Publications

2026

• Direction-aware Ambisonic Speech Separation Using Edge-Conditioned Graph Convolution
  
  • Kelley Liam
  • Fontaine Mathieu
  • Peeters Geoffroy
  , 2026. The conventional Direction-Aware Ambisonic Speech Separation (DAASS) paradigm involves spatial filtering followed by post-filtering refinement. A number of approaches have been proposed to jointly perform spatial filtering and refinement using end-to-end neural methods, using as input full ambisonic signals and spatially filtered signals without explicitly modeling their spatial relationships. In this paper, we propose to unify these different input types directly in the model architecture with a spatial relationship graph. In particular, we design a novel edge-conditioned graph convolution block which aims to replace standard 1D convolutional blocks and be better suited to ambisonic signals. For our experiments, we develop a new synthetic DAASS dataset called Spatial LibriMix which will be available online upon acceptance. Our method matches or outperforms baseline performance with a significantly reduced parameter count (66M to 7.5M).
• Structure preserving adversarial diffusion for unpaired medical image synthesis
  
  • Paniagua Kévin
  • Conze Pierre-Henri
  • Jaouen Vincent
  • Angelini Elsa
  , 2026, pp.1-5. Recent works have established diffusion models as viable candidates for unpaired medical image translation, by incorporating supervision through non-diffusive models in an end-to-end fashion.. Existing models typically rely on cycleconsistent, two-sided, non-diffusive modules of relatively high computational cost where structure preservation is not explicit. In this work, we propose SPAD, a novel one-sided approach that explicitly preserves the source domain firstorder (gradient) orientations, while enabling flexible contrast adaptation between source and target domains. Our approach provides direct edge guidance for the diffusive module, leading to better structural preservation. Experiments performed on image synthesis tasks using BraTS, CERMEP, and Gold Atlas datasets demonstrate that our model improved translation fidelity and reduced training time by over 50% compared to SynDiff while keeping the same diffusion architecture. The reduction in computational cost allowed us to train 3D variants, which achieved consistently higher quantitative scores. Code will be publicly shared on GitHub upon acceptance. (10.1109/ISBI61048.2026.11515588)
  DOI : 10.1109/ISBI61048.2026.11515588
• Adaptive gradient domain normalization for one-sided unsupervised medical image synthesis
  
  • Paniagua Kévin
  • Conze Pierre-Henri
  • Jaouen Vincent
  • Angelini Elsa
  , 2026.
• Leveraging Whole Slide Difficulty in Multiple Instance Learning to Improve Prostate Cancer Grading
  
  • Arrivat Marie
  • Peyret Rémy
  • Angelini Elsa
  • Gori Pietro
  , 2026, pp.1-4. Multiple Instance Learning (MIL) has been widely applied in histopathology to classify Whole Slide Images (WSIs) with slide-level diagnoses. While the ground truth is established by expert pathologists, the slides can be difficult to diagnose for non-experts and lead to disagreements between the annotators. In this paper, we introduce the notion of Whole Slide Difficulty (WSD), based on the disagreement between an expert and a non-expert pathologist. We propose two different methods to leverage WSD, a multi-task approach and a weighted classification loss approach, and we apply them to Gleason grading of prostate cancer slides. Results show that integrating WSD during training consistently improves the classification performance across different feature encoders and MIL methods, particularly for higher Gleason grades (i.e., worse diagnosis). (10.1109/ISBI61048.2026.11515564)
  DOI : 10.1109/ISBI61048.2026.11515564
• Fast tomographic SAR inversion by unrolling a greedy algorithm for sparse reconstruction
  
