Papers

This paper studies the secrecy capacity of a class of degraded broadcast channels in the presence of an external eavesdropper, where a transmitter aims to deliver two independent confidential messages to two legitimate receivers. The transmitter is assumed to have non-causal access to the channel state information (CSI), and each legitimate receiver possesses prior knowledge of the other receiver's message, referred to as receiver message side information (RMSI). We consider two distinct scenarios: complementary RMSI, where each receiver knows only the other's message, and non-complementary RMSI, where the side information does not perfectly align. For both scenarios, we derive novel inner bounds on the achievable secrecy rate region and present tight outer bounds, establishing the secrecy capacity region for the considered degraded channel settings. Unlike prior works, which primarily address general broadcast settings without secrecy constraints or omit key interactions between RMSI and CSI, our results provide a complete characterization of the secure communication limits under these conditions. Moreover, we extend our analysis to the Gaussian degraded broadcast channel, highlighting the pivotal role of CSI in enhancing secure transmission performance. Our findings demonstrate that the combination of RMSI and CSI can be strategically leveraged to expand the secrecy capacity region, thus offering new insights into secure multiuser communication system design.

This paper presents a dual-algebraic framework for control barrier functions (CBFs) that guarantees deterministic execution using exclusively elementary arithmetic. We develop this deterministic approach to solve a fundamental bottleneck in safety-critical control: pointwise minima compose intersecting safe sets, but generate non-smooth boundaries where standard Lie derivatives fail. Existing mathematical workarounds inject approximation bias, probabilistic non-determinism, or combinatorial execution delays that impede hard real-time hardware certification. By embedding the system state and vector field into the dual-number ring, our method extracts both the composite barrier value and its exact directional derivative in a single evaluation. The standard floating-point minimum deterministically isolates a single vertex of the Clarke generalized gradient for the quadratic-program solver. We prove this selected vertex constitutes a Clarke subgradient and the resulting simultaneous-enforcement safety filter guarantees forward invariance. The arithmetic overhead remains a fixed constant factor, independent of state dimension and constraint count. We extend this framework to finite $\min$/$\max$ Boolean compositions, for which enforcement of the routed constraint of each $\delta$-active clause guarantees forward invariance, and to systems of higher relative degree, for which a bivariate truncated-dual evaluation extracts the control coupling without symbolic differentiation. Three numerical examples illustrate the computational scaling.

Radio maps, which characterize the spatial distribution of radio frequency metrics, such as the received signal strength, are essential for a wide range of wireless applications. The problem of radio map estimation involves constructing a radio map from a limited set of radio samples measured by sparsely distributed sensors.Recently, diffusion models have been increasingly adopted for this problem, yet their theoretical performance remains largely unexamined. Consequently, it is difficult to evaluate their performance when ground-truth radio maps are unavailable, as is often the case in practice. To bridge this gap, we first formulate radio map estimation as a non-linear matrix completion problem. We then derive a theoretical expression for the estimation error of a diffusion model, capturing the effects of the mismatch between the training and deployment environments, the model design, and the sampling strategy on the quality of the estimated radio map. Moreover, considering that the derived error expression depends on certain information that is difficult to obtain in practice, we propose an empirical approximation that is readily computable from observable data. Finally, extensive simulations demonstrate that the empirical formula closely approximates the theoretical error expression, validating its effectiveness for practical deployment. Our results provide guidelines not only for evaluating the performance of a diffusion model when ground truth is unavailable, but also for determining how many sensors are required to spatially sample the region to achieve a given estimation accuracy. They further reveal a critical sensor count beyond which the estimation performance of diffusion models converges.

