News – Laboratoire Informatique d’Avignon

Seminar – Hajar El Hammouti – 10/12/2026

9 October 2026

Speaker : Professor Hajar El Hammouti from UM6P Date: 12/10/2026 – 11h30 Place: LIA meeting room. Title: “Energy Efficient Federated Learning” Abstract : Federated learning (FL) is a distributed learning framework that operates effectively over wireless networks. It enables devices to collaboratively train a model over wireless links by sharing model parameters rather than personal data. However, a key challenge in FL arises from the limited computational and communication resources of devices. As a result, energy efficiency has become a critical concern for real-world deployments. In this talk, we provide an overview of key strategies to reduce computational and communication overhead in FL systems. We will also present our recent contributions in this area, including the design of novel algorithms for client selection, model compression, and quantization. These techniques aim to minimize energy consumption while preserving model accuracy and ensuring FL convergence. Keywords: Energy Efficiency; Federated Learning; Internet of Things, Optimization; Wireless Communications. Bio: Hajar El Hammouti is an Assistant Professor at the College of Computing of Mohammed VI Polytechnic University (UM6P) in Morocco. She received her Ph.D. in Electrical Engineering from the National Institute of Posts and Telecommunications (INPT), Rabat, and held postdoctoral positions at the International University of Rabat (UIR) and King Plus d'infos

PhD Defense – Habit Allah Kabbaj – 10/08/2026

5 October 2026

Thesis title: Robust and Trustworthy Federated Learning in Distributed System Date: Thursday, October 8, 2026, at 2:00 PM, Place: Amphithéâtre Blaise at CERI. The presentation will be held in English. The jury members are: Reviewers• Mr Stefano Secci — Professor, Cnam, France• Mr Jalel Ben Othman — Professor, University of Paris 13, France Examiners• Mr Mohamed El Kamili — Professor, Hassan II University of Casablanca, Morocco• Ms Tamara Tosic — Research Engineer, Orange, France• Ms Hajar Elhammouti — Senior Lecturer, Mohammed VI Polytechnic University, Morocco Supervisors• Mr Rachid Elazouzi — Professor, Avignon University, France• Mr Abdellatif Kobbane — Professor, ENSIAS, Mohammed V University in Rabat, Morocco Abstract: Today, data is rarely available in a single place. It is produced and stored across personal devices, institutions, infrastructures, and services, often under constraints related to privacy, ownership, regulation, or technical accessibility. This situation has changed the way machine learning systems can be designed. In many applications, learning must take place without collecting all data in a central location, while still allowing several actors to contribute to a shared model. Federated Learning addresses this need by enabling collaborative training from local data. Yet, by avoiding direct access to the data, it also makes the learning process more uncertain. The server receives model updates from clients whose data distributions, training Plus d'infos

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.

Seminar – Matthew Wiesner – 26/03/2026

26 March 2026

Room 5 – 12h00 Title: Modeling Accent and Language at Scale Abstract: State-of-the-art LID models work reliably for ∼100 languages, but there are orders of magnitude more accents and dialects; annotating all of them is intractable. Furthermore, current LID models fail dramatically when applied to accented speech, and very few annotated accented data exist to support accented TTS. This talk explores these challenges and proposes a potential partial solution using massive amounts of diverse and widely available data collected from radio, with soft language labels in the form of geolocations. The talk then explores the link between robustness to accented speech and the capacity to more effectively model sequence-level data. Finally, these models and insights are shown to greatly improve LID on accented speech, and can be used to mine for accented speech to support scalable, controllable accented TTS.Bio: Matthew Wiesner est chercheur à l’Université Johns Hopkins et chercheur invité au Laboratoire Interdisciplinaire des Sciences du Numérique (LISN). Il a obtenu son doctorat et son master en génie électrique à Johns Hopkins en 2021 et 2016 sous la direction de Jan Trmal et de Sanjeev Khudanpur, ainsi que sa licence en génie électrique à l’Université McGill en 2013. Ses recherches Plus d'infos