  • Mendes Cristiano Ulondu
  • Denis Loïc
  • Kervazo Christophe
  • Tupin Florence
  , 2026. <div><p>As a range-based imaging technique, synthetic aperture radar (SAR) is agnostic to targets' elevation. In urban areas, tomographic synthetic aperture radar (TomoSAR) retrieves the position of sparsely distributed targets along the elevation direction thanks to the phase information from multiple acquisitions of the same area. Compressive sensing (CS)-based methods have received a lot of attention during the last decade, producing satisfactory reconstructions from a limited number of acquisitions. To improve their performance and scalability for pixel-wise TomoSAR inversion, data-driven methods based on the deep unrolling of basis pursuit algorithms have recently been proposed. However, they depend on a discretization of the elevation direction, often leading to artifacts which have to be corrected in a post-processing step. In this paper, we present an approach inspired by the iterations of a greedy algorithm for sparse reconstruction that estimates continuous elevation positions of targets together with well-calibrated uncertainty predictions. Our approach achieves performances comparable to reference CS-based methods while offering significantly faster processing. The trained models and the code used in the different experiments are available at place holder.</p></div>
• Evaluating DV/CV-QKD Architectures for SAFE Long-Term Secure Storage: A Risk Model and ILP-Based Cost Optimization Approach
  
  • Tasdighi Alireza
  • Alléaume Romain
  , 2026, pp.1-9. This paper presents a unified cost model and optimization framework for evaluating hybrid discrete variable / continuous variable quantum key distribution (DV/CV-QKD) architectures within the SAFE (Secure and Efficient) longterm secure storage (LTSS) protocol. The proposed methodology jointly models the information-theoretic and computational aspects of storage security over extended time horizons and integrates a stochastic integer linear programming (ILP) formulation with a quantitative risk model. By combining Sample-Average Approximation (SAA) with an analytically tractable compromise probability, the framework identifies feasible and cost-optimal SAFE topologies under heterogeneous transmission budgets, keyrate constraints, and security tolerances. Simulation results over randomly generated metropolitan-scale deployments reveal how DV, CV, and multiplexed (MUX) QKD modalities are adaptively selected to minimize infrastructure cost while maintaining a target global compromise probability ϵ. The findings show that mixed DV/CV configurations—particularly when combined with multiplexing—achieve significant cost reductions compared to single-modality networks, paving the way towards the deployment of cost-efficient network infrastructures able to leverage existing QKD technology to provide practical cryptographic advantage for long-term secure storage. (10.1109/QCNC69040.2026.00029)
  DOI : 10.1109/QCNC69040.2026.00029
• Automated Derivation of Formal Properties from Requirements
  
  • Sultan Bastien
  • Apvrille Ludovic
  • Saqui-Sannes Pierre De
  , 2026, pp.1-8. Early detection of design errors in the life cycle of systems is one of the many benefits one may expect from using an model-based systems engineering approach. The formal verification of models is thus an issue. Among verification techniques, the paper focuses on model checking. Taking as input a set of properties and a model, model checking outputs a “yes/no” answer for each property saying whether the property is verified or not. The relevance of this proof relies on the relevance of the defined properties. The paper proposes solutions for automated generation of properties from a SysML model and, more specifically, from the requirements expressed in the SysML model. We introduce an AI- and syntactic rule-based process that assists systems engineers in the generation of syntactically correct CTL properties, along with complementary contributions for computing and propagating requirement coverage from formal verification results, backtracing them directly in the SysML requirement diagram. The approach is mathematically defined, with explanatory comments accompanying the formalism to support comprehension. The proposed approach is further implemented by the free software TTool-AI. The latter is an open source SysML toolkit extended with an LLM-based assistant. A satellite system and an embedded maritime system serve as case studies. (10.1109/SysCon66367.2026.11503633)
  DOI : 10.1109/SysCon66367.2026.11503633
• Breaking exponential complexity in games of ordered preference: A tractable reformulation
  