Machine learning (ML) techniques have been commonly adopted to identify the dynamics of building energy systems (BESs), owing to their flexibility relative to first-principles, physics-based modeling approaches. Beyond the choice of ML architecture, the quality of the training data plays an essential role in the resulting model performance. Optimal experimental design (OED), realized in this work through active learning (AL), determines which experiments to conduct in order to collect informative data, rather than relying on standard approaches such as uniformly random sampling. This paper proposes a systematic comparison of OED via AL for building energy system identification, with a particular focus on HVAC thermal dynamics. We investigate fourteen AL techniques across two ML model classes, namely a deterministic feedforward neural network and a stochastic Gaussian process, and classify these techniques into four categories: data space, uncertainty, information gain, and model change. To examine the AL algorithms under realistic conditions, we implement and evaluate them on the high-fidelity building simulator BOPTEST. The results, reported as the root mean square error across multiple test scenarios with varying initial dataset sizes and control input constraints, show that AL-based models generally outperform models trained via passive learning (PL) with uniformly random control inputs, achieving error reductions of up to 54%, although the magnitude and consistency of this improvement vary across acquisition functions and operating regimes.

The growth of artificial-intelligence workloads is increasing the electrical and thermal demands on data-center power-delivery systems, making conversion efficiency, power density, and reliability critical design priorities. This review examines how gallium-nitride (GaN) power devices can be matched to specific stages of the grid-to-load conversion chain, including power-factor correction, isolated DC/DC conversion, 48-V intermediate-bus conversion, and point-of-load regulation. Si, SiC, and GaN are compared using converter-relevant metrics, and lateral, vertical, and specialized GaN architectures are evaluated in terms of voltage scalability, switching behavior, reverse conduction, thermal pathways, gate control, and technology maturity. The analysis shows that GaN provides a stage-dependent rather than universal advantage. Commercial lateral GaN HEMTs are particularly effective in high-frequency, low-to-mid-voltage stages, while specialized and hybrid devices support bidirectional operation, normally-off control, extreme conversion ratios, and integration. Vertical GaN remains an emerging option for higher-voltage and higher-power conversion. A quantitative framework links cascaded converter efficiency to electrical-loss reduction, cooling demand, annual facility energy use, and operational carbon emissions. Broad deployment further requires low-parasitic packaging, disciplined gate-drive and EMI co-design, mission-profile reliability qualification, scalable manufacturing, and supply-chain resilience. GaN is therefore best treated as a stage-specific system lever whose value depends on coordinated device, topology, package, and thermal co-design.

Maternal-fetal US is the primary imaging modality for monitoring fetal development, yet accurate automated segmentation remains challenging due to the scarcity of pixel-level annotations. To address this issue, we propose DACL, a semi-supervised framework for robust fetal US image segmentation. DACL jointly trains a deployment-oriented lightweight convolutional network (1.47\thinsp\mathrm{M} parameters) and a Transformer-based network, leveraging labeled data for supervised learning and unlabeled data via CPS. To enhance prediction stability, we introduce a dual-agreement consistency loss that couples pixel-wise probabilistic divergence with entropy-guided confidence alignment. Unlike conventional CPS methods that enforce agreement only at the prediction level, DACL explicitly regularizes both distributional alignment and uncertainty, thereby suppressing unreliable pseudo-labels and enabling stable cross-architecture pseudo-label learning under extreme annotation scarcity. Furthermore, an interpolation-based consistency strategy using mixup is applied to unlabeled samples to enhance robustness. Under 5% labeled data, DACL improves Dice by up to 2.77% and reduces HD95 by up to 14.69 mm compared with the strongest recent semi-supervised methods, demonstrating significant improvements in boundary accuracy on both fetal head and abdomen datasets. These results demonstrate the effectiveness of agreement-based consistency learning for annotation-efficient fetal US segmentation. Our code is on GitHub.

