-dental anomalies based on multimodal datas
DENT-IA uses a neurosymbolic hybrid AI model, combining knowledge graphs and neural networks on multimodal data to improve the classification of rare dental diseases..
Semi-Supervised MAnagement of dual batteRy elecTric vehicles
2SMART aims to develop an intelligent and optimized Energy Management Strategy for a hybrid architecture of electric vehicles.
Transcending the Usual Rationale for the Future of Ubiquitous NETworks
TURFU-NET explores novel neuro-symbolic approaches for next-generation ubiquitous networks, addressing challenges in connectivity, efficiency, and scalability.
Analysis of hydrocarbon binder degradation using AI
AVLIA aims to develop a Machine Learning models coupled with numerical models to predict the aging and lifespan of roads.
Next Generation Battery Management System Based On Data RichDigital Twin
ENERGETIC develops innovative AI-based methods to enhance BESS performance and safety across the full lifecycle, from diagnostics to operation.
eXplainable Anomaly Detection
XAD investigates interpretable anomaly detection methods combining model-based reasoning and machine learning for industrial data.
Pull the COVID-19 replicative catalytic core apart
French ANR project developing data-driven and model-based methods to analyse COVID-19 related datasets.
Development and Implementation of a Sustainable Modelling Platform for NanoInformatics
NanoInformaTIX develops a web-based Sustainable Nanoinformatics Framework platform for risk management of engineered nanomaterials in industrial manufacturing.
Implementation of Risk Governance: meeting the needs of nanotechnology
Gov4Nano develops the first implementation of a future-proof operational Nano Risk Governance Model.
Peer-reviewed works, posters, and thesis.
I have (had) the pleasure of working with the following people.
Conference organization, academic service, and reviewing/editorial activities.
I mainly teach in the Computer Science Department of the Robert Schuman University Institute of Technology (IUT), University of Strasbourg.