Publications

2026

• How I Met Your Bias: Investigating Bias Amplification in Diffusion Models
  
  • Roos Nathan
  • Iakovleva Ekaterina
  • Gjergji Ani
  • Pastore Vito Paolo
  • Tartaglione Enzo
  , 2026, pp.5374-5383. Diffusion-based generative models demonstrate state-of-the-art performance across various image synthesis tasks, yet their tendency to replicate and amplify dataset biases remains poorly understood. Although previous research has viewed bias amplification as an inherent characteristic of diffusion models, this work provides the first analysis of how sampling algorithms and their hyperparameters influence bias amplification. We empirically demonstrate that samplers for diffusion models – commonly optimized for sample quality and speed – have a significant and measurable effect on bias amplification. Through controlled studies with models trained on Biased MNIST, Multi-Color MNIST and BFFHQ, and with Stable Diffusion, we show that sampling hyperparameters can induce both bias reduction and amplification, even when the trained model is fixed. Source code is available at https://github.com/How-I-met-your-bias/how_i_met_your_bias. (10.1109/WACV61042.2026.00521)
  DOI : 10.1109/WACV61042.2026.00521
• 5G-EcoSim: A Simulation Framework for Estimating 5G Energy Consumption Using Real-World Data and Analytical Models
  
  • Ghali Meriem
  • Busson Anthony
  • Coupechoux Marceau
  , 2026, pp.1-8. The definition and deployment of next-generation mobile networks must incorporate considerations of sustainability and environmental impact. In this context, estimating the energy consumption of a mobile network deployment across a city or region is of utmost importance. Nationwide historical aggregate values are informative but do not allow to understand the underlying dynamics or to perform prospective studies. There is hence a need for bottom-up approaches to assess the energy consumption of mobile networks. However, this is a complex task, as it depends on numerous factors, including the number and spatial distribution of base stations, the underlying technologies and their configuration, as well as user demand patterns and their geographic distribution. This paper thus introduces a simulation framework aimed at estimating the energy consumption of 5G networks at urban, regional or national scale. The framework integrates radio propagation models operating in the 3.5 GHz band with publicly available datasets describing user and base station locations, as well as network traffic volumes. As a case study, we consider the 5G deployment in France and examine the spatial distribution of network load and the resulting energy consumption. The source code and datasets are publicly available, ensuring that the simulator is fully reproducible and easily adaptable to other use cases, countries, or regions. (10.23919/WONS68803.2026.11501828)
  DOI : 10.23919/WONS68803.2026.11501828
• Statistical wave field theory: Anisotropic wave fields under Neumann's boundary condition
  
  • Badeau Roland
  Journal of the Acoustical Society of America, Acoustical Society of America, 2026, 159 (3), pp.2265-2280. The statistical wave field theory mathematically establishes the statistical laws of the solutions to the wave equation in a bounded domain. It provides the closed-form expressions of the power distribution and the correlations of the wave field jointly over time, frequency, and space, which hold at high frequency and after many reflections, in terms of the geometry and the specific admittance of the boundary surface. This theory was originally developed in the particular case of mixing rooms, which are characterized by a diffuse wave field, based on the theory of dynamical billiards and on Weyl-like asymptotic laws. Then it was extended to the finite family of special polyhedra, where the wave field is anisotropic, based on a simpler geometric approach related to mathematical crystallography. In this paper, we introduce a unified version of the theory dedicated to a class of semi-mixing billiards. In the case of Neumann's boundary condition, we show that the wave field is stationary, but it is generally anisotropic. In particular, the correlation between two spatial positions at a given frequency is different from the well-known cardinal sine formula that characterizes diffuse acoustic fields. (10.1121/10.0042450)
  DOI : 10.1121/10.0042450
• Capsule networks do not need to model everything
  