Inverse design of nanophotonic structures is challenging due to the large design space, nonlinear structure-response relationships, and the high computational cost of iterative electromagnetic simulations. Existing deep-learning approaches typically rely on large precomputed datasets or libraries of optimized structures, which limits scalability to continuous and complex inverse-design tasks. We introduce a Dimension Expansion Network (DEN), a fully unsupervised, simulation-efficient framework for nanophotonic inverse design. DEN addresses the mismatch between low-dimensional design objectives and high-dimensional nanophotonic structures by transforming compact target parameters into structured, high-dimensional conditioning representations before inverse design. This improves target expressivity and conditioning quality for structure generation. The model is trained end-to-end using differentiable electromagnetic simulations, removing the need for any pre-generated dataset. We validate DEN on free-form metalens and asymmetric Y-splitter design problems. For metalens design, DEN achieves focal intensities comparable to adjoint-based optimization while reducing simulation cost by approximately 50% and generalizing across tens to thousands of focal targets within a shared focal region. For Y-splitter design, DEN accurately produces arbitrary power-splitting ratios using only 21 training targets and demonstrates robust broadband performance. Ablation studies and representation analyses show that dimension expansion enhances sensitivity to target variations, increases structural diversity, and reduces mode-collapse-like behavior. Overall, DEN provides a scalable conditioning strategy for inverse design with low-dimensional objectives, enabling efficient photonic design across large continuous target spaces.

Early identification of speech sound errors in children is often limited by access to specialists, motivating lightweight screening tools that can operate outside the clinic. We present a screening pipeline for Polish-speaking children focused on sibilant substitutions, coupling a wav2vec2-based CTC token recognizer with alignment-based error typing and a template-grounded caregiver assistant for screening, not diagnosis. On a held-out test set of 10 unseen children comprising 559 utterances, the recognizer achieves 88.7 percent exact sequence match. As a conservative screening proxy, we flag a mismatch when the system emits substitution-evidence bracketed tokens at the target segment, yielding 72.9 percent precision, 61.4 percent recall, F1 = 0.67, and a 2.7 percent false-alarm rate on target-correct items. We describe the assistant's safety boundaries and outline a clinician-in-the-loop validation plan for future deployment.

Field-scale retrieval of surface soil moisture (SM), leaf area index (LAI), and plant height (PH) is essential for precision agriculture, yet it remains an ill-posed inverse problem. Concurrent variations in soil moisture and canopy density generate substantial ambiguities in radar backscatter and spectral responses, which reduces the effectiveness of traditional feedforward regression models in heterogeneous smallholder cropping systems. This study presents the Iterative Energy-Based Transformer (iEBT) for the joint retrieval of coupled soil-canopy states from Sentinel-1 C-band SAR and Sentinel-2 multispectral time series. Instead of direct regression, iEBT embeds multi-modal predictors within a shared sequence, produces an initial state estimate, and iteratively updates the target [SM, LAI, PH] vector through normalized gradient descent to minimize a learned scalar compatibility energy function. Using 700 quality-controlled field measurements from Varanasi, India, iEBT achieved the highest learned-model performance on the random test split, with a four-seed mean R^2 of 0.854 \pm 0.012 (R_SM^2 = 0.841, R_LAI^2 = 0.905, R_PH^2 = 0.821). WCM and PROSAIL were retained as physically interpretable SAR and optical reference models for comparison. Modality ablations confirmed that Sentinel-1 drives SM retrieval, while Sentinel-2 dominates LAI, whereas PH relies on combined structural-phenological signatures. Crucially, the model's terminal energy functions as an uncalibrated post-retrieval quality diagnostic; screening the 10% highest-energy samples markedly reduced target level root-mean-square errors. While leave-one-campaign-out validation highlights persistent cross-season domain shift challenges due to localized management variations, compatibility-guided multimodal fusion offers a structured self-diagnostic path toward reliable biophysical parameter estimation

Agentic AI offers significant potential to automate complex building-engineering workflows. However, most existing applications remain isolated proof-of-concept demonstrations and lack reusable domain capabilities, human-verified evaluation cases, and standardized benchmarking infrastructure. This study presents Buildrix, an open, community-driven platform for developing, sharing, executing, and evaluating agentic AI skills for building engineering. Buildrix integrates three components: a Python command-line package for developing, validating, publishing, installing, and managing skills and test cases; a web-based Hub for organizing open challenges, reusable skills, test cases, reviews, and benchmark results; and a local agent harness that supports skill discovery, external toolchain provisioning, progressive context loading, and multi-step workflow execution. Buildrix skills are organized as standardized, self-contained packages containing task instructions, executable scripts, dependencies, and supporting resources. Quantitative test cases can be verified by domain experts and promoted to golden test cases for reproducible benchmark evaluation. Buildrix provides an open foundation for reusable capability development, transparent evaluation, and community-driven advancement of agentic AI in building engineering.

Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity. However, such metrics, including the widely used FID, focus on visual fidelity without reflecting downstream utility, and can diverge from human perception under perturbations that are imperceptible to human observers. In this work, we systematically evaluate Earth observation datasets alongside synthetic counterparts generated by deep generative models, comparing automatic metrics against human perception and downstream tasks. Our results reveal a stark misalignment: semantics-preserving perturbations such as rotation drastically alter metric scores while leaving human recognition unaffected, and synthetic samples that score poorly on automatic metrics achieve comparable or higher perceived realism, and can improve downstream performance when combined with real data. By benchmarking semantic segmentation models trained on mixed real-synthetic datasets, we demonstrate that quality metrics rooted in ImageNet-pretrained feature spaces are unreliable indicators for geospatial data. Our findings underscore that automatic quality evaluation of synthetic datasets should be grounded in downstream task performance and human evaluation.

Respiratory acoustic foundation models (FMs) are benchmarked exclusively on smartphone recordings, yet clinical deployment increasingly targets body-coupled (BC) wearables whose sensors attenuate high-frequency content through tissue and bone, leaving FM reliability uncharacterised. We introduce BCoughBench, evaluating five FMs (OPERA-CT/CE/GT, HeAR, M2D+Resp) on nine classification tasks (AUROC, sensitivity at 95% specificity, Expected Calibration Error) and three age regression tasks (MAE vs. a mean-predictor baseline) across five EBEN-simulated BC sensor conditions on five labeled cough datasets. Mean AUROC declines from 0.785 (smartphone) to 0.689-0.723, degrading most under temple vibration pickup ($\Delta$ = -0.096) and least under the soft in-ear ($\Delta$ = -0.062). No FM meets the clinical sensitivity threshold (Se@Sp95 $\geq$ 0.20) on most disease tasks under any BC sensor. Sex classification on the CIDRZ cohort collapses (AUROC 0.954 to 0.596-0.628, $\Delta$ = -0.341) while COVID detection is nearly unaffected ($\Delta$ = -0.004). Age regression is robust, improving under the forehead accelerometer on CoughVID (MAE 9.61 to 8.97 yr); HeAR leads on regression and demographic tasks, M2D+Resp on disease and characteristic tasks. BCoughBench provides a reproducible framework for FM evaluation under wearable conditions.

We introduce Directed Hypergraph Signal Processing (DHGSP), a unified framework that extends graph signal processing to accommodate both higher-order (polyadic) and asymmetric (directional) relationships simultaneously. Using the tensor singular value decomposition (t-SVD) within the t-product algebra, we define a novel adjacency tensor for directed hypergraphs, a topologically faithful shift operator, and a lossless Directed Hypergraph Fourier Transform (t-DHGFT). Experiments on real traffic networks demonstrate that DHGSP outperforms matrix-based (graph and digraph) and undirected tensor-based (hypergraph) baselines in denoising tasks.

We consider wideband channel estimation for extremely large-scale multiple-input multiple-output (XL-MIMO) arrays under hybrid analog-digital compression, in which a uniform linear array (ULA) is observed through far fewer radio-frequency (RF) chains than antennas. At a carrier frequency of 28 GHz with bandwidths reaching several hundred MHz, the standard narrowband polar-domain channel model fails: the near-field Fresnel curvature becomes subcarrier-dependent, and the compressed observation destroys the per-subcarrier spatial covariance structure that narrowband methods exploit. We propose the Wideband Cross-subcarrier Kullback–Leibler (WB-CL-KL) estimator, which jointly estimates angle and range directly from the compressed sample covariance, without full-array reconstruction, by fitting a structured Fresnel covariance model across orthogonal frequency-division multiplexing (OFDM) subcarriers via a cross-subcarrier Kullback–Leibler (KL) divergence criterion. We also derive the wideband compressed-domain Cramér–Rao bound (CRB) – the performance lower bound for this hybrid architecture – from the Slepian–Bangs formula, and decompose its gain over the narrowband bound into a data-diversity component of +27.093 dB and a geometric-diversity component of +0.701 dB, totalling +27.793 dB at B = 400 MHz (Propositions 1 and 2). In the single-path line-of-sight regime, WB-CL-KL attains a range root-mean-square error of 19.8 mm against a 19.9 mm bound at signal-to-noise ratio (SNR) = 10 dB, a ratio of 0.996. Under the 3GPP Urban Micro (UMi) path-loss and shadow-fading SNR distribution, it achieves a bound ratio of 0.959 at the median deployment SNR of 9.6 dB, indicating near-CRB operation at the representative deployment point, where the compressed-domain bound is evaluated at the scene-median geometry.

