Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this gap is not a uniform cognitive deficit. Evaluating two architecturally diverse SLLMs, we show speech-to-text (S2T) matches or exceeds text-to-text (T2T) on spatial, syntactic, and factual tasks. Yet on logical tasks requiring entity tracking, S2T accuracy collapses to chance. We diagnose this as an entity binding failure: continuous speech features blur precise entity-property associations during implicit reasoning. To validate this diagnosis, we introduce Entity-Aware Chain-of-Thought (EA-CoT), a lightweight inference-time intervention forcing SLLMs to enumerate entities and bind them to claims before reasoning. EA-CoT bridges the gap, even when spoken names are misrecognized, yielding up to a 24.4 percentage-point accuracy gain. Ablations confirm the gains stem from explicit semantic binding, reframing the gap as an elicitation failure rather than a missing capability.

A unified, closed-form analytical PI/PID tuning method is presented for all-pole plants up to third order that yields a strictly monotonic (zero-overshoot) step response with minimum settling time. The design target is the binomial closed loop p^n/(s+p)^n, which is monotonic with robustness depending only on the order n. Because a fixed PI/PID cannot assign the closed-loop poles and the controller zeros independently, realizing this target exactly requires the controller zeros to be cancelled, which forces the controller numerator to divide the plant denominator. It follows that an exact, real-gained solution exists for any stable plant precisely up to second order with a PI controller and third order with a PID controller; beyond that the residual binomial factor acquires a complex pair of damping sqrt(3)/2, which a generic plant does not contain. Explicit gains are derived for first-order plants (PI), second-order plants with real and complex poles (PI and PID), and third-order plants with three real poles or one real pole plus a complex pair (PID). The freedom of the coincident designs is shown to be bounded: a quadratic nonnegativity condition gives the exact window of the design pole for strict monotonicity, which collapses at the pole-ratio-2 changeover for real poles and is nonempty for damping ratios above approximately 0.443 for complex poles. Monotonicity guarantees Mt = 1, hence Ms <= 2, phase margin >= 60 degrees, and gain margin >= 6 dB, tightening to universal constants for the binomial family. Load-disturbance attenuation obeys IAEd = 1/Ki, making the cost of cancellation explicit, and comparisons with SIMC, the CHR zero-overshoot rule, and deadbeat-fitted explicit formulas quantify the trade: at matched maximum sensitivity the proposed design settles faster than SIMC on the third-order example, with markedly lower controller gains and peak control effort.

As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or alignment limitations, this paper explores the architectural vulnerability of unbounded autonomy - the presumption that an agent should continue operating regardless of rising uncertainty. It introduces a theory of managed autonomy that defines intelligent behavior through the formal capacity to detect epistemic drift, suspend reasoning, attempt recovery, and ultimately surrender control when reliability diminishes. We instantiate this theory via the SMARt (Self-Managing Multi-tier Autonomous Reasoning with Regulated/Revoked transitions) model, a four-layer framework featuring Stable, Meta-cognitive, Assisted, and Regulated states. By developing a timed, guarded Petri net formulation, we establish theoretically bounded properties for the system, demonstrating how architecture can formally mandate escalation, constrain invalid outputs, and ensure governance reachability under specified conditions. We further analyze how incorporating domain-specific trigger sets across varied operational settings (e.g., healthcare, robotics, etc.) can systematically preserve safety, assuming completeness and soundness criteria are met. Because these triggers are designed to be adaptive, the SMARt model accommodates the safe, controlled expansion of an agent's operational scope over time. We conclude that formalizing failure management within the autonomy lifecycle is a crucial step toward realizing reliable and governed artificial intelligence.

Engineered infrastructure systems pose inverse problems in which hidden states, unknown parameters, and subsystem couplings must be inferred from sparse and noisy measurements. These problems are difficult because physical subsystems are heterogeneous, sensing is partial, uncertainty is distributed across subsystem interfaces, and computational cost grows rapidly with system size. We address this challenge with probabilistic compositional inference, a graph-based architecture that represents a coupled system as interacting subsystems, each retaining its own local model, estimator, and uncertainty representation, while coupling is handled through physically meaningful stochastic messages exchanged across subsystem interfaces. This formulation allows mechanistic, learned, and deterministic components to coexist within a single inference framework and propagates calibrated uncertainty without assembling a global augmented state or covariance. We validate the framework in three increasingly demanding settings: a sparse-sensing canonical inverse problem, where interface couplings can also be learned from data; infrastructure-scale power networks, where the method matches centralized joint state-and-parameter inference while reducing computational scaling from approximately cubic to approximately linear; and a multi-physics turbine embedded in a power-grid network, where heterogeneous subsystems compose hierarchically without degrading local inference or collapsing local posteriors into a global estimate. Together, these results show that subsystem structure can be exploited as the organizing principle for uncertainty-aware inverse inference in coupled engineered systems.