  • Renzulli Riccardo
  • Tartaglione Enzo
  • Grangetto Marco
  Pattern Recognition, Elsevier, 2026, 171, Part A, pp.112119 (1-11). Capsule networks are biologically inspired neural networks that group neurons into vectors called capsules, each explicitly representing an object or one of its parts. The routing mechanism connects capsules in consecutive layers, forming a hierarchical structure between parts and objects, also known as a parse tree. Capsule networks often attempt to model all elements in an image, requiring large network sizes to handle complexities such as intricate backgrounds or irrelevant objects. However, this comprehensive modeling leads to increased parameter counts and computational inefficiencies. Our goal is to enable capsule networks to focus only on the object of interest, reducing the number of parse trees. We accomplish this with REM (Routing Entropy Minimization), a technique that minimizes the entropy of the parse tree-like structure. REM drives the model parameters distribution towards low entropy configurations through a pruning mechanism, significantly reducing the generation of intra-class parse trees. This empowers capsules to learn more stable and succinct representations with fewer parameters and negligible performance loss. (10.1016/j.patcog.2025.112119)
  DOI : 10.1016/j.patcog.2025.112119
• Carbon Footprint of Urban 5G Traffic in Lyon Based on Real-World Data and Analytical Modeling
  
  • Ghali Mériem
  • Busson Anthony
  • Coupechoux Marceau
  Annals of Telecommunications - annales des télécommunications, Springer, 2026, pp.1-16. The deployment of 5G networks has generated significant debate regarding its environmental implications, particularly concerning carbon emissions. Although 5G technology offers improved energy efficiency per bit transmitted, concerns persist due to potential rebound effects and the significant carbon footprint associated with infrastructure deployment and baseline energy consumption. This paper presents a bottom-up approach combining a detailed radio load model and spatial distribution of users to precisely estimate the energy usage and carbon emissions of 5G networks using the 3.5 GHz band. Although the model is valid for other regions, we focus specifically on the city of Lyon in France, providing a detailed assessment of current emissions (2021-2024) and projections up to 2050, incorporating traffic growth and national energy decarbonization scenarios. At the base station scale, our results show that emissions generated by hardware manufacturing and baseline energy consumption constitute the dominant contributors to the overall carbon footprint, compared with emissions induced by traffic load. As a result, our projections indicate that an increase in traffic demand does not significantly impact the carbon footprint unless it necessitates the deployment of additional base stations. By 2050, infrastructure-related emissions could constitute up to 70% of total network emissions, highlighting a major challenge in the management of network growth to avoid rebound effect. The study demonstrates that decarbonizing electricity and enhancing energy efficiency alone are insufficient. (10.1007/s12243-026-01166-9)
  DOI : 10.1007/s12243-026-01166-9
• Decentralized Ranking Aggregation: Gossip Algorithms for Borda and Copeland Consensus
  
  • van Elst Anna
  • Le Caillec Kerrian
  • Colin Igor
  • Clémençon Stéphan
  , 2026. <div><p>The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often originating in social choice theory, have been documented in the literature, offering theoretical guarantees in a centralized setting, i.e., when all the ranking data to be aggregated can be brought together in a single computing unit. For many technologies (e.g. peer-to-peer networks, IoT, multi-agent systems), extending the ability to calculate consensus rankings with guarantees in a decentralized setting, i.e., when preference data is initially distributed across a communicating network, remains a major methodological challenge. Indeed, in recent years, the literature on decentralized computation has mainly focused on computing or optimizing statistics such as arithmetic means using gossip algorithms. The purpose of this article is precisely to study how to achieve reliable consensus on collective rankings using classical rules (e.g. Borda, Copeland) in a decentralized setting, thereby raising new questions, robustness to corrupted nodes, and scalability through reduced communication costs in particular. The approach proposed and analyzed here relies on random gossip communication, allowing autonomous agents to compute global ranking consensus using only local interactions, without coordination or central authority. We provide rigorous convergence guarantees, including explicit rate bounds, for the Borda and Copeland consensus methods. Beyond these rules, we also provide a decentralized implementation of consensus according to the median rank rule and local Kemenization. Extensive empirical evaluations on various network topologies and real and synthetic ranking datasets demonstrate that our algorithms converge quickly and reliably to the correct ranking aggregation. This work paves the way for principled collective decision-making in fully decentralized systems.</p></div>
• Exploiting Subgradient Sparsity in Max-Plus Neural Networks
  
  • Enaieh Ikhlas
  • Fercoq Olivier
  , 2026. Deep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Max-Plus neural architecture in which classical addition and multiplication are replaced with maximum and summation operations respectively. This is a promising architecture in terms of interpretability, but its training is challenging. A particular feature is that this algebraic structure naturally induces sparsity in the subgradients, as only neurons that contribute to the maximum affect the loss. However, standard backpropagation fails to exploit this sparsity, leading to unnecessary computations. In this work, we focus on the minimization of the worst sample loss which transfers this sparsity to the optimization loss. To address this, we propose a sparse subgradient algorithm that explicitly exploits the algebraic sparsity. By tailoring the optimization procedure to the non-smooth nature of Max-Plus models, our method achieves more efficient updates while retaining theoretical guarantees. This highlights a principled path toward bridging algebraic structure and scalable learning.
• On A Class Of Dynamical Poisson-Voronoi Tessellations
  