The rapid expansion of artificial intelligence (AI) infrastructure is driving unprecedented growth in electricity demand from data centers. Traditional power-system planning treats large computing facilities as inflexible peak loads, leading to costly infrastructure upgrades and long delays in grid interconnection. Recent work has shown that AI clusters can reduce electricity consumption during peak demand through software-based workload orchestration. This article explores how modern GPU-based AI data centers can operate as grid-interactive assets that respond dynamically to power system conditions. We describe an architecture integrating grid signals, workload scheduling, and power telemetry for fine-grained cluster power control. Experimental results from a real-world deployment on a 130 kW GPU cluster demonstrate multiple forms of flexibility, including rapid load reduction, sustained curtailment, and carbon-aware operation while preserving service levels for priority jobs. We further demonstrate performance-aware load shifting across geographically distributed clusters, enabling workloads to migrate toward regions with lower grid stress. Together, these capabilities transform AI infrastructure from static electricity consumers into flexible resources that support grid reliability, accelerate interconnection, and improve computing sustainability.

The rapid growth of AI workloads is driving unprecedented increases in data center power demand, current transients, and thermal stress, exposing fundamental limitations in traditional 48 V rack architectures, low-voltage AC distribution, and line-frequency transformer interfaces. This paper reviews the three stages of architectural shifts required to support next-generation AI data centers and identifies three enabling technological building blocks: high-voltage conversion-ratio DC/DC converters, facility-level low-voltage DC distribution, and medium-voltage solid-state transformers. The advantages, technical challenges, and potential solutions associated with each building block are reviewed. Finally, future research directions and open challenges are discussed.

Model Predictive Control (MPC) is widely used in industrial and robotic systems for enforcing constraints and embedding domain knowledge through finite-horizon optimization-based planning. However, despite these strengths, an MPC scheme typically does not yield optimal policies for sequential decision-making problems formulated as Markov Decision Processes (MDPs). Recent combinations of MPC with Reinforcement Learning (RL) alleviate this issue by treating MPC as a parameterized model of the optimal policy of an MDP and adjusting its parameters using data. While these approaches typically consider classical MDPs, many real-world problems include future information–such as forecasts, prices, or reference trajectories–at decision time, which must be included in the MDP state for optimal decision-making. Current MPC-RL approaches do not directly account for this augmented-state structure, raising the question of how to incorporate future information into MPC to obtain an optimal policy. This work establishes the structural requirements under which a parameterized MPC can exactly represent the optimal value functions and policy of an MDP with future information. We further demonstrate that such a parameterized MPC can serve as a structured function approximator, with its parameters learned using RL. The approach is illustrated on a point-mass racing task with future reference information.

The increasing integration of distributed energy resources (DERs) is crucial for power system decarbonization, yet unlocking DERs' flexibility is challenged by their inherent uncertainties and modelling complexity. As traditional optimization methods struggle with such uncertainty and complexity of DERs, reinforcement learning (RL) has emerged as a promising alternative for DER management. However, standard RL methods suffer from sample inefficiency and sub-optimality when trained from scratch. Inspired by the training paradigms in large language models, this paper proposes a Supervised Reinforcement Learning (SRL) framework for learning DER coordination policies. This framework first pre-trains a policy on demonstration data in a supervised-learning fashion, which is then further fine-tuned using RL. Furthermore, we propose a two-step fine-tuning process: offline fine-tuning for enhancing policy performance and online fine-tuning for adapting it to the real-world dynamics. Experiments demonstrate that RL implementations based on the proposed framework significantly outperform all benchmarks, achieving high cost efficiency even under low-quality demonstration data.

