Publications

2026

• 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predictions exhibit semantic proximity to ground truth entities, highlighting the LLM's accurate disambiguation of historical references.
• 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%.
• 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.
• From Weights to Layers : Deep Neural Network Compression for Efficient Inference
  
  • Quétu Victor
  , 2026. Deep learning models continue to grow in depth and computational cost, yet modern inference pipelines remain constrained by latency, memory, and energy budgets. This thesis investigates where redundant computation hides in over-parameterized architectures, and how to remove it safely. We first analyze the Sparse Double Descent phenomenon and show how aggressive sparsification can paradoxically enhance generalization. We characterize this behavior and propose regularization and distillation-based approaches supported by an entropy-based metric. Building on this metric, we introduce three familiesof depth-reduction strategies: entropy-based pruning (EGP, EASIER), BatchNorm-guided layer collapse(TLC), and Optimal Transport–based inductive regularization (LaCoOT). Together, these methods reduce up to 70% of network depth across CNNs, Transformers, and diffusion models, often with minimal performance degradation, and sometimes even gains in accuracy. Finally, we extend the notion of redundancy to the operand by proposing FOLDER, a training-free token-pruning module that accelerates multimodal LLMs by up to 2.4 times with preserved or improved performance. Collectively, these contributions advance the understanding of redundancy in deep networks and propose general strategies for improving inference efficiency, paving the way toward more sustainable and adaptive deep learning models. (10.70675/119fe6b4z7f81z4dccza002z1b60abad57b4)
  DOI : 10.70675/119fe6b4z7f81z4dccza002z1b60abad57b4
• Where Experts Disagree, Models Fail: Detecting Implicit Legal Citations in French Court Decisions
  
  • Floro Avrile
  • Dhorasoo Tamara
  • Pellez Soline
  • Holzenberger Nils
  , 2026. Computational methods applied to legal scholarship hold the promise of analyzing law at scale. We start from a simple question: how often do courts implicitly apply statutory rules? This requires distinguishing legal reasoning from semantic similarity. We focus on implicit citation of the French Civil Code in first-instance court decisions and introduce a benchmark of 1,015 passage-article pairs annotated by three legal experts. We show that expert disagreement predicts model failures. Inter-annotator agreement is moderate (κ = 0.33) with 43% of disagreements involving the boundary between factual description and legal reasoning. Our supervised ensemble achieves F1 = 0.70 (77% accuracy), but this figure conceals an asymmetry: 68% of false positives fall on the 33% of cases where the annotators disagreed. Despite these limits, reframing the task as top-k ranking and leveraging multi-model consensus yields 76% precision at k = 200 in an unsupervised setting. Moreover, the remaining false positives tend to surface legally ambiguous applications rather than obvious errors.
• 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
• Simulation of Fog-Induced Attenuation and Inter-Symbol Interference in Mid-and Long-Infrared Free-Space Optical Communications
  
  • Breton Vicente Alberto
  • Sorrente Béatrice
  • Roux Aurélien
  • Fade Julien
  • Da Silva Anabela
  • Grillot Frédéric
  , 2026. <div><p>Free-space optical (FSO) communications offer large bandwidths but are strongly affected by atmospheric fog. Recent advances in quantum cascade lasers enable high-speed transmission in the mid-and long-infrared ranges (3-6 and 8-12 µm), which are expected to provide increased robustness compared to the conventional visible or 1.55 µm bands. In this work, light propagation through fog is modeled using a time-domain approximate radiative transfer equation solver, accounting for wavelength-dependent scattering, absorption, and droplet size distributions of a realistic fog scenario, demonstrating its advantages against visibility-based models for satisfactory evaluation of FSO links performance in the mid-and long-infrared. The model is applied to an example optical communication link to assess attenuation and inter-symbol interference effects. Quantitative results indicate that long-infrared wavelengths exhibit reduced temporal spreading and improved tolerance to fog-induced impairments.</p></div>
• Towards a systemic framework for assessing the environmental rebound effects of Artificial Intelligence
  
  • Delarue Simon
  , 2025.
• 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
• An order-reversing embedding of Turing degrees into Arthur-Nimue-Merlin degrees
  
