PhD Defense – Sylvie Chaddad – 10/20/2026

23 September 2026

Title : Modélisation stochastique et analyse des dynamiques du financement participatif et de l’influence sociale dans les réseaux en ligne Place : Salle des thèses d’Avignon Université, au centre-ville d’Avignon. Date : Tuesday, October 20, 2026, at 2:00PM The presentation will be held in English. The jury members are: Abstract: Online platforms have become important systems where individuals interact, exchange information, make decisions, and influence each other over time. Crowdfunding platforms, social networks, recommendation systems, and open-source software platforms are examples of such systems. In these systems, decisions are not only based on personal preferences, but also on social interactions, platform visibility, previous actions, and the structure of the underlying network. As a result, repeated interactions between many users can lead to collective dynamics that evolve over time. This thesis develops stochastic models and analytical methods to study collective dynamics in networked systems. The main motivation comes from crowdfunding campaigns, where contributors arrive over time, observe the campaign state, and decide whether to participate. The thesis also considers related online systems, including competitive influence propagation in social networks, social learning with heterogeneous rationality, and contributor dynamics in open-source software projects. Overall, this thesis shows how stochastic modeling, network analysis, approximation methods, and game theory Plus d'infos

Seminar – Maryem Bouziane – 10/08/2026

21 September 2026

Title: Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder Date: 8 October 2026 Abstract: Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong performance on specific downstream tasks. Recent post-training approaches, such as SAMU-XLSR and SONAR, align speech representations with utterance-level semantic representations, enabling effective multimodal (speech–text) and multilingual applications. While speech foundation models typically learn contextual embeddings at the acoustic frame level, these methods learn representations at the utterance level.In this work, we extend this paradigm to arbitrary utterance-level attributes and propose a unified post-training framework that enables a single speech foundation model to generate multiple types of utterance-level representations. We demonstrate the effectiveness of this approach by jointly learning semantic, speaker, language, and emotion representations and evaluating them on multilingual semantic retrieval, speaker verification, language identification, and speech emotion recognition.