  • Lee Dong Ho
  • Li Jingqi
  • Peters Lasse
  • Bakirtzis Georgios
  • Fridovich-Keil David
  , 2026. Games of ordered preference (GOOPs) model multi-player equilibrium problems in which each player maintains a distinct hierarchy of strictly prioritized objectives. Existing approaches solve GOOPs by deriving and enforcing the necessary optimality conditions that characterize lexicographically constrained Nash equilibria through a single-level reformulation. However, the number of primal and dual variables in the resulting KKT system grows exponentially with the number of preference levels, leading to severe scalability challenges. We derive a compact reformulation of these necessary conditions that preserves the essential primal stationarity structure across hierarchy levels, yielding a "reduced" KKT system whose size grows polynomially with both the number of players and the number of preference levels. The reduced system constitutes a relaxation of the complete KKT system, yet it remains a valid necessary condition for local GOOP equilibria. For GOOPs with quadratic objectives and linear constraints, we prove that the primal solution sets of the reduced and complete KKT systems coincide. More generally, for GOOPs with arbitrary (but smooth) nonlinear objectives and constraints, the reduced KKT conditions recover all local GOOP equilibria but may admit spurious non-equilibrium solutions. We introduce a second-order sufficient condition to certify when a candidate point corresponds to a local GOOP equilibrium. We also develop a primal-dual interior-point method for computing a local GOOP equilibrium with local quadratic convergence. The resulting framework enables scalable and efficient computation of GOOP equilibria beyond the tractable range of existing exponentially complex formulations.
• Importance Sampling Optimization with Laplace Principle
  
  • Dragomir Radu-Alexandru
  • Portier François
  • Priser Victor
  , 2026. Grid search and random search are widely used techniques for hyperparameter tuning in machine learning, especially when gradient information is unavailable. In these methods, a finite set of candidate configurations is evaluated, and the best-performing one is selected. We propose a simple and computationally inexpensive refinement of this paradigm: instead of selecting a single best point, we form a weighted average of the evaluated configurations, where the weights are chosen using an importance sampling scheme inspired by the Laplace principle. This scheme can be implemented as a post-processing step on top of a random search, with no additional function evaluations. We also propose an iterative variant, where the sampling distributions are chosen adaptively to generate new candidate points around the previous estimate, in the spirit of Evolution Strategy (ES) methods. In a general non-convex setting, we show that, after n evaluations, the error of the proposed methods is of smaller order than n -2/(d+2) . This compares favorably to random search or grid search rates of n -1/d as soon as d &gt; 2. We illustrate the practical benefits of this averaging strategy on several examples.
• Self-Supervised Quantification of Despeckling Uncertainties Applied to Unsupervised Radiometric Change Detection in SAR imaging
  
  • Bultingaire Thomas
  • Kervazo Christophe
  • Denis Loïc
  • Tupin Florence
  , 2026. The Synthetic Aperture Radar (SAR) imaging modality is well-suited for change detection tasks. In particular, its robustness to day-night cycles and cloud coverage is critical for certain applications, such as disaster assessment and monitoring the deforestation in old-growth forests that are frequently cloudcovered. However, its use is often impeded by the speckle phenomenon, causing strong fluctuations in the radar images, which are difficult to distinguish from actual temporal changes. To suppress these fluctuations, we propose to resort to a stateof-art despeckling method. In addition, to better take into account the residual fluctuations in the areas that are the most challenging to restore, we quantify despeckling uncertainties, which enables reaching a constant rate of false positive detections. We also show that incorporating spatial correlations into the despeckling uncertainties model can further improve change detection, especially in highly textured regions such as building areas. The proposed SAR Despeckling Uncertainty Change detection frameworK (SAR-DUCK) is applied to TerraSAR-X and Sentinel-1 images, demonstrating improved detection rates compared to methods from the state-of-the-art, as well as a constant and controlled false alarm rate. Supplementary results and an implementation of the proposed method are available on GitLab at https://gitlab.telecom-paris.fr/ring/sar-duck.
• The Role of Averages in CV-QKD over Fast Fading Channels
  
