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

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

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) :

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.

Cornet seminar – Andrea Fox – 14/11/2025

10 November 2025

Vendredi 14 novembre, 11h30 – Salle C057. Title: Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks Abstract: In edge computing systems, autonomous agents must make rapid local decisions while competing for shared resources. Existing MARL approaches often rely on centralized critics or frequent inter-agent communication, which breaks down under limited observability and communication constraints. We propose a decentralized framework in which agents coordinate implicitly through a shared constraint on resource usage. This constraint is updated infrequently, requiring minimal communication, while each agent independently solves a local constrained Markov decision process (CMDP) to learn its behavior. Leveraging safe reinforcement learning, agents learn policies that satisfy both local and global objectives. We provide theoretical guarantees under mild assumptions and validate our approach experimentally, demonstrating superior performance to centralized and independent baselines, particularly in large-scale settings.

Cornet seminar – Rachid El-Azouzi – 20/11/2025

10 November 2025

20 Novembre 2025 – 11h30 – Salle C057. Titre : Strategic Analysis of Just-In-Time Liquidity Provision in Concentrated Liquidity Market Makers Abstract: Liquidity providers (LPs) are essential figures in the operation of automated market makers (AMMs); in exchange for transaction fees, LPs lend the liquidity that allows AMMs to operate. While many prior works have studied the incentive structures of LPs in general, we currently lack a principled understanding of a special class of LPs known as Just-In-Time (JIT) LPs. These are strategic agents who momentarily supply liquidity for a single swap, in an attempt to extract disproportionately high fees relative to the remaining passive LPs. This paper provides the first formal, transaction-level model of JIT liquidity provision for a widespread class of AMMs known as Concentrated Liquidity Market Makers (CLMMs), as seen in Uniswap V3, for instance. We characterize the landscape of price impact and fee allocation in these systems, formulate and analyze a non-linear optimization problem faced by JIT LPs, and prove the existence of an optimal strategy. By fitting our optimal solution for JIT LPs to real-world CLMMs, we observe that in liquidity pools (particularly those with risky assets), there is a significant gap between observed and optimal Plus d'infos

Cornet seminar – Cléophée Robin – 05/06/2025

27 May 2025

Nous avons le plaisir de vous inviter au séminaire de l’équipe CORNET, qui se tiendra le jeudi 5 juin à 11h35 en salle C057 (ancienne BU). À cette occasion, nous accueillerons Cléophée Robin, enseignante-chercheuse à l’IRIF, qui nous présentera ses travaux intitulés : _________________________________________________________ Clique-covering co-bridge-free prismatic graphs Résumé : A graph G is prismatic if for every triangle T of G, every vertex of G that is not in T, has exactly one neighbor in T. The complement of a prismatic graph is called antiprismatic. The complexity of the coloring problem when restricted to prismatic graphs is unknown. Hence, the complexity of the clique-covering problem on prismatic graphs is also unknown. Chudnovsky and Seymour gave a full structural description of prismatic graphs. They divided the class in two subclasses : the orientable prismatic graphs and the non-orientable prismatic graphs.  Preissman, Robin and Trotignon gave an algorithm to solve the clique problem in non-orientable prismatic graphs in polynomial time. We show this algorithm can also be used for prismatic graphs with no 2K_1 + C_4 (co-bridge), whether they are orientable or not. To achieve this, we show that this class of graphs admits a bounded number of disjoint triangles through Plus d'infos

SLG seminar – Ismail Mohsine – 12/06/2025

27 May 2025

Le 12 juin à 12h, nous aurons le plaisir d’accueillir une présentation du Dr Ismail Mohsine, spécialiste en hydroinformatique, actuellement en séjour au LIA. La présentation se tiendra en salle S6.Veuillez trouver ci-dessous le résumé du séminaire ainsi qu’une courte biographie du Dr Ismail Mohsine. ==================================== Bio Ismail Mohsine est docteur en sciences de la Terre, spécialiste en hydroinformatique. Formé au laboratoire LG2E (Faculté des Sciences de Rabat), en partenariat avec l’Université d’Avignon et l’IRD, il mène des recherches intégrant géosciences, intelligence artificielle et modélisation environnementale appliquées au domaine des ressources en eau. Résumé Dans un contexte de changement climatique et de pression croissante sur les ressources en eau, la prévision des niveaux piézométriques devient un enjeu majeur pour la gestion durable des aquifères. Cette présentation propose une approche de prédiction basée sur des réseaux de neurones récurrents (type LSTM), appliquée à des séries temporelles multivariées combinant données in situ, satellitaires (NDVI, température, précipitations, évapotranspiration …). Entraînés à l’échelle des unités hydrogéologiques, ces modèles tirent parti de la dynamique temporelle et des variations géographiques des données, tout en intégrant des mécanismes explicites de gestion des valeurs manquantes. Cette méthodologie hybride permet de reconstruire les lacunes de mesure et d’anticiper l’évolution des nappes dans des contextes complexes, contribuant à une Plus d'infos

1 2 3 … 7