Automated classification of acute lymphoblastic leukemia (ALL) from peripheral blood smear images has often reported near-perfect performance on the C-NMC 2019 dataset. We show that such results can be inflated by patient-level data leakage caused by random image-level partitioning, where cells from the same subject may appear in both training and test folds. We establish a leakage-aware benchmark under a strict subject-disjoint protocol, comparing LightGBM, RBF-SVM, EfficientNet-B0, EfficientNet-B1, and ViT-Tiny. Models are developed using three subject-disjoint folds from 73 subjects and evaluated on an external preliminary-phase test set of 1,867 images from 28 unseen subjects with zero patient overlap. Beyond discrimination, we assess calibration using expected calibration error, Brier score, and temperature scaling. Under honest evaluation, EfficientNet-B1 achieves the best performance, with AUROC 0.913, sensitivity 0.87, specificity 0.80, and calibrated ECE 0.024. Frozen-feature classifiers and ViT-Tiny show high sensitivity but poor specificity, indicating a tendency to over-predict the malignant class. A random-versus-subject-disjoint ablation shows that random splitting inflates AUROC by about 0.04 even in the conservative frozen-feature setting. These findings caution against image-level evaluation on C-NMC 2019 and provide a reproducible, calibration-aware benchmark for future work.

Heart disease is among the most common serious conditions in dogs and cats, and a heart murmur heard on auscultation is one of the earliest signs of such disease; such murmurs are often subtle and challenging to detect at early stages. General-practice veterinary examinations catch only a fraction of these murmurs, and definitive cardiac assessment typically requires either a board-certified cardiologist or an in-clinic echocardiogram, which may involve cost and scheduling constraints. We describe Sonus Health, a smartphone-based screening system that analyses an auscultation recording of approximately thirty seconds or longer - captured by a pet owner at home or by a veterinarian or nurse in clinic - and returns a tiered result within moments. The system was evaluated on 322 veterinary-labelled recordings under standard out-of-fold cross-validation. For recordings assigned to the high-confidence tier (30% of cases), accuracy reaches 95.9%, with 94.0% sensitivity and 97.9% specificity. Uncertain cases are prospectively routed to veterinary review rather than assigned an automated classification. Results are stable across standard and group-aware cross-validation, a held-out test split, and multiple random seeds. Beyond murmur detection, the platform also estimates heart rate and heart rate variability, and we position it as a screening, triage, and longitudinal-monitoring layer for companion-animal cardiac care.

Advanced semiconductor nodes drastically increased demand for Transmission Electron Microscopy (TEM), yet destructive sample preparation, slow imaging and high costs severely limit the availability of diverse datasets needed for downstream machine learning (ML). Synthetic data generation is becoming essential, but current generative models often miss TEM-specific noise, structural detail, and stochastic variability crucial for evaluation. We present a Denoising Diffusion Probabilistic Model (DDPM) framework for synthetic TEM image generation under extreme data scarcity. A progressive patch-based training strategy scales from low-resolution patches to full images, enabling from-scratch training with only 15 samples. We integrate a custom TrivialAugment adaptation, cross-process domain transfer, classifier guidance, and RePaint-style inpainting, culminating in full-image generation that preserves global structural and spatial relationships in compliance with FAB metrology requirements. Beyond synthesis, we repurpose DDPM feature representations for segmentation, partitioning encoder feature maps to obtain coherent region masks. Our synthetic images achieve up to MS-SSIM > 0.98 and qualitative expert assessment consistent with structural similarity results, facilitating downstream ML training for defect detection, segmentation, and metrology while preserving statistical and physical realism.