  • Abou-Samra Jean
  • Madore David Alexander
  , 2026. <div><p>The Arthur-Nimue-Merlin degrees are a generalization of the Turing degrees introduced by Kihara as a tangible description of the partially ordered set of Lawvere-Tierney topologies on the effective topos (equivalently, subtoposes of the effective topos). They are defined in terms of a three-player game that introduces both angelic and demonic nondeterminism into oracle queries. We construct an order embedding of the Turing degrees with their order reversed into the Arthur-Nimue-Merlin degrees, whose image we call the "co-Turing degrees"; we then study the order relationship of these co-Turing degrees with the (naturally embedded) Turing degrees within the Arthur-Nimue-Merlin degrees.</p></div>
• The Hi-Audio Online Platform for Recording and Distributing Multi-Track Music Datasets
  
  • Gil Panal José M
  • David Aurélien
  • Richard Gaël
  EURASIP Journal on Audio, Speech, and Music Processing, SpringerOpen, 2026 (Special issue on "Signal Processing for the Internet of Sounds"). This paper introduces the Hi-Audio online platform, an open-source tool designed to support musicians and researchers in the field of Music Information Retrieval (MIR). The platform enables the recording, uploading, and sharing of multitrack musical compositions, aiming to build an open-access audio database to advance research in music technology. Uploaded audio files are automatically analyzed upon synchronization with the server, leveraging signal processing techniques and machine learning models to generate rich metadata. The platform facilitates remote and asynchronous collaboration via a web-based interface accessible at hiaudio.fr. Furthermore, a novel built-in method for accurate and robust round-trip latency estimation in the browser is proposed and integrated into the platform, demonstrating its applicability in real-world distributed recording scenarios. Finally, an initial user evaluation with musicians was conducted to assess usability and practical relevance under realistic usage conditions. The evaluation combined task-based performance analysis with standardized usability and workload measures. The results indicate high task completion rates for core recording functions and show that the platform can be used effectively by musicians with minimal prior training. (10.1186/s13636-026-00459-0)
  DOI : 10.1186/s13636-026-00459-0
• Compression in 3D Gaussian Splatting: A Survey of Methods, Trends, and Future Directions
  
  • Ali Muhammad Salman
  • Zhang Chaoning
  • Cagnazzo Marco
  • Valenzise Giuseppe
  • Tartaglione Enzo
  • Bae Sung-Ho
  IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2026, pp.1-1. <div><p>Gaussian Splatting (3DGS) has recently emerged as a pioneering approach in explicit scene rendering and computer graphics. Unlike traditional neural radiance field (NeRF) methods, which typically rely on implicit, coordinatebased models to map spatial coordinates to pixel values, 3DGS utilizes millions of learnable 3D Gaussians. Its differentiable rendering technique and inherent capability for explicit scene representation and manipulation positions 3DGS as a potential game-changer for the next generation of 3D reconstruction and representation technologies. This enables 3DGS to deliver realtime rendering speeds while offering unparalleled editability levels. However, despite its advantages, 3DGS suffers from substantial memory and storage requirements, posing challenges for deployment on resource-constrained devices. In this survey, we provide a comprehensive overview focusing on the scalability and compression of 3DGS. We begin with a detailed background overview of 3DGS, followed by a structured taxonomy of existing compression methods. Additionally, we analyze and compare current methods from the topological perspective, evaluating their strengths and limitations in terms of fidelity, compression ratios, and computational efficiency. Furthermore, we explore how advancements in efficient NeRF representations can inspire future developments in 3DGS optimization. Finally, we conclude with current research challenges and highlight key directions for future exploration.</p></div> (10.1109/TCSVT.2026.3676048)
  DOI : 10.1109/TCSVT.2026.3676048
• 3D Imaging Contribution in Pediatric Surgical Oncology: A Multistakeholder Assessment Study
  
