Publications

2026

• Of All StrIPEs: Investigating Structure-informed Positional Encoding for Efficient Music Generation
  
  • Agarwal Manvi
  • Wang Changhong
  • Richard Gaël
  IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2026, 34, pp.1388-1400. While music remains a challenging domain for generative models like Transformers, a two-pronged approach has recently proved successful: inserting musically-relevant structural information into the positional encoding (PE) module and using kernel approximation techniques based on Random Fourier Features (RFF) to lower the computational cost from quadratic to linear. Yet, it is not clear how such RFF-based efficient PEs compare with those based on rotation matrices, such as Rotary Positional Encoding (RoPE). In this paper, we present a unified framework based on kernel methods to analyze both families of efficient PEs. We use this framework to develop a novel PE method called RoPEPool, capable of extracting causal relationships from temporal sequences. Using RFF-based PEs and rotation-based PEs, we demonstrate how seemingly disparate PEs can be jointly studied by considering the interactions they induce between two descriptive levels of the data: the input, capturing quickly-varying components, and the prior, capturing slowly-varying components. For empirical validation, we use a symbolic music generation task, namely, melody harmonization. We show that RoPEPool, combined with highly-informative structural priors, outperforms all methods. (10.1109/TASLPRO.2026.3662483)
  DOI : 10.1109/TASLPRO.2026.3662483
• Distilling Learned Image Compression Models: An Analytical Approach for Low-Latency FPGA Deployment
  
  • Mazouz Alaa Eddine
  • Chaudhuri Sumanta
  • Cagnazzo Marco
  • Mitrea Mihai
  • Tartaglione Enzo
  • Zatt Bruno
  • Fiandrotti Attilio
  IEEE Transactions on Multimedia, Institute of Electrical and Electronics Engineers, 2026. <div><p>Learned Image Compression (LIC) models now rival traditional video codecs in rate-distortion (RD) efficiency, spurring interest in hardware-friendly deployments. However, most existing implementations take an LIC model and fit it to a specific hardware platform through time-consuming, lowlevel hardware optimizations. Moreover, these methods are not designed to meet a pre-established target latency, leading to suboptimal complexity-efficiency-latency trade-offs. We propose a paradigm for distilling a student LIC model under a target latency constraint, avoiding the need for low-level hardware redesign. First, we establish an analytical relationship between the number of convolutional channels of a LIC model and its latency. Second, we introduce a framework to distill a large LIC model into a latency-bound student. Finally, we design a pipelined FPGA architecture that employs mixed-precision quantization, parallel processing, and optimized resource allocation for maximum efficiency. RD efficiency is preserved thanks to a hardwarefriendly GDN/iGDN module end-to-end integrated within our LIC pipeline. Experiments on a ZCU102 FPGA show that our approach achieves competitive RD efficiency with explicit latency control, reaching up to 60 fps for HD content while consuming less than 2.14 J/frame.</p></div>
• Rate of convergence of the conditioned random walk towards the Brownian bridge
  
  • Decreusefond Laurent
  • Jacquet Antonin
  , 2026. <div><p>We study the rate of convergence of two discrete processes towards the Brownian bridge: the random walk conditioned to be zero at time 2n and the empirical process which appears in the Glivencko-Cantelli theorem. Combining a functional Stein method with a Radon-Nikodym representation of the bridge, we bound the Fortet-Mourier distance between these conditioned processes and the Brownian bridge.</p></div>
• Statistically Robust Resource Block Allocation for Satellite Communications
  
  • Manapragada Chaitanya
  • Decreusefond Laurent
  • Martins Philippe
  , 2026. It is critical to dimension (accurately estimate capacity of) a satellite system prior to deployment, as it is very expensive to reconfigure launched satellite systems that fail to meet demand or that waste capacity. The fundamental requirement is a dimensioning rule for resource blocks (RBs) given a satellite footprint and a target overload probability (target Quality-of-Service). The rule must be robust to the spatial covariance structure of signal attenuation, which is generally unknown both at the time of pre-deployment dimensioning and afterwards. Existing approaches address parts of this problem, but there does not yet exist a footprint-level RB dimensioning rule for the satellite context. We develop such a rule: starting with a Gaussian attenuation field that induces a covariance structure inspired by classical work on spatial covariance of attenuation, we sample users at random along with their field-based attenuation values, and estimate aggregate RB demand for a target overload probability. We do this in two complementary ways: a Monte Carlo route that gives a simulation-derived RB budget for a given target overload probability, and a concentration route that gives a conservative analytic upper bound on the target overload probability for a given RB budget (such as the one obtained through simulation). Taken together, these complementary approaches give a principled way to dimension RBs for a satellite footprint under spatially correlated attenuation.
• Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures
  