PhD Defense – Manh Tuan NGUYEN – 25/03/2026

19 March 2026

Date: Wednesday, March 25th at 2:00 PM Place: amphitheater Blaise at CERI. The presentation will be held in English. The jury members: Title: Considering the inter-judge variability in the perceptual evaluation of speech and voice disorders and its integration into an automatic decision support system Abstract:Perceptual judgments are widely used in domains that lack clear objective criteria or reliable measurement methods, requiring reliance on human expert evaluation. However, such judgments are inherently subjective, often leading to a lack of agreement and, consequently, variability when multiple experts assess the same material. This variability, referred to as inter-rater variability, is typically addressed by aggregating scores or applying majority voting to produce a consensus decision. While effective for obtaining a final decision, this approach leaves the underlying causes of inter-rater variability largely unexplored.This thesis aims to explain inter-rater variability rather than treating consensus decisions as an absolute reference. We argue that such variability may arise from systematic differences between experts, particularly in terms of professional background, training, and the perceptual dimensions emphasized during assessment. By reducing individual judgments to a single consensus score, traditional approaches implicitly discard valuable information about expert reasoning and decision-making strategies. Understanding and explaining this variability is therefore essential.To address this objective, we propose a computational approach to model and interpret inter-rater variability. Leveraging the pattern-recognition capabilities of Plus d'infos

CORNET Seminar – Younes Ben Mazziane – 20/03/2026

16 March 2026

Date: 20/03/2026 à 11h30 Location: Salle C057 Title: Learning in Proportional Allocation Auctions Games Abstract: The Kelly or proportional allocation mechanism is a simple and efficient auction-based scheme that distributes an infinitely divisible resource proportionally to the agents’ bids. When agents are aware of the allocation rule, their interactions form a game, that has been extensively studied. This paper examines the less explored repeated Kelly game, focusing mainly on utilities that are logarithmic in the allocated resource fraction. We first derive this logarithmic form from fairness–throughput trade-offs in wireless network slicing, and then prove that the induced stage game admits a unique Nash equilibrium (NE). For the repeated play, we prove convergence to this NE under three behavioral models: (i) all agents use Online Gradient Descent (OGD), (ii) all agents use Dual Averaging with a quadratic regularizer (DAQ) (a variant of the Follow-the-Regularized leader algorithm), and (iii) all agents play myopic best responses (BR). Our convergence results hold even when agents use personalized learning rates in OGD and DAQ (e.g., tuned to optimize individual regret bounds), and they extend to a broader class of utilities that meet a certain sufficient condition. Finally, we complement our theoretical results with extensive simulations Plus d'infos

SLG Seminar – Tom Labiausse – 16/03/2026

12 March 2026

16 mars à 13h Tom présentera ses derniers travaux sur Hibiki-Zero, un modèle de traduction simultanée de la parole vers la parole. Les améliorations par rapport à ses travaux précédents, Hibiki, sont vraiment très intéressantes et s’appuient sur une technique d’apprentissage par renforcement (GRPO). Utilisée comme le propose Tom, cette technique évite d’avoir à préparer des données d’apprentissage parole-parole alignées au niveau mot comme dans la première mouture d’Hibiki. Vous êtes invités à assister à cette présentation qui pourrait vous donner des idées d’application à certains de vos travaux. Pour plus d’information, vous pouvez consulter cette page web très instructive et accessible (exemples, code, article) :

Habilitation defense – Rosa Figueiredo – 04/03/2026

25 February 2026

Titre: Combinatorial Optimization Methods for Signed Graph Partitioning Date: 04/03/2026, 15h Lieu: Amphi ADA du CERI Composition du jury Rapporteur·e·s : Safia KEDAD, Professor, Conservatoire National des Arts et Métiers, Paris, France Dritan NACE, Professor, University of Technology of Compiègne, Compiègne, France Hande YAMAN, Professor, Katholieke Universiteit Leuven, Leuven, Belgium Examinateur·rice·s : Paula CARROLL, Professor, University College Dublin, Dublin, Ireland Manoel CAMPELO, Professor, Federal University of Ceará, Fortaleza, Brazil

Cornet seminar – Raghupati Vyas – 27/02/2026

13 February 2026

Vendredi 27 Février à 11h30 en C057. Title: Games with Rational and Herding Players Résumé : This talk examines large-population games with heterogeneous decision-making, in which an α-fraction of players are rational, while the remaining agents exhibit herding behaviour. We introduce a new equilibrium notion, called the α-Rational Nash Equilibrium (α-RNE), and discuss its interpretations. We show that some classical equilibria may disappear and new ones may emerge for small values of α>0. Interestingly, rational players benefit from the presence of herding and may even achieve utility exceeding the socially optimum. Even more strikingly, in some cases, herding players also benefit, attaining utility close to the social optimum. Using transportation and bandwidth sharing games as case studies, we analyse the impact of herding on congestion and resource allocation, and quantify system inefficiencies through the Price of Anarchy. Finally, we discuss the mechanism and influence design in the presence of herding. While the expanded set of equilibria creates new opportunities, it also increases the risk of undesirable outcomes when influence cannot be effectively implemented.

1 2 3 … 13 »