  • Pio Luca
  • Kassir Rani
  • La Barbera Giammarco
  • Lozach Cecile
  • Bonnot Enzo
  • Isla Thomas
  • Pablo de la Plata Alcalde Juan
  • Gori Pietro
  • Bloch Isabelle
  • Sarnacki Sabine
  Scientific Reports, Nature Publishing Group, 2026 (16), pp.14264-1:14264-10. Introduction: Medical imaging is crucial for surgical planning, yet surgeons struggle with mental transformation of 2D images into 3D representations, particularly in complex pediatric pelvic anatomy. This study evaluated perceived benefits of 3D imaging with tractography compared to conventional 2D MRI in pediatric pelvic tumor surgery.<p>Methods: A nationwide study assessed three groups: non-medical personnel (n=30), medical trainees (residents and fellows; primary analysis n=61, excluding 3 medical students), and senior pediatric surgeons (n=12). Using 3-Tesla MRI with specialized protocols including highresolution CoroT2cube and diffusion tensor imaging, participants evaluated five clinical cases in both 2D and 3D formats using 7-point Likert scales. Statistical analysis employed Wilcoxon paired tests with Bonferroni correction.</p><p>Results: All groups showed significant improvements in perceived understanding with 3D imaging. Non-medical personnel scores increased from 4.24 (±0.69) to 6.27 (±0.28) (p&lt;0.001), particularly in understanding disease and surgical objectives. Medical trainees improved from 5.08 (±0.61) to 6.42 (±0.49) (p&lt;0.001), with enhanced understanding of surgical objectives and anatomical relationships. Senior surgeons' scores increased from 5.02 (±0.69) to 6.33 (±0.52) (p&lt;0.001), showing significant improvements in preoperative planning and family communication. Effect sizes were substantial across groups (Cohen's d: 2.80, 1.90, and 1.52 respectively), though the within-subject design likely contributes to effect size inflation.</p><p>Discussion: This study provides preliminary evidence for perceived 3D imaging value in pediatric pelvic tumor surgery. Improved anatomical comprehension among non-medical personnel may benefit informed consent, while enhanced visualization aids surgical education and planning. High surgeon acceptance (92%) suggests strong acceptability, though these exploratory findings require validation before implementation recommendations can be made.</p><p>Prospective studies evaluating objective clinical outcomes, workflow integration and costeffectiveness require further study.</p> (10.1038/s41598-026-44543-z)
  DOI : 10.1038/s41598-026-44543-z
• Microarchitectural Espionage: FPGA-Based Security Analysis of Branch Prediction in RISC-V Out-of-Order Cores
  
  • Khan Mahreen
  • Bin Mohd Shahfie Muhammad Emir
  • Mushtaq Maria
  • Pacalet Renaud
  • Apvrille Ludovic
  , 2026, pp.1-7. <div><p>Modern processor microarchitectural optimizations, while enhancing performance, inadvertently introduce side channels that can leak sensitive information through timing variations. This paper presents an FPGA-based security testbed for studying branch predictor side-channel vulnerabilities in open-source RISC-V out-of-order cores. We demonstrate a configurable platform built on the Berkeley Out-of-Order Machine (BOOM) core, adapted for resource-constrained FPGA deployment with customizable branch predictor configurations. Through baremetal execution and cycle-accurate timing measurements, we implement and evaluate three classes of timing attacks: Conditional Branch Prediction Attacks (CBPA), Indirect Branch Prediction Attacks (IBPA), and a practical smart-lock application attack. Our results show that simplified one-level predictors exhibit deterministic timing separations of 9 to 17 cycles, enabling perfect secret recovery with 100% accuracy for 16-bit secrets within 500 measurement rounds. We further demonstrate practical attack scenarios, including the extraction of a randomly-generated 4-digit smart-lock code, and evaluate the impact of branch predictor complexity on attack feasibility. This work provides an open-source framework for reproducible microarchitectural security research on RISC-V platforms, enabling evaluation of both attacks and countermeasures.</p></div> (10.1109/ISDFS69419.2026.11459082)
  DOI : 10.1109/ISDFS69419.2026.11459082
• Analytical solution of radiative transfer equation of light radiance in turbid slab with inner-medium source under P3-1D approximation
  
  • Fade Julien
  • Roux Aurélien
  • Breton Vicente Alberto
  • Sorrente Béatrice
  • Grillot Frederic
  • Silva Anabela Da
  , 2026. A generalized model of the 1-dimensional radiative transfer equation of the light radiance in a turbid slad is detailed, under the P-3 approximation, including the possibility to model a continuous plane-wave source located at any depth within the scattering slab. This analytical model, which requires significant evolution of the P3-1D model is extensively described and validated by comparison with Monte-Carlo numerical experiments. A series of numerical simulations illustrates some of the modelling possibilities offered by this extended model, which makes it possible to continuously model the transition between a classical slab geometry and a semi-infinite geometry.
• This is not a speculation, this is the reality: Reflection on Speculative Design Workshop in HCI &amp; Design Research
  