  • Laval Julien
  • Guiavarch Robin
  • Dufournet Antoine Joachim
  • Menasria Racim
  • Drabczuk Barthélémy
  • Mendoza Cristobal
  • Tounsi Saeb
  • Baroud Chikh Abdelghani
  • Bourenane Merieme
  • Troiani Vanessa
  • Snyder William
  • Patti Marisa
  • Mylene Moyal
  • Plaze Marion
  • Cachia Arnaud
  • Santacroce Federica
  • Committeri Giorgia
  • Cury Claire
  • de Matos Kevin
  • Colliot Olivier
  • Sun Zhong Yi
  • Fischer Clara
  • Frouin Vincent
  • Gori Pietro
  • Rivière Denis
  • Chavas Joël
  • Mangin Jean-Francois
  , 2026. The human brain folds in utero, primarily during late gestation. Shortly after birth, cortical folding patterns are established and remain stable thereafter, making them promising early neurodevelopmental markers. Yet it is unclear whether the representations given by current neuroimaging foundation models capture cortical folding variability. Here, we introduce Champollion, a self-supervised learning framework that learns interpretable local representations of cortical folding from structural MRI. Optimized on representative folding-related tasks, Champollion accurately captures known folding patterns across cortical regions and external datasets. In a comprehensive benchmark, it consistently outperforms neuroimaging and general-purpose foundation models. Furthermore, Champollion reveals richer genetic associations than conventional morphometric descriptors and identifies localized folding signatures associated with incomplete hippocampal inversion, prematurity, and maternal smoking. These results establish cortical folding as a rich and largely untapped source of neurodevelopmental information, and Champollion provides a unified framework for discovering, localizing and interpreting long lasting cortical folding signatures. (10.5281/zenodo.22229006)
  DOI : 10.5281/zenodo.22229006
• UNSUPERVISED DOMAIN ADAPTATION WITH TARGET-ONLY MARGIN DISPARITY DISCREPANCY
  
  • Miralles Gauthier
  • Le Folgoc Loic
  • Jugnon Vincent
  • Gori Pietro
  , 2026. <div><p>In interventional radiology, Cone-Beam Computed Tomography (CBCT) is a helpful imaging modality that provides guidance to practicians during minimally invasive procedures. CBCT differs from traditional Computed Tomography (CT) due to its limited reconstructed field of view, specific artefacts, and the intra-arterial administration of contrast medium. While CT benefits from abundant publicly available annotated datasets, interventional CBCT data remain scarce and largely unannotated, with existing datasets focused primarily on radiotherapy applications. To address this limitation, we leverage a proprietary collection of unannotated interventional CBCT scans in conjunction with annotated CT data, employing domain adaptation techniques to bridge the modality gap and enhance liver segmentation performance on CBCT. We propose a novel unsupervised domain adaptation (UDA) framework based on the formalism of Margin Disparity Discrepancy (MDD), which improves target domain performance through a reformulation of the original MDD optimization framework. Experimental results on CT and CBCT datasets for liver segmentation demonstrate that our method achieves state-of-the-art performance in UDA, as well as in the few-shot setting.</p></div>
• Self-supervised interferogram restoration by regularized inversion of despeckled projections
  
  • Gaya Victor
  • Denis Loïc
  • Pinel-Puysségur Béatrice
  • Bultingaire Thomas
  • Tupin Florence
  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, IEEE, 2026. Synthetic Aperture Radar Interferometry (InSAR) gives access to topographical and displacement information. Yet, the estimation of interferometric phase and coherence requires refined image restoration techniques to reduce fluctuations due to spatial and temporal decorrelations. Recently, the generic approach MuChaPro has been proposed to reduce speckle in multi-channel SAR data by reducing, thanks to projections, the restoration problem to a series of single-channel despeckling tasks. In the specific case of interferometric data, this method shows some limits in very low coherence areas. This paper identifies these limitations and proposes to improve MuChaPro estimation by introducing a spatial regularization framework dedicated to interferometric data. Experiments on simulated interferograms and real TerraSAR-X and PAZ data show that the proposed optimization framework significantly improves the quality of the phase and coherence estimations.
• Is Phase Really Needed for Weakly-Supervised Dereverberation ?
  
  • Rodrigues Marius
  • Bahrman Louis
  • Badeau Roland
  • Richard Gaël
  , 2026. In unsupervised or weakly-supervised approaches for speech dereverberation, the target clean (dry) signals are considered to be unknown during training. In that context, evaluating to what extent information can be retrieved from the sole knowledge of reverberant (wet) speech becomes critical. This work investigates the role of the reverberant (wet) phase in the time-frequency domain. Based on Statistical Wave Field Theory, we show that late reverberation perturbs phase components with white, uniformly distributed noise, except at low frequencies. Consequently, the wet phase carries limited useful information and is not essential for weakly supervised dereverberation. To validate this finding, we train dereverberation models under a recent weak supervision framework and demonstrate that performance can be significantly improved by excluding the reverberant phase from the loss function.
• Stein's functional method for weakly dependent random variables
  
  • Coutin Laure
  • Darou Kebe Sérigné
  • Decreusefond Laurent
  , 2026. <div><p>This article extends Stein's functional method to establish explicit rates of convergence in the Wasserstein-1 distance for Donsker's invariance principle under weak dependence. Our approach first reduces the problem of bounding distances between distributions on a function space to estimating distances between finite-dimensional marginals. We then employ the block technique, which is standard in Stein's methodology, to handle dependence. While our analysis focuses on φ-mixing sequences, the method extends to other forms of weak dependence admitting suitable covariance inequalities.</p></div>
• Convergence rate for the coupon collector's problem with Stein's method
  