Submerged electric vehicles (SEVs), including autonomous underwater vehicles (AUVs), remotely operated vehicles, and diver propulsion systems, may radiate distinct tonal, harmonic, and modulated acoustic components associated with electric propulsion drives and motor-control electronics. Characterizing these signatures is relevant to passive detection and engineering diagnostics, but remains challenging in coastal environments because ambient noise, shallow-water propagation, and aspect-dependent radiation can obscure vehicle-related features. Existing underwater radiated noise (URN) standards, developed primarily for surface vessels, do not address the spectral, operational, and geometric complexity of SEV measurements. This paper presents an eight-step methodology for SEV URN characterization, covering measurement design, cavitation assessment, frequency-band selection, ambient-noise characterization, spectral and time-frequency analysis, subsystem-oriented interpretation, propagation-corrected source-related estimation, and angular and operational analysis. The novelty lies in integrating calibrated pass-by acoustics with synchronized vehicle metadata, ambient-noise context, and subsystem-oriented analysis to resolve tonal and modulated features that broadband methods cannot capture. The methodology is demonstrated using an A18D AUV measured in coastal water. Drive-related tonal groups were observed near 5.56, 11.1, and 22.2 kHz, with harmonic structure up to 105 kHz. Source-related tonal PSD estimates ranged from 77 to 120 dB re 1 uPa^2/Hz at 1 m

Generative models, particularly diffusion and score-based approaches, have recently achieved strong performance in speech enhancement, but their iterative sampling process limits real-time deployment. Flow Matching offers an efficient alternative by transporting noisy speech toward clean speech through an ordinary differential equation with few function evaluations. In this work, we propose a skip-free encoder-decoder backbone for flow-matching speech enhancement, guided by Latent Representation Alignment (LRA). Instead of relying on U-Net skip connections, which may transfer noise-correlated low-level features to the decoder, the proposed model aligns its bottleneck and decoder representations with clean latent features extracted from a frozen Descript Audio Codec encoder-decoder without quantization. This codec-aligned supervision promotes compact clean-speech representations while preserving efficient few-step inference. Experiments on WSJ0-CHiME3 and VoiceBank-DEMAND show improved PESQ and perceptual quality, especially on VoiceBank-DEMAND, using only five function evaluations.

Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mixed Chinese-Latin-digit names. These forms are frequent in real listening workflows, and a text-to-speech (TTS) system can preserve the written string while changing the spoken meaning. We introduce CN-NewsTTS Bench v0.1, an open target-level benchmark for evaluating whether Chinese news TTS products pronounce such targets correctly from raw text, without user-side rules, LLM rewriting, SSML hints, or manual edits. The release contains a 200-record development set, an 800-record public test set, 992 public auto-evaluable targets, fixed transcripts from a three-ASR ensemble, an automatic target scorer, and initial results for seven product TTS systems. We additionally report ASR-route diagnostics, ASR-subset ablations, category-level results, confidence intervals, and provider configuration metadata. The best system reaches 0.879 strict accuracy, while several systems remain below 0.60.

In assembly line balancing, tasks are assigned to stations in order to satisfy a required cycle time. When production conditions change, the line must be rebalanced by modifying the current task allocation, typically aiming to move as few tasks as possible between stations. Similarity measures are commonly used to control such changes, but they generally evaluate configuration preservation by treating all tasks equally, which may not reflect their different practical importance. In this work, a pruned Mean Similarity Factor is proposed for assembly line rebalancing, evaluating similarity only over a subset of structurally relevant tasks identified through a relevance score. The proposed measure is integrated into a compact mixed-integer linear programming (MILP) formulation that considers practical aspects of manual assembly, specifically workload balance, ergonomic exposure, multi-worker stations, and positional constraints. Computational experiments on extended benchmark instances derived from the literature show that the proposed approach can obtain optimal rebalancing solutions within reasonable computational times, while maintaining high task colocation and balanced workload and ergonomic distributions. In particular, focusing the similarity evaluation on relevant tasks helps reduce the computational effort.

