Seminars

Weekly seminars take place on Tuesdays at 2pm (usual length: 1 hour) often in Room A008 (together with a MS-Teams-based remote access for colleagues located in Metz). If you want to present your work or else have question, please contact Jean Lieber.

Past and future presentations are described below.

Presentations

Robopsychology: radical study of the verbal behavior of LLMs

chatbot
free associations
LLMs
radical behaviorism
verbal behavior
(This talk will take place in LORIA, room A008.) LLMs are used in conversational agents (CAs) (e.g., Claude, ChatGPT) to interact with users through text generation. The…
Tuesday, March 17, 2026
Pierre Mercuriali

Méthode hiérarchique hybride pour la segmentation de séquences biologiques

(This talk will take place in LORIA, room A008.) Nombreux sont les problèmes de bioinformatique, et singulièrement de biologie structurale prédictive, qui se réduisent à un…
Tuesday, March 10, 2026
Yann Guermeur

Representing Expert Reasoning Experience by Process Cases - Application to the Delimitation of Mobile Genetic Elements in Bacterial Chromosomes

(This talk will take place in LORIA, room A008.) Delimiting mobile genetic elements (MGEs) in bacterial genomes traditionally relies on experts in biology. This paper…
Tuesday, March 3, 2026
Toufik Hamadouche

Visual Analytics for Insight and Decision Support in Data-Driven Agriculture

(This talk will take place in LORIA, room A008.) Agricultural systems are becoming increasingly complex, making efficient resource use and sustainability essential.…
Tuesday, February 10, 2026
Nadia Boukhelifa

The “Github Spec Kit”: an introduction to vibe development

IA
(This talk will take place in LORIA, room A008.) GitHub Spec Kit brings a new approach to AI-based software development workflows – instead of vibe coding every new feature…
Tuesday, February 3, 2026
Samuel Cruz-Lara

When Cryptography and Artificial Intelligence join forces to serve Historians

IA
Sometimes, in an archive box, historians suddenly come across an encrypted document that has remained unchanged since it was sent. As a result, a great many historical…
Tuesday, January 20, 2026
Cécile Pierrot

Case-Based Cleaning of Text Images

Reasoning
CBR (case-based reasoning)
Frugal AI
Bikes and planes
Keywords: CBR (case based reasoning); LLM (will it be just to make you come to the talk?); Frugal AI; Bikes and planes
Tuesday, January 13, 2026
Jean Lieber

Perspectives in clinical NLP - Privacy and Temporality

IA
The first part of this presentation is a hybrid approach to automatically remove Personal Health Identifiers (PHIs) from clinical text using medicine reconciliation…
Tuesday, January 6, 2026
Judith Jeyafreeda

TBD

Nancy
IA
TBD
Tuesday, December 16, 2025
Alexanne Worm

Cross-lingual Aspect-Based Sentiment Analysis with Large Language Models

Nancy
IA
Cross-lingual Aspect-Based Sentiment Analysis (ABSA) aims to perform fine-grained sentiment analysis in a target language by transferring knowledge from a resource-rich…
Tuesday, December 9, 2025
Pavel Kral

Journée des doctorant·e·s MosAIk / MosAIk’s PhD candidates’ Day

B011/B013 (morning) and C005 (afternoon)
IA
Accueil - Introduction / Welcome - Opening (salle B011/B013)
Monday, December 8, 2025
Lydia Boudjeloud-Assala

Uncertainty quantification with classification models for better explainability and human-in-the-Loop systems.

Nancy
IA
Uncertainty quantification is a broad field that extends beyond artificial intelligence. Lying at the intersection of mathematics and computer science, its goal is to model…
Tuesday, December 2, 2025
Arthur Hoarau

TBD

Nancy
IA
TBD
Tuesday, November 18, 2025
Alain Gély

TBD

Nancy
IA
TBD
Tuesday, November 4, 2025
Nicolas Zampieri

Learner Models for Personalized Intelligent Tutoring Systems

Nancy
IA
Intelligent Tutoring Systems provide personalized and adaptive learning experiences, with the goal of complementing, or replacing, human instruction. Many existing…
Tuesday, October 14, 2025
Pierre-Alexandre Murena

Ingénieurs IA au LORIA

Nancy
IA
Ingénieurs IA
Tuesday, October 7, 2025
Adrien Guénard

Interprétabilité des Word Embeddings

Metz
explainability
NLP
En apprentissage profond, le fait de représenter les mots par des vecteurs numériques de plusieurs centaines de valeurs permet un calcul automatique de la proximité lexicale…
Tuesday, September 30, 2025
David Langlois

Adversarial Machine Learning for Fraud Detection: Classication Task against Adaptive Adversaries

Room A008
Classification
La détection de la fraude par apprentissage automatique est de plus en plus confrontée au problème de l’adaptabilité des adversaires, qui sont de plus en plus capables de…
Tuesday, September 23, 2025
Chloé Przemyski

Learning theory and generalization error bounds: Can we keep it simple?