Recent advances in spoken dialogue language models have shifted from turn-based to full-duplex designs, where the model continuously listens to the user while generating responses. However, existing duplex backbones still lack a native channel for in-conversation planning and tool calling, leaving real-time agentic behaviour either tied to turn boundaries or relegated to an external cascade. We propose DuplexSLA, a native full-duplex Speech-Language-Action foundation model that decodes assistant audio together with a structured action stream on a shared 160 ms chunk timeline. DuplexSLA is built on a dual-stream three-channel formulation: a continuous user audio channel, a discrete assistant audio channel, and a rate-limited textual action channel, all decoded jointly by a single backbone, so that listening, speaking, planning, and tool calling unfold on one shared clock. Two capabilities define the model: (1) semantic-driven turn-taking control, where interruption, pause, and backchannel are handled inside the same backbone instead of by an external semantic VAD; and (2) in-conversation planning and tool calling, where planning text and structured tool calls are emitted on the action channel without halting assistant audio, so that multi-action and backchannel-triggered tool use are interleaved with ongoing speech. To evaluate these capabilities together, we further construct DuplexSLA-Bench, a duplex benchmark covering pause, interrupt, and backchannel turn-taking together with three styles of in-conversation tool calling. Our project page, interactive demos, and the DuplexSLA-Bench evaluation suite are publicly available at this https URL.

Existing Audio Deepfake Detection (ADD) systems often struggle to generalise effectively due to the significantly degraded audio quality caused by audio codec compression and channel transmission effects in real-world communication scenarios. To address this challenge, we developed a rigorous benchmark to evaluate the performance of the ADD system under such scenarios. We introduced ADD-C, a new test dataset to evaluate the robustness of ADD systems under diverse communication conditions, including different combinations of audio codecs for compression and packet loss rates. Benchmarking three baseline ADD models on the ADD-C dataset demonstrated a significant decline in robustness under such conditions. A novel Data Augmentation (DA) strategy was proposed to improve the robustness of ADD systems. Experimental results demonstrated that the proposed approach significantly enhances the performance of ADD systems on the proposed ADD-C dataset. Our benchmark can assist future efforts towards building practical and robustly generalisable ADD systems.

This paper presents a novel nonlinear backstepping control law for continuous, low-thrust station-keeping in the Earth-Moon system. Quasi-periodic libration point orbits are targeted under a high-fidelity model of the dynamics. Almost global uniform exponential stability guarantees are attained, as shown through Lyapunov's stability theory. Saturation of the actuators is formally included in the controller design, such that these guarantees hold even in the event of saturation. The relationship between saturation threshold, control gains, and deviation is studied and an optimal procedure for gain selection is discussed. The control solution is tested numerically through a Monte Carlo analysis over representative application cases, subject to operational errors, constraints, and external perturbations. Station-keeping under actuation saturation is validated considering a conservative threshold for typical electric propulsion systems.

Robust and generalizable segmentation of brain tumors on multi-parametric magnetic resonance imaging (MRI) remains difficult because tumor types differ widely. The BraTS 2025 Lighthouse Challenge benchmarks segmentation methods on diverse high-quality datasets of adult and pediatric tumors: multi-consortium international pediatric brain tumor segmentation (PED), preoperative meningioma tumor segmentation (MEN), meningioma radiotherapy segmentation (MEN-RT), and segmentation of pre- and post-treatment brain metastases (MET). We present a flexible, modular, and adaptable pipeline that improves segmentation performance by selecting and combining state-of-the-art models and applying tumor- and lesion-specific processing before and after training. Radiomic features extracted from MRI help detect tumor subtype, ensuring a more balanced training. Custom lesion-level performance metrics determine the influence of each model in the ensemble and optimize post-processing that further refines the predictions, enabling the workflow to tailor every step to each case. On the BraTS testing sets, our pipeline achieved performance comparable to top-ranked algorithms across multiple challenges. These findings confirm that custom lesion-aware processing and model selection yield robust segmentations yet without locking the method to a specific network architecture. Our method has the potential for quantitative tumor measurement in clinical practice, supporting diagnosis and prognosis.