Spatial audio is spreading in applications such as virtual and augmented reality and immersive games. The higher-order ambisonic (HOA) format is particularly useful in this context. Transmitting spatial information requires multiple channels, e.g., 16 channels for 3rd-order ambisonics, resulting in increased memory requirements for storage and higher bitrates for communication. Therefore, efficient compression algorithms are necessary for those contents. The recently standardized IVAS codec allows the coding of HOA content for communication use-cases. Here, we propose to evaluate it in comparison with a basic multi-mono approach across a variety of contents and spatialization methods. Results show that IVAS outperforms the multi-mono approach at the same bitrate. In particular, this codec exploits inter-channel correlation to reduce the bitrate. We point out that it is therefore especially robust for signals with a high interchannel correlation, such as those composed of a limited number of plane waves. Conversely, the multi-mono approach is unable to exploit this correlation and performs poorly on this type of signal.

Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech. However, prior approaches predominantly focus on holistic naturalness, leaving fine-grained paralinguistic distinctions underexplored. We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender. Our experiments show that current LALM judges still lag behind human judgments by 32%p on average and exhibit severe calibration failures, particularly in Tie cases where the correct decision is to abstain. To further analyze lexical versus acoustic reliance, the benchmark includes both same-transcript and cross-transcript conditions. ParaPairAudioBench enables multi-dimensional, calibration-aware assessment of the reliability of LALM-as-a-Judge for paralinguistic speech evaluation.

In this paper, we propose a generalized framework for the design and analysis of suboptimal and reduced-order nonlinear Model Predictive Control (MPC) architectures. The proposed framework manages real-time operation of MPC schemes by (i) computing the control action suboptimally, i.e., by running a generic optimal control algorithm for a finite number of iterations, and (ii) relying on a reduced-order model that neglects part of the plant dynamics (accounting for, e.g., unmodeled dynamics or a low-level compensator). To rigorously handle the interplay between optimization error and model mismatch, we treat the sampling time as a tunable design parameter. We analyze the resulting closed-loop system, comprising the full-order physical plant interconnected with the iterative optimization algorithm (treated as a dynamical system), by leveraging tools from timescale separation. We prove that operating at a sufficiently fast sampling rate ensures that the closed-loop system maintains recursive feasibility and achieves an exponentially stable equilibrium point. The effectiveness of the proposed framework is validated on an underactuated two-link robotic arm through virtual experiments in the high-fidelity MuJoCo physics engine.

Linear Quadratic (LQ) control problems are at the heart of linear control theory and Model Predictive Control (MPC). While performant, standard approaches to solving such problems are inherently serial, limiting real-time scalability despite the parallel computing power available on modern multi-core CPUs. Contributing to addressing this challenge and motivated by “divide and conquer” strategies, we present a parallel-in-time approach that solves computationally demanding conic optimal control problems through the use of the alternating direction method of multipliers (ADMM). In particular, we formulate the inner primal update of ADMM as an LQ problem and split the reformulated problem along the time horizon. This enables us to derive a variant of the Riccati recursion using dynamic programming to solve each subproblem in parallel. Numerical benchmarks on two real-world applications demonstrate as much as a 5x speedup compared to existing related approaches on multi-core CPU hardware.

Recent advances in robotics have enabled robots to operate in shared human environments, emphasizing the importance of effective human robot interaction HRI. Prior studies indicate that anthropomorphism, defined as the incorporation of human like features into robotic systems, facilitates more natural interaction and enhances both task performance and user experience. In robotic arm teleoperation, however, user controlled motions often deviate from human like kinematic characteristics due to intrinsic limitations of teleoperation systems. In this work, we propose a real time framework that generates human like end effector trajectories based on the two thirds power law of voluntary human hand movements, while preserving the operators intended control inputs. The proposed approach is validated through real world experiments conducted on a 6 degree of freedom Dobot CR10 robotic arm. Quantitative analysis demonstrates that the generated trajectories exhibit significantly stronger adherence to human like kinematic profiles compared to conventional teleoperation, with the estimated beta coefficient moving 39.7% closer on average to the theoretical value of 1/3. Furthermore, the method achieves an approximate 34% improvement in motion smoothness, measured by RMS torque rate reduction, with 80% of evaluated motion patterns showing statistically significant improvements while maintaining comparable task completion times.