  • Castillo-Celeita Miguel
  • Schiavon Matteo
  Entropy, MDPI, 2026, 28 (4), pp.388. This work presents a study of continuous-variable quantum key distribution (CV-QKD) protocols over fast-fading channels, typically found in free-space communication links. Two eavesdropping models are considered to evaluate their security under collective attacks: Holevo bound average (HBA) and covariance matrix average (CMA). In the HBA approach, the Holevo bound is averaged over the channel transmittance. In contrast, the CMA method calculates the Holevo bound from the average covariance matrix. Analytical expressions are developed for both strategies. The two methods also differ in how they calculate the mutual information between the legitimate parties. The results demonstrate that the SKR is significantly influenced by how you treat channel fluctuations, highlighting the importance of choosing the model that best describes the actual implementation of the protocol. (10.3390/e28040388)
  DOI : 10.3390/e28040388
• Taylor-SWFT: fast discrete Statistical Wave Field Theory using Taylor expansion for late reverberation Work under review
  
  • Rodrigues Marius
  • Lalay Louis
  • Badeau Roland
  • Richard Gaël
  • Fontaine Mathieu
  , 2026. Dynamic room acoustic simulation aims to render the acoustic effects of an environment in real time while accounting for potentially moving sources and receivers. In this context, the efficient synthesis of the long-term room response, also known as late reverberation, remains challenging because of the intricate relationship between room geometry and acoustic behavior. This paper introduces Taylor-SWFT, an efficient implementation of key results from Statistical Wave Field Theory (SWFT) for the geometry-aware dynamic synthesis of late reverberation. The method is evaluated on the Benchmark for Room Acoustical Simulation (BRAS) and achieves competitive performance compared with classical approaches, while substantially reducing computational cost.
• Cross-Core Covert Channel for RISC-V: Implementation, Countermeasures and Cross-Platform Analysis
  
  • Khan Mahreen
  • Mushtaq Maria
  • Pacalet Renaud
  • Apvrille Ludovic
  , 2026. <div><p>Cache-based covert channels exploit microarchitectural timing differences to enable unauthorized communication between processes. While extensively studied on x86 architectures, such channels remain underexplored in the emerging RISC-V ecosystem. This paper presents the design and implementation of a novel prefetcher and cache timing covert channel for RISC-V platforms that exploits the timing difference between cached and uncached memory accesses. Our implementation supports both standardized RISC-V cache management extensions (Zicbom and Zicbop) and vendor-specific instructions (T-Head C910 custom instructions), demonstrating cross-platform portability across heterogeneous RISC-V implementations. The sender encodes bits by selectively prefetching or flushing a shared cache line, while the receiver decodes information by measuring memory access latency. Through careful synchronization using POSIX shared memory and atomic operations, we achieve reliable bit transmission on both the RISC-V gem5 full-system simulator (Sifive U54 core) and physical RISC-V Beagle-V Ahead (T-Head C910 core). Our paper contributes to understanding the security implications of cache and prefetcher management instructions in RISC-V systems and provides a foundation for developing detection and mitigation strategies for this emerging architecture.</p></div>
• Virtual PUF: Built-in Model for Highly Reliable and Secure PUF
  
  • Nasir Neelam
  • Cheng Wei
  • Kühne Ulrich
  • Graba Tarik
  • Danger Jean-Luc
  , 2026. Strong Physical Unclonable Functions (PUFs) with challengeresponse protocols provide a cost-effective authentication solution for resource-limited devices. However, they are susceptible to modeling attacks. An effective countermeasure for multi-bin PUFs -such as the Ring Oscillator PUF (RO-PUF) and Loop PUF -is the use of Non-Monotonic Quantization (NMQ) of the response. However, NMQ requires quite high quantization levels in order to effectively improve the security. This makes the PUF unreliable, rendering it impractical for authentication purposes. In this paper, we present a solution called the Virtual PUF : It generates a lightweight PUF model at device start-up, which is then used instead of the physical PUF during authentication. This allows the elimination of the noise impact and renders the PUF fully reliable and secure against ML attacks at the same time. As a proof of concept, we present an FPGA implementation based on a Loop PUF -a PUF relying on a single ring oscillator -and we show that beside its perfect reliability and high security, the Virtual PUF can be designed in a lightweight manner. However, the model built by the Virtual PUF may differ from the enrolled model and cause mismatch errors between the two models, which could deteriorate the authentication protocol. We show that the mismatch error measured in different configurations and environments can be optimized towards an acceptable range and/or managed by the authentication protocol.
• LLM-as-a-qualitative-judge: automating error analysis in natural language generation
  