Room A008
classification
This talk will introduce basic concepts of learning theory in a tutorial-like manner. In particular, we will first see how to derive a simple generalization error bound with…
Tuesday, September 9, 2025
Fabien Lauer

Making AI systems more trustworthy through uncertainty disentanglement

Room A008
Given the increasing use of machine learning (ML) models for decisions that directly affect humans, it is essential that these models not only provide accurate predictions…
Tuesday, July 8, 2025
Willem Waegeman

Structuring intelligence, How Knowledge representation and reasoning shape decision-making systems

Room C005
ontology
Hybrid IA
In today’s data-driven world, organizations face unprecedented complexity and volatility, making adaptive, informed and explained decisions more vital than ever. Intelligent…
Tuesday, July 1, 2025
Davy Monticolo

Solving complex problems with large language models

Amphi Kahn
LLM
reasoning
One of the great promises that people connect with LLMs is that they can make complex problem-solving with computers accessible to lay users. Unlike traditional symbolic…
Thursday, June 26, 2025
Alexander Koller

Pattern Mining with Paspailleur: Intro to a new Python package

Room TBD
Pattern mining
Pattern Mining (also known as Data Mining) is a field of science designed for extracting symbolic patterns in datasets. The mined patterns can then be used for constructing…
Tuesday, June 17, 2025
Egor Dudyrev

IA Générative et Traitement Automatique des Langues: une interaction fructueuse

Room A008
DL
TAL
NLP
L’IA générative a véritablement révolutionné le domaine du Traitement Automatique des Langues (TAL) rendant possible des applications qui ont longtemps échouer à rendre…
Tuesday, June 10, 2025
Claire Gardent

Graphs, Words, and Communities : converging paths to interpretability with a frugal embedding framework

Room B011/B013
NLP
explainability
frugality
This research addresses the growing sustainability and interpretability concerns in representation learning by introducing a framework that efficiently embeds both graph…
Tuesday, June 3, 2025
Thibault Prouteau

Towards Ontology-Based Descriptions of Conversations with Qualitatively-Defined Concepts

Room B011
LLM
ontology
explainability
Hybrid IA
The controllability of Large Language Models (LLMs) when used as conversational agents is a key challenge, particularly to ensure predictable and user-personalized…
Tuesday, May 27, 2025
Barbara Gendron

Modeling User Preferences for Music Recommendations with LLMs: Opportunities and Limitations

Room A008
LLM
recommendation
This talk explores the potential of large language models (LLMs) in enhancing music recommendation systems through explicit modeling of user preferences. We begin by…
Thursday, May 22, 2025
Deezer researchers

Sharper Bounds on the Metric Entropies of Margin Classifiers

Room A008
classification
This talk deals with the characterization of the generalization performance of margin multi-category classifiers, addressed through the derivation of upper bounds on their…
Tuesday, May 13, 2025
Yann Guermeur

L’intelligence artificielle entre symbolique et génératif : règles de monotonicité et modèles de langage

Room B011/B013
LLM
semantic web
L’intelligence artificielle évolue sur plusieurs axes, dont l’apprentissage symbolique et les grands modèles de langage (LLM). Le web sémantique constitue un cadre structuré…
Tuesday, May 6, 2025
Thamer Mecharnia

Compromise between scale and cost for LLMs

Room A008
DL
robustness
This talk will review the state-of-the-art about LLM scaling laws, both for training and inference, and will contrast this requirement to scale to achieve the best…
Tuesday, March 25, 2025
Christophe Cerisara

Contrastive Alignment for Preference-Driven KG-to-Text Generation

Room A008
NLP
The topic of my presentation is “Contrastive Alignment for Preference-Driven KG-to-Text Generation”. I will introduce multilingual cross-modal alignment between Knowledge…
Wednesday, March 19, 2025
Yifei Song

Deep learning based anomaly detection in time series and sustainable AI

Room A008
DL
robustness
In the ever-evolving landscape of machine learning, detecting concept drift and anomalies is crucial for maintaining model reliability and decision-making accuracy…
Tuesday, March 18, 2025
Mansour Mayaki

Approches hybrides et interactives

Room A008
explainability
hybrid IA
Concevoir des systèmes d’IA et d’apprentissage automatique qui intègrent systématiquement l’humain dans le processus devient une nécessité. L’approche « human-in-the-loop »…
Tuesday, March 11, 2025
Lydia Boudjeloud-Assala

Clarity: a Deep Ensemble for Visual Counterfactual Explanations

Room A008
DL
explainability
frugality
Counterfactual visual explanations are aimed at identifying changes in an image that will modify the prediction of a classifier. Unlike adversarial images, counterfactuals…
Tuesday, March 4, 2025
Brieuc Conan-Guez

Olaaaf: A General Adaptation Prototype

Room A008
explainability
taxonomy
Adaptation is often considered a complex issue during the design of a case-based reasoning system. Various approaches can be found in the literature, but their scopes are…
Tuesday, February 25, 2025
Emmanuel Nauer
No matching items
Back to top