Journée IA au LIUM

AI-Day   Members of the two LIUM teams (IEIAH & LST), some 40 people in all, came together for a day dedicated to artificial intelligence. This highly rewarding day was divided into two parts. After a morning dedicated to presenting the AI work of each team, highlighting innovative projects and advances made, the members of […]

LST-day

LST day   The LST team’s summer day is being held on 16 June. On this occasion, the researchers – both young and more experienced – present their research themes. It is also the occasion for our guest, Edwin Simonet, to present the Apside company. After a general presentation and a reminder of the year’s […]

Soutenance de thèse : Dynil DUCH

PhD defence, Dynil DUCH Date : 21/05/2025 Time : 9h00 Location : Institut d’Informatique Claude Chappe, Amphitheatre Hall Phd defence video :   Title – Predicting Student Performance through Cross-Institutional Learning Analytics: CISE Model and Reflective Learning Tools   Jury composition : M. Yvan PETER – University Professor, Université de Lille (President) Mme Armelle BRUN […]

Machine Learning models explainability for text and audio classification

Seminar from Norbert Tsopze, Professor at Université Yaounde 1   Date: 13/05/2025 Time: 11h00 Place: IC2, Boardroom Speaker: Norbert Tsopze     Machine Learning models explainability for text and audio classification   Abstract : The interpretability of the Machine Learning models outcomes to the end user is one of the most important properties which favors […]

Visite de Miriam Hansen et Iuliia Pliushch, chercheuses à l’Goethe-Universität Frankfurt

Visit from Miriam Hansen and Iuliia Pliushch, researchers at Goethe-Universität Frankfurt This week, our IEIAH team had the pleasure of welcoming Miriam Hansen and Iuliia Pliushch, researchers at the Goethe-Universität Frankfurt as part of Le Mans University’s “incoming international mobility” program! Their exchanges with our team aim to strengthen links between our laboratories, explore avenues […]

Prix de thèse 2025 décerné à Sebastian SIMON

Sebastian SIMON wins the 2025 thesis prize from the University of Le Mans Well done! Sebastian SIMON completed his thesis with LIUM’s IEIAH team, under the supervision of Sébastien George (director) and Iza Marfisi (day-to-day supersivor). He defended his thesis, entitled “Collaborative learning in mobile settings : conceptual framework and design of an innovative device […]

Towards a Smarter Homophone Correction Tool: A Case Study in Khmer Writing

Seminar from Seanghort BORN, PhD student at LIUM-TEL   Date: 7/04/2025 Time: 11h00 Place: IC2, Boardroom Speaker: Seanghort BORN     Towards a Smarter Homophone Correction Tool: A Case Study in Khmer Writing   Homophone errors are a common challenge in written communication, affecting both high-resource languages like English and low-resourced languages such as Khmer. […]

Séminaire de Charles Guin-Vallerand

Conception et déploiement de technologies d’assistance pour le support à la cognition basées sur l’intelligence ambiante et la réalité mixte   Date: 31/03/2025 Time: 14h Place: Cerium, salle de réunion et en visio Speaker: Charles Guin-Vallerand Résumé : Ce séminaire présente les projets de recherche du Laboratoire DOMUS de l’Université de Sherbrooke (Canada), axés sur le […]

Using large ASR models for training lightweight models in low-resource and computation-limited languages

Seminar from Aran Mohammadamini, Post-doc fellow at LIUM   Date: 24/03/2025 Time: 11h00 Place: IC2, Boardroom Speaker: Aran Mohammadamini     Using large ASR models for training lightweight models in low-resource and computation-limited languages   Low-resource languages often suffer not only from a lack of language resources but also from limited computational resources. Recent multilingual […]

Advances in measuring the interpretability of speaker representation spaces

Seminar from Félix Saget, PhD student at LIUM   Date: 10/03/2025 Time: 11h00 Place: IC2, Boardroom Speaker: Félix Saget     Advances in measuring the interpretability of speaker representation spaces   Features extracted by speaker representation models have proven to be potent and versatile, yielding respectable performance in various speaker-related tasks. However, a human user […]