  • Chirkova Nadezhda
  • Ajayi Tunde Oluwaseyi
  • Aycock Seth
  • Mujahid Zain Muhammad
  • Perlić Vladana
  • Borisova Ekaterina
  • Vartampetian Markarit
  , 2026, pp.99-132. Prompting large language models (LLMs) to evaluate generated text, known as LLM-as-ajudge, has become a standard evaluation approach in natural language generation (NLG), but is primarily used as a quantitative tool, i.e. with numerical scores as main outputs. In this work, we propose LLM-as-a-qualitative-judge, an LLM-based evaluation approach with the main output being a structured report of common issue types in the NLG system outputs. Our approach is targeted at providing developers with meaningful insights on what improvements can be done to a given NLG system and consists of two main steps, namely open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm. We also introduce a strategy for evaluating the proposed approach, coupled with ∼300 annotations of issues in instances from 12 NLG datasets. Our results show that instancespecific issues output by LLM-as-a-qualitativejudge match those annotated by humans in 2/3 cases, and that LLM-as-a-qualitative-judge is capable of producing error type reports resembling the reports composed by human annotators. We also demonstrate in a case study how the use of LLM-as-a-qualitative-judge can substantially improve NLG systems performance. Our code and data are publicly available. (10.18653/v1/2026.mme-main.7)
  DOI : 10.18653/v1/2026.mme-main.7
• New approaches to CLT for stable random variables
  
  • Coutin Laure
  • Decreusefond Laurent
  • Huang Lorick
  , 2026. In this paper, we present novel approaches to the Central Limit Theorem (CLT) for stable random variables, particularly focusing on cases where the distribution has heavy tails. The study develops three independent methods, each addressing different aspects of convergence in the context of α-stable distributions. We explore both non-integrable and integrable cases, offering new derivations and highlighting the distinct normalization required when dealing with heavy-tailed distributions. Special attention is given to the Stein method, adapted to handle stable laws, leveraging Fourier techniques and Poisson process representations. We provide convergence rates and quantify the Wasserstein distance between sums of independent and identically distributed random variables and their limiting stable distributions. Our findings extend existing results by offering intrinsic methods for stable CLTs, with applications to distributions such as Pareto, where classical CLT normalization fail.
• How Predicted Links Influence Network Evolution: Disentangling Choice and Algorithmic Feedback in Dynamic Graphs
  
  • Perez Mathilde
  • Romero Raphaël
  • Lijffijt Jefrey
  • Laclau Charlotte
  , 2026. Link prediction models are increasingly used to recommend interactions in evolving networks, yet their impact on network structure is typically assessed from static snapshots. In particular, observed homophily conflates intrinsic interaction tendencies with amplification effects induced by network dynamics and algorithmic feedback. We propose a temporal framework based on multivariate Hawkes processes that disentangles these two sources and introduce an instantaneous bias measure derived from interaction intensities, capturing current reinforcement dynamics beyond cumulative metrics. We provide a theoretical characterization of the stability and convergence of the induced dynamics, and experiments show that the proposed measure reliably reflects algorithmic feedback effects across different link prediction strategies.
• Data Metrics with Statistical Depths and Kernel Methods
  