  • Baccelli François
  • Kumar Jhawar Sanjoy
  , 2025. Consider a dynamical network model featuring mobile stations on the Euclidean plane. The initial locations of the stations are given by a homogeneous Poisson point process. The stations are all moving at a constant speed and in a random direction. Consider fixed users located in the Euclidean plane, which are served by the mobile stations. Each user stays connected to the nearest station at any given point of time. Since the stations are moving, an user disconnects and connects with different stations over time, by always selecting which ever station is the closest. This gives rise to a dynamical version of the Poisson-Voronoi tessellation. The focus of this paper is on the sequence of "handover" events of a typical user, which are the epochs when its association changes. This defines a point process on the time-axis, the "handover point process". We show that this point process is stationary and we determine its main properties, in particular its intensity and the joint distribution of its inter-event times. We also analyze the handover Palm distributions of several variables of practical interest. This includes the distance to the closest mobile stations and the point process of all other mobile stations at handover epochs. The analysis is conducted both in the single-speed and in the multi-speed scenarios. It leads to the identification of the three dimensional state variables that "Markovize" the association dynamics. The analysis is based on a specific system of non-compact particles. The motivations are in the modeling of low or medium orbit satellite wireless communication networks. The model studied here is a planar "caricature" of this problem, which is initially defined on the sphere.
• D3.2 – Certification Roadmap
  
  • Alleaume Romain
  , 2026. This document gives, in a first part, an overview of the efforts undertaken towards the security certification of Quantum Key Distribution (QKD), and presents a gap analysis of the first QKD Protection Profile published in 2023. In a second part, a new methodological framework for QKD security proof, well adapted for a furture standardization is presented, and compared to previous approaches.
• Texo: Formula Recognition within 20M Parameters
  
  • Mao Sicheng
  , 2026. In this paper we present Texo, a minimalist yet highperformance formula recognition model that contains only 20 million parameters. By attentive design, distillation and transfer of the vocabulary and the tokenizer, Texo achieves comparable performance to state-of-the-art models such as UniMERNet-T and PPFormulaNet-S, while reducing the model size by 80% and 65%, respectively. This enables real-time inference on consumer-grade hardware and even in-browser deployment. We also developed a web application to demonstrate the model capabilities and facilitate its usage for end users.
• Qiana: A First-Order Formalism to Quantify over Contexts and Formulas with Temporality
  
  • Coumes Simon
  • Paris Pierre-Henri
  • Schwarzentruber François
  • Suchanek Fabian
  Journal of Artificial Intelligence Research, Association for the Advancement of Artificial Intelligence, 2026, 85, pp.12:1-12:35. We introduce Qiana, a logic framework for reasoning on formulas that are true only in specific contexts. In Qiana, it is possible to quantify over both formulas and contexts to express, e.g., that “everyone knows everything Alice says”. Qiana also permits paraconsistent logics within contexts, so that contexts can contain contradictions. Furthermore, Qiana is based on first-order logic, and is finitely axiomatizable, so that Qiana theories are compatible with pre-existing first-order logic theorem provers. We show how Qiana can be used to represent temporality, event calculus, and modal logic. We also discuss different design alternatives of Qiana. (10.1613/jair.1.18402)
  DOI : 10.1613/jair.1.18402
• Deep learning of self-supervised audio representation for general audio and music tagging
  
