Le CRIL en bref
Le Centre de Recherche en Informatique de Lens (CRIL UMR 8188) est un laboratoire de l’Université d’Artois et du CNRS dont la thématique de recherche fédératrice concerne l'intelligence artificielle et ses applications. Il regroupe près de 70 membres : chercheurs, enseignants-chercheurs, doctorants et personnels administratifs et techniques.
Le CRIL participe à la Confédération Européenne de Laboratoires en Intelligence Artificielle CAIRNE et à l'alliance régionale humAIn. Il bénéficie du soutien du Ministère de l’Enseignement Supérieur et de la Recherche, du CNRS, de l’Université d’Artois et de la région Hauts de France.
Le CRIL est localisé sur deux sites à Lens : la faculté des sciences Jean Perrin et l’IUT.
Actualités (RSS)
Séminaire Séminaire de Nicolas Schwind
Iterated Belief Change as Learning
4 déc. 2025 - 14:00In this work, we show how the class of improve- ment operators – a general class of iterated belief change operators – can be used to define a learning model. Focusing on binary classification, we present learning and inference algorithms suited to this learning model and we evaluate them empirically. Our findings highlight two key insights: first, that iterated belief change can be viewed as an effective form of online learning, and second, that the well-established axiomatic foundations of belief change operators offer a promising avenue for the axiomatic study of classification tasks.
Séminaire Séminaire de Markus Hecher
#P is Sandwiched by One and Two #2DNF Calls: Is Subtraction Stronger Than We Thought?
23 oct. 2025 - 14:00The canonical class in the realm of counting complexity is #P. It is well known that the problem of counting the models of a propositional formula in disjunctive normal form (#DNF) is complete for #P under Turing reductions. On the other hand, #DNF is in SpanL which is strictly contained in #P under parsimonious reductions and reasonable assumptions. Hence, the class of functions logspace reducible to #DNF is a strict subset of #P under plausible complexity-theoretic assumptions.
Séminaire Séminaire de David Ing
On Integrating Logical Analysis of Data into Random Forests
16 oct. 2025 - 14:00Random Forests (RFs) are one of the most popular classifiers in machine learning. RF is an ensemble learning method that combines multiple Decision Trees (DTs), providing a more robust and accurate model than a single DT. However, one of the main steps of RFs is the random selection of many different features during the construction phase ofDTs, resulting in a forest with various features,which makes it difficult to extract short and concise explanations.
Séminaire Séminaire d'Antoine Berthier - IRT-systemx
Alignment and Interpretation of Language Models through Activation Engineering
9 oct. 2025 - 14:00This presentation reports exploratory research conducted in partnership between IRT SystemX and the CRIL. The work focuses on the alignment and interpretability of large language models (LLMs) through activation engineering. The talk will provide an overview of the state of the art, outline the research directions that were explored and their outcomes, and highlight promising avenues for future work. It offers an opportunity to dive into the inner workings of LLMs, showing how they can be aligned using very limited data and how their internal activations can be leveraged to detect and better understand undesirable behaviors.
Séminaire Séminaire de Johannes Fichte
Complex and Faceted Reasoning
2 oct. 2025 - 14:00Symbolic AI reasoning utilizes symbols and logical rules to represent knowledge, which compactly represents the conditions for solutions. Research in many areas has primarily focused on qualitative reasoning, such as searching for a single solution or optimal solutions. Researchers also investigated enumeration and quantitative reasoning, such as counting or conditional probabilities. These techniques can also be used to understand better the solution space of given symbolic representations. For example, which element of the solution is very significant?
Séminaire Séminaire de Frédéric MARÇON - Laboratoire AGIR UR 4294 - Université de Picardie Jules Verne
Impact des chocs et vibrations sur la stabilité des biothérapies : Quels apports des données de vie réelle et de l’IA pour établir les recommandations ?
25 sept. 2025 - 14:00Assurer la stabilité des biothérapies pendant leur transport constitue un défi important, notamment face aux contraintes mécaniques mal maitrisées telles que les chocs, les vibrations ou face aux fluctuations thermiques. Si la régulation de la chaine du froid et des températures maitrisées est bien encadrée, les stress mécaniques restent peu explorés, malgré un impact avéré sur la stabilité des protéines et les risques iatrogènes associés. La quantification fine des conditions réelles de transport, à l’aide de capteurs embarqués (accéléromètres, gyroscopes, thermomètres), ainsi que la modélisation de leurs effets sur les caractéristiques physico-chimiques des produits biologiques, représente un enjeu stratégique en logistique pharmaceutique.
Séminaire Séminaire de Yasmina Beddar, Ingénieure Projets Européens - IRIT
Présentation Projets Européens
18 sept. 2025 - 14:00Présentation des différents dispositifs et projets européens existants.