  • Huron Samuel
  • Wei Wei
  • Tseng Wen-Jie
  • Bonnail Elise
  • Genest Eleonore
  , 2026. In this paper, we reflect on the qualities of our methods across three speculative design workshops that we designed, ran, and analyzed as part of distinct Human-Computer Interaction research projects. These workshops were conducted over the past four years and each yielded to a research publication on a different topics: visualization, virtual reality, and extended reality. Each workshop employed a different speculative framing that we define in the paper: functional, critical, and exploratory. We summarize the motivations, the process of applying speculative methods, and the outcomes of the speculation. Finally, we reflect on five qualities for speculative design research: speculative plausibility, grounding of speculation, common framing of speculation, synthesis within a framework, and the quality of reflection.
• Artifact: PSMark: a distributed IoT benchmark for publish/subscribe under domain-based workloads
  
  • Badolato Christian
  • Samson Nathan
  • Hajj Hassan Houssam
  • Huang Chih-Kai
  • Bouloukakis Georgios
  • Pappachan Primal
  • Yus Roberto
  , 2026. This artifact paper presents a guide for PSMark, a distributed benchmarking framework to evaluate Publish/Subscribe (pub/sub) systems against real-world representative IoT workloads. PSMark addresses limitations in existing pub/sub benchmarks by supporting: (i) heterogeneous device behaviors (e.g, varying payload sizes, publication rates, and connection stability); (ii) distributed multi-node deployments; and (iii) cross-protocol evaluation across MQTT and DDS.
• Anomaly Detection in Non-stationary Time Series
  
  • Emelchenkov Anton
  , 2026. Anomaly detection is critical for ensuring the reliability of industrial systems, yet remains particularly challenging for complex mechanical assemblies such as electric powertrains due to their non-stationary and multi-component dynamics. This thesis presents two complementary pipelines applied to anomaly detection in electric powertrains, combining interpretable signal-level modelling with data-driven temporal analysis.The first pipeline builds on a non-linear chirp signal model to accurately track multiple time-varying amplitudes at predefined frequencies, enabling reliable and interpretable monitoring of individual mechanical components. We introduce novel amplitude-tracking methods and demonstrate their robustness through extensive numerical experiments and rigorous statistical validation.The second pipeline adopts a holistic view of vibrational signals and leverages deep learning architectures to capture complex temporal dependencies that are difficult to isolate using amplitude-based tracking alone. Within this framework, we propose ALERT, a novel anomaly detection method for non-stationary time series based on a linear autoregressive latent space.To enable systematic development and evaluation, we introduce a comprehensive experimental testbench, first large-scale dataset of non-stationary vibrational signals with synchronized rotational speed measurements, further enriched with diverse expert-guided degradation scenarios derived from real-world operating conditions.Together, these contributions advance the state of the art toward deployable, real-time anomaly detection systems for long-horizon monitoring in complex industrial environments.
• PSMark: a distributed IoT benchmark for publish/subscribe under domain-based workloads
  
  • Badolato Christian
  • Samson Nathan
  • Hajj Hassan Houssam
  • Huang Chih-Kai
  • Bouloukakis Georgios
  • Pappachan Primal
  • Yus Roberto
  , 2026. The Publish/Subscribe (pub/sub) paradigm is widely used in the Internet of Things (IoT). Standalone sensors, wearables, and other devices act as producers that publish messages to consumers such as edge servers or even other IoT devices. Selecting and configuring a pub/sub protocol for an IoT system requires considering network requirements, device reliability, and required Quality-of-Service guarantees. Pub/sub benchmarking suites can help compare expected behavior of various protocols, implementations, and network configurations. However, current pub/sub benchmarks focus primarily on stress testing systems assuming mostly static configurations of homogeneous publishers which are not representative of real-world IoT deployments. To address this, we present PSMark, a distributed, multi-protocol benchmark for evaluating topic-filtered pub/sub systems under workloads representative of real-world IoT environments. PS-Mark supports (i) workloads representative of heterogeneous IoT device deployments including variations in device communication parameters, (ii) evaluation of distributed IoT deployments with multiple data aggregation servers, (iii) cross-protocol measurements across MQTT and DDS, with extensibility to additional protocols, and (iv) a modular design for adding additional metrics and interfaces. We further construct twelve IoT-focused workloads derived from seven real-world datasets in the domains of manufacturing, healthcare, smart homes, and smart cities. Finally, we benchmark five popular MQTT brokers and one DDS implementation using PSMark and analyze their performance across multiple testbeds and Quality-of-Service settings.
• Readability as a multi-measure construct in data visualization
  