  • Quélennec Aurian
  , 2026. The objective of this dissertation is to develop new deep learning methods for building general-purpose audio foundation models capable of learning meaningful representations without annotated data. We first conduct a systematic analysis of both self-supervised and supervised audio foundation models within a shared evaluation protocol. In particular, we study their inference behavior and measure how robust they are to variations in input segment duration. This analysis provides practical guidance for choosing pre-trained audio embeddings and highlights the strong robustness of Audio Spectrogram Transformer models when processing shorter audio segments. Building on these observations, we propose MATPAC, a self-supervised method based on Masked Latent Prediction combined with an unsupervised classification objective. This design encourages the model to learn both predictive and semantic structure, leading to representations that outperform previous self-supervised approaches and rival supervised models. We then introduce an improved version, MATPAC++, which addresses the ambiguity of predicting masked content by generating multiple hypotheses and selecting among them with Multiple Choice Learning. This variant achieves state-of-the-art performance on various audio tagging tasks. Finally, we explore how these models can be reused in different contexts. We demonstrate that their learned representations can be efficiently compressed into small models without labels, and we show that they can serve as conditioning modules in multimodal systems. In particular, we introduce TinyMU, a compact music language model that leverages MATPAC++ to achieve high-level music reasoning while remaining lightweight and deployable.
• RV-Sec5: Enhancing RISC-V Security Evaluation via Targeted ISA-Level Instrumentation using gem5
  
  • Awais Muhammad
  • Mushtaq Maria
  • Naviner Lirida
  • Bruguier Florent
  • Haj Yahya Jawad
  , 2026, pp.10-19. The modularity of the RISC-V Instruction Set Architecture (ISA) has accelerated its adoption in security-critical domains, yet it introduces significant challenges for pre-silicon security validation. Current evaluation methods often rely on high-level emulation that overlooks microarchitectural side effects or post-silicon testing that identifies vulnerabilities too late in the design cycle. This paper presents RV-Sec5, a systematic framework for ISA-level security evaluation that leverages the gem5 simulator. Unlike standard simulators, RV-Sec5 introduces a methodology to map high-level security invariants-such as privilege isolation and memory protection-directly to automated, cycle-accurate instrumentation points within the ISA decoder. This approach bridges the semantic gap between abstract security policies and low-level hardware execution. We demonstrate the framework's efficacy through a case study involving unauthorized Control and Status Register (CSR) modifications, showing how RV-Sec5 detects privilege escalation attempts and monitors microarchitectural anomalies, such as TLB flushes and cache state changes, in real-time. (10.1145/3793638.3793640)
  DOI : 10.1145/3793638.3793640
• Optimal Quantum Algorithm for Gibbs State Preparation
  
  • Rouzé Cambyse
  • Stilck França Daniel
  • Alhambra Álvaro
  Physical Review Letters, American Physical Society, 2026, 136 (6), pp.060601. It is of great interest to understand the thermalization of open quantum many-body systems, and how quantum computers are able to efficiently simulate that process. A recently introduced dissipative evolution, inspired by existing models of open system thermalization, has been shown to be efficiently implementable on a quantum computer. Here, we prove that, at high enough temperatures, this evolution reaches the Gibbs state in time scaling logarithmically with system size. The result holds for Hamiltonians that satisfy the Lieb-Robinson bound, such as local Hamiltonians on a lattice, and includes long-range systems. To the best of our knowledge, these are the first results rigorously establishing the rapid mixing property of high-temperature quantum Gibbs samplers, which is known to give the fastest possible speed for thermalization in the many-body setting. We then apply our result to the problem of estimating partition functions at high temperature, showing an improved performance over previous classical and quantum algorithms. (10.1103/lhht-svmn)
  DOI : 10.1103/lhht-svmn
• DRAGON: Robust Classification for Very Large Collections of Software Repositories
  
  • Balla Stefano
  • Zacchiroli Stefano
  • Degueule Thomas
  • Falleri Jean-Rémy
  • Robbes Romain
  , 2026. The ability to automatically classify source code repositories with "topics" that reflect their content and purpose is very useful, especially when navigating or searching through large software collections. However, existing approaches often rely heavily on README files and other metadata, which are frequently missing, limiting their applicability in real-world large-scale settings. We present DRAGON, a repository classifier designed for very large and diverse software collections. It operates entirely on lightweight signals commonly stored in version control systems: file and directory names, and optionally the README when available. In repository classification at scale, DRAGON improves F1@5 from 54.8% to 60.8%, surpassing the state of the art. DRAGON remains effective even when README files are absent, with performance degrading by only 6% w.r.t. when they are present. This robustness makes it practical for real-world settings where documentation is sparse or inconsistent. Furthermore, many of the remaining classification errors are near misses, where predicted labels are semantically close to the correct topics. This property increases the practical value of the predictions in real-world software collections, where suggesting a few related topics can still guide search and discovery. As a byproduct of developing DRAGON, we also release the largest open dataset to date for repository classification, consisting of 825 thousand repositories with associated ground-truth topics, sourced from the Software Heritage archive, providing a foundation for future large-scale and language-agnostic research on software repository understanding.
• Efficient Online Variational Estimation via Monte Carlo Sampling
  