  • Costacèque Bruno
  • Decreusefond Laurent
  Stochastic Processes and their Applications, Elsevier, 2026, 193, pp.104835. The functional characterization of a measure, an essential but delicate aspect of Stein's method, is shown to be accessible for stable probability distributions on convex cones. This notion encompasses the usual stable distributions \textit{e.g.} Gaussian, Pareto, \textit{etc.} but also the max-stable distributions: Weibull, Gumbel and Fréchet. We use the definition of max-stability to define a Markov process whose invariant measure is the stable measure of interest. In this paper, we focus on the Gumbel distribution and show how this construction can be applied to estimate the rate of convergence in the classical coupon collector's problem. (10.1016/j.spa.2025.104835)
  DOI : 10.1016/j.spa.2025.104835
• Applying Morphological Operations to Subsets of Points for the Discovery of Repeated Musical Patterns and Their Variations
  
  • Lascabettes Paul
  • Quaetaert Nils
  • Daniel Mathys
  • Andreatta Moreno
  • Bloch Isabelle
  Journal of Mathematical Imaging and Vision, Springer Verlag, 2026. This article deals with the discovery of repeated patterns and their variations in a discrete representation of musical data. This task consists in identifying repetitions within a set of points in R2 , where each point represents a musical note whose coordinates are its onset and its pitch value. A common approach is to compute all the possible translations between points in order to discover repeated musical patterns. In this paper, we propose to start from specific subsets of points and to complete them by using morphological operations to form repeated patterns. Moreover, these operations can be extended to discover pattern variations given a particular approximation. This method not only reveals certain variations of the given subset of points, but also adds specific points to it despite the fact that they were not initially present. We apply our approach to the collection of 24 fugues from the first book of Bach's Well-Tempered Clavier. In this particular case, we consider the first m points as the subset to be completed by the morphological operators. We demonstrate that specific values of m enable the discovery of the subject and its occurrences, whereas the smallest values identify truncated versions of it. We compare our approach with previous work on the analysis of Bach's fugues and illustrate the results for different values of m with graphical representations including both exact and approximate repetitions. (10.1007/s10851-026-01301-0)
  DOI : 10.1007/s10851-026-01301-0
• THE INTERNET ARCHIVE MUSIC DATASET
  
  • Stamatiadis Paraskevas
  • Miranda Bernardo V
  • Berger Clémentine
  • Richard Gaël
  • Fontaine Mathieu
  • Essid Slim
  , 2026. <div><p>We introduce the Internet Archive Music Dataset (IAMD), a large-scale collection of captioned music segments derived from the Internet Archive. To the best of our knowledge, IAMD constitutes the largest publicly available music-caption dataset to date with over 34,000 hours of audio, providing a valuable benchmark for training and evaluating music understanding and generative models. The dataset is built from content declared to be distributed under Creative Commons licenses, and cross-referencing with MusicBrainz is done to improve license information reliability. To annotate IAMD, we present an automatic captioning pipeline that augments base captions produced by an audio-language model (ALM) with textual metadata sourced from the Internet Archive and imputed metadata obtained using audio classification models. Caption quality is assessed objectively and subjectively, and results indicate that the annotation pipeline is reliable and does not degrade caption quality with scaling.</p></div>
• Rust Coreutils: Rebuilding Unix Foundations in a Modern Language
  
  • Ledru Sylvestre
  • Tardieu Samuel
  • Zacchiroli Stefano
  IEEE Software, Institute of Electrical and Electronics Engineers, 2026. GNU core utilities (coreutils) is a crucial package in modern UNIX systems. It comprises around 100 fundamental commands-like ls, cp, and cat-which run every day on millions of computers. However, GNU coreutils is also legacy software, with its C codebase dating back to the early 1990s and arguably feature-complete. If one were to consider reimplementing this essential package, how would they do so effectively, and why? This paper recounts the development of Rust coreutils, a contemporary open source reimplementation of GNU coreutils in the Rust programming language, which has reached the status of a drop-in replacement for GNU coreutils, compatible with most Linux distributions. By comparing Rust coreutils with its ancestor, we offer insights into creating a reliable substitute for critical software and highlight how modern programming features can attract development interest in legacy packages. (10.1109/MS.2026.3733266)
  DOI : 10.1109/MS.2026.3733266
• Real-World Assessment of RF-EMF Exposure From 3G, 4G, and 5G Mobile Networks Across Different Urbanization Levels
  
  • Lee Ae-Kyoung
  • Jeon Sangbong
  • Hong Seon-Eui
  • Wang Shanshan
  • Wiart Joe
  • Samaras Theodoros
  • Moon Jung Ick
  IEEE Access, IEEE, 2026, pp.1-1. (10.1109/ACCESS.2026.3728447)
  DOI : 10.1109/ACCESS.2026.3728447