  • Castellanos Salinas Arturo
  , 2026. Data is ubiquitous nowadays, with more and more virtualization of the real world. That raises the question: how well can we understand and picture data? “Mathematics and the Picturing of Data” was the title of the seminal work by John Tukey in 1975 that started the field of statistical data depths, and it is suggesting, of course, to rely on mathematical techniques, while keeping the idea of simplicity of a picture. The challenge is to keep the balance between fidelity to the complexity of the data and simplicity to be understandable by the human mind. In computational statistics, this challenge is often translated as using computational power to analyze a finite number of samples, that should approximate well an underlying distribution, yet to compute relevant characteristics of such distribution. Because the computational complexity is bound to increase with the number of samples, a trade-off appears where the statistical approximation error is hoped to decrease fast enough with the number of samples.In this work, we design tools to understand better data under the constraints that their sample complexity should not grow too high. First, we focus on designing new data depth functions with two kind of extensions of the Tukey depth. One extension is done by changing its geometrical nature, inspired by kernel methods to change from the classical Euclidean inner product. The other is by seeing the Tukey depth as classification risk and changing the space of classifiers as well as the loss function. In both cases, we manage to guarantee parametric rate for this non-parametric methods.In a another part, we also consider understanding distribution by looking at distances to discriminate them. The Wasserstein distance from optimal transport is a well-known distance to quantify the difference of two distributions, however its sample complexity suffers from the curse of dimensionality. On the other hand, we show that the Maximum Mean Discrepancy (MMD), a kernel-based distance enjoying good sample complexity, is sometimes too lenient for discriminating distributions, and we suggest to use a distance in-between those two that has higher discriminating power than MMD at the cost of a slight increase of the sample complexity.All of these methods can be used to prevent contamination of data to ruin our statistical analyses, whether it is by detecting outliers using data depth scores or by enhancing the discrimination of distributions via distances.
• A POP ⋆ is Born: Formal Predictable Out-of-Order Processor Model
  
  • Rouizi Lilia
  • Binder Benjamin
  • Asavoae Mihail
  • Ermis Engin
  • Rieg Lionel
  • Brandner Florian
  , 2026. Modern processors, even at the mid-range level, include multi-level caches, pipelines with branch predictors, or Out-of-Order (OoO) execution. While these are essential for average-case performance, they also increase the complexity of worst-case execution time analysis. OoO execution, for instance, is prone to timing anomalies and, due to the lack of efficient abstractions, quickly leads to state-space explosion. Consequently, it remains highly challenging in the context of critical real-time systems. This work proposes the first generic approach to predictable OoO execution, which is formally modeled and proven in the F* language and experimentally evaluated through simulations in gem5. Performance is evaluated on different processor models for MiBench and Embench programs. The average slowdown for an ARM A710-like processor model amounts to about 18.3% due to an implementation particularity of gem5. Eliminating bias from this issue reduces the slowdown to only 8.8%-10.4%.
• On Gossip Algorithms for Machine Learning with Pairwise Objectives
  
  • Colin Igor
  • Bellet Aurélien
  • Clémençon Stephan
  • Salmon Joseph
  , 2026. In the IoT era, information is more and more frequently picked up by connected smart sensors with increasing, though limited, storage, communication and computation abilities. Whether due to privacy constraints or to the structure of the distributed system, the development of statistical learning methods dedicated to data that are shared over a network is now a major issue. Gossip-based algorithms have been developed for the purpose of solving a wide variety of statistical learning tasks, ranging from data aggregation over sensor networks to decentralized multi-agent optimization. Whereas the vast majority of contributions consider situations where the function to be estimated or optimized is a basic average of individual observations, it is the goal of this article to investigate the case where the latter is of pairwise nature, taking the form of a U -statistic of degree two. Motivated by various problems such as similarity learning, ranking or clustering for instance, we revisit gossip algorithms specifically designed for pairwise objective functions and provide a comprehensive theoretical framework for their convergence. This analysis fills a gap in the literature by establishing conditions under which these methods succeed, and by identifying the graph properties that critically affect their efficiency. In particular, a refined analysis of the convergence upper and lower bounds is performed.
• It’s All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using Large Language Models
  