  • Chagneux Mathis
  • Müller Mathias
  • Gloaguen Pierre
  • Le Corff Sylvain
  • Olsson Jimmy
  , 2026. This article addresses online variational estimation in parametric state-space models. We propose a new procedure for efficiently computing the evidence lower bound and its gradient in a streaming-data setting, where observations arrive sequentially. The algorithm allows for the simultaneous training of the model parameters and the distribution of the latent states given the observations. It is based on i.i.d. Monte Carlo sampling, coupled with a well-chosen deep architecture, enabling both computational efficiency and flexibility. The performance of the method is illustrated on both synthetic data and real-world air-quality data. The proposed approach is theoretically motivated by the existence of an asymptotic contrast function and the ergodicity of the underlying Markov chain, and applies more generally to the computation of additive expectations under posterior distributions in state-space models.
• Towards Reliable LLM-Based Model Driven Engineering: when Full Syntax Checking and Formal Verification Join the Loop
  
  • Sultan Bastien
  • Apvrille Ludovic
  , 2026. Model-Driven Engineering facilitates the design of embedded systems by promoting abstraction and enabling early verification of design correctness. Recent approaches have integrated Large Language Models into MDE workflows to automatically generate models from textual specifications. However, these models often require extensive prompt refinement and lack formal guarantees of correctness. This paper introduces an enhanced LLM-based generation process in TTool-AI, incorporating a novel dual feedback loop that combines automated syntactic checking with formal verification of safety properties. The loop iteratively refines LLM-generated SysML block and state-machine diagrams to ensure syntactic validity and verify safety properties. First experimental evaluation on both academic and industrial-grade specifications demonstrates that the proposed mechanism reliably produces syntactically correct models, enabling direct model checking of LLM-produced models and reducing the effort required by engineers to obtain correct-by-construction designs.
• Collaborative Action on Timing InterferenCes: Summary and Perspectives at Mid-term
  
  • Maiza Claire
  • Rieg Lionel
  • Asavoae Mihail
  • Béchennec Jean-Luc
  • Blouin Dominique
  • Brandner Florian
  • Carle Thomas
  • Cassé Hugues
  • Faucou Sébastien
  • Ferres Bruno
  • Hladik Pierre-Emmanuel
  • Erwan Jahier
  • Jan Mathieu
  • Jenn Éric
  • Jezequel Loïg
  • Potop Butucaru Dumitru
  • Puaut Isabelle
  • Raymond Pascal
  • Rochange Christine
  • Sotin Pascal
  • Parent-Vigouroux Catherine
  • Zahaf Houssam
  • Chabot Hector
  • Essabyr Maha
  • Jeanmougin Louison
  • Rebhi Hichem
  , 2026, pp.1-11. CAOTIC is an ambitious initiative aimed at pooling and coordinating the efforts of major French research teams working on timing analysis of multicore real-time systems, with a focus on interference due to shared resources. The objective is to enable the efficient use of multicores in critical systems. Based on a better understanding of timing anomalies and interference, considering the specificities of applications (structural properties and execution model), and revisiting the links between timing analysis and synthesis processes (code generation, mapping, scheduling), we target significant progresses in timing analysis models and techniques for critical systems, as well as in methodologies for their application in industry. In this paper, at project mid-term, we show the progress of the project. We also present some original work, about the use of a Tricore plaform and its timing model, and discuss open questions and future work. (10.82331/ERTS.2026.27)
  DOI : 10.82331/ERTS.2026.27
• Characterization of EMF exposure induced by French cellular networks
  