  • Cabouat Anne-Flore
  • Huron Samuel
  • Isenberg Tobias
  • Isenberg Petra
  , 2026, pp.1-5. In this paper, we argue that readability cannot be meaningfully discussed without considering multiple complementary measures, and that relying on a single measure constitutes an epistemological choice that constrains the conclusions that can be drawn.
• Frequency-Domain Characterization of Deployed Fiber-Medium Coupling using DAS
  
  • Pruvost Pierre
  • Awwad Élie
  • Huang Heming
  • Jaouën Yves
  , 2026, pp.Th2A.59. An optical cable is monitored using a DAS interrogator and an accelerometer. Frequency-domain analysis shows that, despite notable differences beyond 100Hz, DAS still provides valuable information on the media surrounding the cable.
• Distributed Fiber Sensing Over Deployed Networks: Opportunities and Challenges
  
  • Awwad Élie
  • Prato Diane
  • Pruvost Pierre
  • Freire-Hermelo Maria
  • Gabet Renaud
  • Jaouën Yves
  , 2025. We review opportunities and challenges of deploying Rayleigh-based distributed sensing over existing networks. Focusing on deployment possibilities, sensitivity, phase noise, and large-scale data analysis, we highlight recent advances and future directions. (10.1364/OFC.2026.W4D.1)
  DOI : 10.1364/OFC.2026.W4D.1
• Frequency-Domain Characterization of Deployed Fiber-Medium Coupling using DAS
  
  • Pruvost Pierre
  • Awwad Élie
  • Huang Heming
  • Jaouën Yves
  , 2026, pp.Th2A.59. An optical cable is monitored using a DAS interrogator and an accelerometer. Frequency-domain analysis shows that, despite notable differences beyond 100Hz, DAS still provides valuable information on the media surrounding the cable.
• Integrating musicological knowledge in positional encoding for applications to music generation
  
  • Agarwal Manvi
  , 2026. Attention-based Transformer generative models can produce high-quality, realistic samples.For effective performance, they require two resources: substantial compute budgets and large-scale datasets. The first requirement raises broader questions about, for instance, skewed socio-economic resource allocation and detrimental environmental impact.The second requirement is blocked by the low resource nature of the domain of symbolic music.These factors present an interesting scientific challenge : how can we maintain superior performance on generative symbolic music tasks with limited compute and data? In this thesis, we address this question through empirical and theoretical approachesfocused on a specific component of the Transformer architecture : positional encoding (PE).We explore how the design of positional encoding can be improved to meet the twin challenges of low data and low compute through the introduction of musically-relevant prior knowledge. At an empirical level, we infuse positional encoding with musical structureinformation, exposing the model to appropriate inductive biases through Structure-Informed PositionalEncoding. We introduce Fast, Structure-Informed Positional Encoding (F-StrIPE) by melding together musical structure information with an existing linearcomplexity relative positional encoding method called Stochastic Positional Encoding (SPE). At a theoreticallevel, we show not only that SPE is deeply connected to well-known kernel approximation methods, but also that linearized relative PEs such as SPE and FStrIPE can be understood through a canonical form of PE-enriched attention. We further show that otherwidely-used efficient PE methods from the literature, such as Rotary Positional Encoding (RoPE), also fit within our framework, enabling us to reveal computational principles shared by different efficient PEs. This also allows us to propose a novel efficient positionalencoding method called RoPEPool. Finally, we use our canonical form to provide insights on why well designed priors help empirical performance. Finally, we show that our ideas on structure-informed positional encoding are also applicable to tokenized audio.We introduce a new resource, the Audio909 dataset, through which we show that musically-informed priors benefit performance on music generation.