  • Santini Cristian
  • van Erp Marieke
  • Alam Mehwish
  , 2026. Despite the recent advancements in NLP with the advent of Large Language Models (LLMs), Entity Linking (EL) for historical texts remains challenging due to linguistic variation, noisy inputs, and evolving semantic conventions. Existing solutions either require substantial training data or rely on domain-specific rules that limit scalability. In this paper, we present MHEL-LLaMo (Multilingual Historical Entity Linking with Large Language MOdels), an unsupervised ensemble approach combining a Small Language Model (SLM) and an LLM. MHEL-LLaMo leverages a multilingual bi-encoder (BELA) for candidate retrieval and an instruction-tuned LLM for NIL prediction and candidate selection via prompt chaining. Our system uses SLM's confidence scores to discriminate between easy and hard samples, applying an LLM only for hard cases. This strategy reduces computational costs while preventing hallucinations on straightforward cases. We evaluate MHEL-LLaMo on four established benchmarks in six European languages (English, Finnish, French, German, Italian and Swedish) from the 19th and 20th centuries. Results demonstrate that MHEL-LLaMo outperforms state-of-the-art models without requiring fine-tuning, offering a scalable solution for low-resource historical EL. Our error analysis reveals that 41\% of false predictions exhibit semantic proximity to ground truth entities, highlighting the LLM's accurate disambiguation of historical references.
• Bandwidth-Scalable Neural Behavioral Modeling of Wideband RF Power Amplifiers : NARX Neural Networks and a Unified Figure of Merit
  
  • Pham Trong Thuy
  , 2026. Wideband RF power amplifiers (PAs) face a fundamental efficiency-linearitytrade-off in which nonlinearities and memory effects degrade in-band waveformfidelity and generate out-of-band spectral regrowth. To resolve this problem,accurate behavioral models serve as essential digital surrogates for thedevelopment of Digital Predistortion (DPD). By characterizing complex memoryeffects and spectral regrowth, these models enable safe and systematic designevaluation without the risks of extensive hardware iterations. This thesisdevelops bandwidth-scalable neural behavioral modeling methods for wideband PAs,emphasizing accuracy, robustness under bandwidth variation, andimplementation-relevant complexity. A structured recurrent formulation based onthe nonlinear autoregressive neural network with exogenous inputs (NARXNN) isestablished as a favorable accuracy-complexity compromise relative to polynomialbaselines and representative neural network alternatives. To improve modelingfidelity in strongly nonlinear regimes, a piecewise NARXNN (PW-NARXNN)architecture is proposed by segmenting the operating space and trainingspecialized NARXNN submodels; on the reference dataset, PW-NARXNN improvesNMSE to -39.2 dB with a moderate increase in parameters (666 compare to377 of global NARXNN), and yields improved spectral fidelity. Bandwidthgeneralization is then investigated on a measured multi-band 5G-NR datasetspanning 20-100 MHz acquired on an LDMOS PA, using standard,interpolation, and extrapolation validation schemes to quantify robustness underbandwidth changes. Finally, a bandwidth-aware Figure of Merit (FoM) isintroduced to unify comparison by combining mean accuracy, prediction stability,bandwidth sensitivity, and a logarithmic complexity penalty, providing a compactranking and consistently identifying NARXNN as the most favorable trade-offamong evaluated baselines. (10.70675/9a164464z9694z4b5fzb5fbz54c29615ea7d)
  DOI : 10.70675/9a164464z9694z4b5fzb5fbz54c29615ea7d
• Multiple Choice Learning from Ambiguous Signals
  