  • Liu Jiang
  • Wang Shanshan
  • Haider Zain
  • Sun Qunfei
  • Zhang Yarui
  • Bories Serge
  • Ourak Lamine
  • Wiart Joe
  Annals of Telecommunications - annales des télécommunications, Springer, 2026, pp.1-21. Abstract This study presents a comprehensive evaluation of electromagnetic exposure in operational French fourth generation (4 G)/long term evolution (LTE) networks, combining field measurements with computational modeling to assess both uplink (UL) and downlink (DL) contributions. We introduce the novel Radiated Energy per Bit Transmitted (REBT) metric to quantify network radiated energy efficiency, while characterizing TX power patterns across different services, revealing higher mean-to-maximum power ratios for data services compared to voice calls. Through analysis of a representative 2600 MHz user, we demonstrate field-strength-dependent exposure dynamics: with DL field strength of 1 V/m, UL contributes 30% (head) and 12.8% (whole body) of total exposure, while at 0.38 V/m, UL becomes predominant (75% head, 50.4% whole body). Notably, the relative contribution of UL exposure to the total head exposure is consistently higher than that of DL exposure across all scenarios. All measured exposure levels remain well below ICNIRP safety limits, validating safety compliance of LTE. The study establishes an important methodological framework, combining the global exposure index with detailed transfer function analysis, providing critical insights for both current 4 G and emerging fifth generation (5 G) exposure assessments. (10.1007/s12243-026-01156-x)
  DOI : 10.1007/s12243-026-01156-x
• Layer Collapse Can be Induced by Unstructured Pruning
  
  • Liao Zhu
  • Quétu Victor
  • Nguyen Van-Tam
  • Tartaglione Enzo
  Transactions of Machine Learning Research, Transactions on Machine Learning Research, 2026. <div><p>Unstructured pruning is a popular compression method for efficiently reducing model parameters. However, while it effectively decreases the number of parameters, it is commonly believed that unstructured pruning cannot shorten the computational critical path, i.e., the maximum number of layers traversed during forward propagation.</p><p>In this paper, we study when and how unstructured pruning can yield structural effects. For rectifier-activated networks, we introduce the notion of neuron entropy, which quantifies the degree of nonlinearity utilization. We show that magnitude-based pruning naturally lowers this entropy, sometimes down to zero-entropy layers that become linearizable and can thus be removed. Building on this insight, we propose a method that leverages "unstructured" pruning to favor sparsity in low-entropy layers, enabling their complete removal. We validate the phenomenon across CNNs, Vision Transformers, and NLP models: unstructured pruning can induce effective layer removal with little or no performance degradation in over-parameterized networks. Our code is available at https://github.com/ZhuLIAO001/NEPENTHE.git.</p></div>
• Reconfigurable intelligent surfaces (RIS) using NOMA with energy harvesting from vibrations for 6G
  
  • Boujemaa Hatem
  • Alhussein Musaed
  • Rekaya Ghaya
  Annals of Telecommunications - annales des télécommunications, Springer, 2026, 81 (1-2), pp.121-131. Reconfigurable Intelligent Surfaces (RIS) enhance wireless communication by dynamically controlling electromagnetic waves. When combined with Non-Orthogonal Multiple Access (NOMA), RIS optimizes spectrum usage, allowing multiple users to share the same frequency via power domain multiplexing. This integration improves network capacity, spectral efficiency, and signal quality while reducing interference. Adding vibration-based energy harvesting to RIS with NOMA enables sustainable, autonomous operation in power-limited environments. This paper examines the potential of integrating RIS, NOMA, and vibration energy harvesting to advance sustainable, efficient wireless communication. (10.1007/s12243-025-01095-z)
  DOI : 10.1007/s12243-025-01095-z
• SIBH structure integration approaches and building blocks for next generation of transceivers on Indium Phosphide
  
  • Prado de la Cruz Shirley
  , 2026. Data traffic has significantly increased in recent years and is expected to keep rising due to bandwidth-intensive services such as Artificial Intelligence (AI) and high-definition gaming. One approach to enhance transmission data rates is to develop transceivers based on photonic integrated circuits (PICs), which are the key elements responsible for transmitting and receiving signals in Passive Optical Networks (PONs). The fundamental components forming a PIC, known as building blocks (BBs), are the focus of this work.Three approaches were investigated to improve the transmission capabilities of next-generation transceivers. The first concerns the development of SIBH technology used for the fabrication of active BBs. A one-step SIBH structure incorporating a blocking layer was developed. Several studies were conducted to evaluate the influence of growth temperature and layer thickness, with the optimal parameters identified as a growth temperature of 520 °C and a thickness of 40 nm. Additional investigations were also carried out on alternative materials for the semi-insulating layers of the SIBH structure, such as InP:Be and InP:Ru.The second approach focuses on passive BBs. Fabrication processes were developed to enable the monolithic integration of passive and active components despite their two different waveguide architectures (SIBH and deep-ridge). The main challenge encountered was the formation of polycrystals due to the SIBH regrowth, resulting in propagation losses exceeding 10 dB/cm for 1.5 µm deep-ridge waveguides. This issue was successfully resolved using an improved second fabrication process.Finally, a new InP (de)multiplexer structure based on a tilted angled multimode interferometer (AMMI) was developed. The device exhibits a compact footprint of 0,09 mmµ^2µ, a crosstalk level of 14.35 dB, and an insertion loss of 8 dB. (10.70675/57eec20fz9626z4acdza586z2ddef81a9013)
  DOI : 10.70675/57eec20fz9626z4acdza586z2ddef81a9013
• Random Stinespring superchannel: converting channel queries into dilation isometry queries
  
  • Girardi Filippo
  • Mele Francesco Anna
  • Zhao Haimeng
  • Fanizza Marco
  • Lami Ludovico
  , 2025. The recently introduced random purification channel, which converts $n$ copies of an arbitrary mixed quantum state into $n$ copies of the same uniformly random purification, has emerged as a powerful tool in quantum information theory. Motivated by this development, we introduce a channel-level analogue, which we call the random Stinespring superchannel. This consists in a procedure to transform $n$ parallel queries of an arbitrary quantum channel into $n$ parallel queries of the same uniformly random Stinespring isometry, via universal encoding and decoding operations that are efficiently implementable. When the channel is promised to have Choi rank at most $r$, the procedure can be tailored to yield a Stinespring environment of dimension $r$. As a consequence, quantum channel learning reduces to isometry learning, yielding a simple channel learning algorithm, based on existing isometry learning protocols, that matches the performance of the two recently proposed channel tomography algorithms. Complementarily, whereas the optimality of these algorithms had previously been established only up to a logarithmic factor in the dimension, we close this gap by removing this logarithmic factor from the lower bound. Taken together, our results fully establish the optimality of these recently introduced channel learning algorithms, showing that the optimal query complexity of learning a quantum channel with input dimension $d_A$, output dimension $d_B$, and Choi rank $r$ is $Θ(d_A d_B r)$.
• Unrolled Multiplicative Updates for Nonnegative Matrix Factorization applied to Hyperspectral Unmixing
  
  • Kervazo Christophe
  • Cohen Jérémy E.
  , 2026. HyperSpectral Unmixing (HSU), the problem of separating mixed spectra of overlapping materials in a hyperspectral image, has motivated dedicated algorithmic developments in the last two decades. On the one hand, traditional model-based algorithms frequently guarantee interpretable results. On the other hand, deep-learning-based approaches are often faster at inference time and may obtain better empirical results. This work utilizes the strengths of both approaches by building on the deep unrolling paradigm. Our contribution is twofold. First, we propose two new algorithms based on deep unrolling of the well-known Multiplicative Updates. The first, coined Non-Adaptive Learned Multiplicative Updates (NALMU), adopts a simple element-wise multiplicative scheme. The second, called Recursive Adaptive Learned Multiplicative Updates (RALMU), has more flexible updates and better take into account the spatial correlations in the abundances. Second, we relate NALMU to the minimization of an explicit cost function under some assumptions. Such guarantees are unique in the HSU field. NALMU and RALMU are tested on astrophysics and remote sensing datasets. They outperform the other deep learning-based HSU algorithms and classical iterative schemes for the endmember estimates and obtain competitive results for the abundance estimates, even when trained in a self-supervised way. The code used in this paper will be made available upon publication.
• The NPA hierarchy does not always attain the commuting operator value
  
  • Fanizza Marco
  • Kroell Larissa
  • Mehta Arthur
  • Paddock Connor
  • Rochette Denis
  • Slofstra William
  • Zhao Yuming
  , 2025. We show that it is undecidable to determine whether the commuting operator value of a nonlocal game is strictly greater than 1/2. Specifically, there is a computable mapping from Turing machines to /boolean constraint system (BCS) nonlocal games in which the halting property of the machine is encoded as a decision problem for the commuting operator value of the game. As a corollary, there is a BCS game for which the value of the Navascués-Pironio-Acín (NPA) hierarchy does not attain the commuting operator value at any finite level. (10.48550/arXiv.2510.04943)
  DOI : 10.48550/arXiv.2510.04943