  • Letzelter Victor
  , 2026. Machine-learning-based predictive systems are faced with limitations when data is ambiguous. If a one-to-many relationship between inputs and outputs exists, a single prediction may not be sufficient, and multiple predictions may be required. In this context, practical constraints often lead one to produce a small set of representative samples from the conditional output distribution using a trained neural network. Multiple Choice Learning (MCL) addresses this by using a multi-head network that outputs one hypothesis per head and is trained with a Winner-Takes-All (WTA) scheme. While MCL has already been applied to numerous tasks, its probabilistic interpretation is not fully understood yet. Furthermore, MCL is known to suffer from limitations, such as overconfidence and collapse.To mitigate overconfidence at inference time, where hypotheses that correspond to rare events tend to be over-represented, we learn score heads to predict the probability of each scenario. We show that the resulting model can be interpreted as a geometry-aware conditional density estimator with truncated kernels, by viewing MCL as a quantization method. We validate this on synthetic data and sound event localization.To prevent collapse during training, where only a few heads are selected and the others are not updated, we used deterministic annealing, which enhances the exploration of the hypothesis space during training through a temperature parameter. This is validated on synthetic datasets, where we observe phase transitions: performance suddenly improves at predictable temperature levels.With these tools, we demonstrate the applicability of MCL for sequence modeling. We applied MCL to general time-series and motion forecasting, showcasing the performance of MCL at a light computational cost. Finally, we applied MCL to language modeling. We show how MCL can be adapted in the context of Large Language Models fine-tuning with multiple low-rank adapters. We demonstrate that the method can capture modes in synthetically generated mixtures of Markov chains. We then apply our method to audio and visual captioning, as well as machine translation, showing that our method achieves high diversity and relevance in generated outputs.
• Continuous-variable quantum communication
  
  • Usenko Vladyslav
  • Acín Antonio
  • Alléaume Romain
  • Andersen Ulrik
  • Diamanti Eleni
  • Gehring Tobias
  • Hajomer Adnan A. E.
  • Kanitschar Florian
  • Pacher Christoph
  • Pirandola Stefano
  • Pruneri Valerio
  Reviews of Modern Physics, American Physical Society, 2026, 98 (1), pp.015003. Tremendous progress in experimental quantum optics during the past decades enabled the advent of quantum technologies, one of which is quantum communication. Aimed at novel methods for more secure or efficient information transfer, quantum communication has developed into an active field of research and proceeds toward full-scale implementations and industrialization. Continuous-variable methods of multi-photon quantum state preparation, manipulation, and coherent detection, as well as the respective theoretical tools of phase-space quantum optics, offer the possibility to make quantum communication efficient, applicable and accessible, thus boosting the development of the field. We review the methodology, techniques and protocols of continuous-variable quantum communication, from the first theoretical ideas, through milestone implementations, to the recent developments, covering quantum key distribution as well as other quantum communication schemes, suggested on the basis of continuous-variable states and measurements. (10.1103/mgj7-t6d3)
  DOI : 10.1103/mgj7-t6d3
• Security and Real-Time FPGA Integration for Learned Image Compression
  
  • Eddine Mazouz Alaa
  • Trias Carl de Sousa
  • Chaudhuri Sumanta
  • Cagnazzo Marco
  • Mitrea Mihai
  • Tartaglione Enzo
  • Fiandrotti Attilio
  IEEE Transactions on Multimedia, Institute of Electrical and Electronics Engineers, 2026, pp.1-12. Learned Image Compression (LIC) is gaining traction nowadays, yet real-time performance and secure operations on hardware platforms remain challenging. This work addresses both challenges by presenting an integrated workflow for training, securing, and deploying LIC models on hardware. To achieve a hardware-efficient LIC model, we employ an iterative pruning and quantization process within a standard end-to-end learning framework. Additionally, we introduce Quantization-Aware Watermarking (QAW), a novel technique that embeds a watermark during quantization via a joint loss function, ensuring model integrity and security without degrading video performance. The watermarked weights undergo public-key encryption, enhancing protection by safeguarding both content and user traceability. We evaluate real-time performance, latency, energy consumption, and compression efficiency across two Field Programmable Gate Array (FPGA) platforms, showing that the watermarking and encryption steps introduce minimal overhead, PSNR decreases by 0.2 dB on average, energy consumption increases by 2%, and FPS drops by 6% on average while maintaining real-time constraints and security. Furthermore, our approach outperforms existing hardware-based LIC implementations in FPS and energy efficiency, delivering optimized LIC codecs for HD, FHD, and UHD resolutions at 61, 24, and 14 FPS, respectively. (10.1109/TMM.2026.3676828)
  DOI : 10.1109/TMM.2026.3676828