Increasing penetration of electric vehicles, heat pumps, and rooftop photovoltaics is creating thermal and voltage stress in low-voltage distribution grids. This work links the German Federal Government energy transition pathway (2025-2045) with state estimation performance requirements, evaluated on two SimBench reference networks across three equipment quality levels (good, medium, poor) and three VDE Forum Netztechnik/Netzbetrieb (VDE FNN) measurement constellations that differ in the availability of transformer and feeder-level instrumentation. Within this work's analysis, congestion is caused exclusively by transformer overloading and voltage-band violations. No individual line exceeds its thermal rating (maximum: 89.5%). Equipment quality governs congestion onset for a given deployment trajectory: under good equipment, congestion remains absent through 2045, under medium equipment it emerges from 2035 (3/6 scenarios), under poor equipment from 2025 (6/6). Without transformer instrumentation, median voltage estimation errors reach 6-42% regardless of smart meter penetration. Adding a single transformer measurement reduces errors by an order of magnitude, achieving median errors of 0.5-1.7%. In urban networks, transformer-level instrumentation meets the VDE FNN voltage accuracy target (99th percentile voltage error below 2%) in all configurations. In rural networks under poor equipment, the target is approached but not met. These findings motivate prioritizing transformer instrumentation as an effective first step for grid observability and supplementing the current consumption-driven metering rollout with risk-based deployment criteria linked to local congestion exposure.

Single-snapshot FDA-MIMO-GPR requires clutter models that account for dispersive-medium uncertainty, yet the statistical link between complex-medium characterization and clutter covariance analysis has remained unclear. This paper develops a propagation-side statistical framework that maps random perturbations of the relaxation spectrum to complex permittivity, complex wavenumber, steering-vector perturbation, medium-induced clutter covariance, and total clutter covariance. Within this framework, the effects of medium uncertainty on effective rank, effective clutter-subspace dimension, and target--clutter separability are characterized through a KL-based modal decomposition and a subspace-projection analysis. Numerical validation uses five literature-informed dielectric families to define physically traceable prior scenarios, a controlled random-field model to exercise the main propagation chain, and gprMax-based full-wave FDTD snapshots for an independent solver-level consistency check. Monte Carlo closure shows stage-wise numerical consistency, identifies steering linearization as the dominant approximation-sensitive step, and supports a weak perturbation regime with a bounded extension into a moderate regime. In a representative whitening-and-detection benchmark, the structured covariance model raises AUC from 0.593 for a diagonal baseline to 0.753, while prior-mismatch experiments indicate gradual rather than abrupt degradation. These results provide an explicit and interpretable interface for embedding complex-medium uncertainty into FDA-MIMO-GPR clutter analysis within a first-order, propagation-dominated setting.

While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgment scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. Code is available at GitHub ( this https URL ). Model weights: CMI-RM ( this https URL ). Datasets: CMI-Pref-Pseudo ( this https URL ) and CMI-Pref ( this https URL )

In this work, we address the need for efficient and formally stable Recurrent Neural Networks (RNNs) in environments with limited computational resources by analyzing the stability of the Minimal Gated Unit (MGU) network, a lightweight alternative to common gated RNNs used in system identification. We derive sufficient parametric conditions for the MGU network's input-to-state stability and incremental input-to-state stability properties. These conditions enable a-posteriori validation of model stability and form the basis for novel stability-promoting training methodologies, including a warm-start of the network's parameters and a projected gradient-based optimization scheme, both of which are presented in this work. Comparative evaluation, including robustness analysis and validation on synthetic and real-world data (i.e., the Silverbox benchmark), demonstrates that the minimal gated unit network successfully combines formal stability guarantees with superior parameter efficiency and faster inference times compared to other state-of-the-art recurrent neural networks, while maintaining comparable and satisfactory accuracy. Notably, the results attained on the Silverbox benchmark illustrate that the stable MGU network effectively captures the system dynamics, whereas other stable RNNs fail to converge to a reliable model.

Classical first-order optimization methods for imaging inverse problems scale poorly with image resolution. Wavelet based multilevel strategies can accelerate convergence under strong blur, but their fixed coarse-to-fine schedules lose effectiveness in moderate-blur or noise-dominated regimes. In this work, we propose an adaptive multiresolution block coordinate Forward-Backward algorithm for image restoration. Multiresolution block selection is driven by the local magnitude of the proximal update via a stochastic non-smooth Gauss-Southwell rule applied to the wavelet decomposition of the image. This adaptive selection strategy dynamically balances updates across scales, emphasizing coarse or fine blocks according to the degradation regime. As a result, the proposed method automatically adapts to varying blur and noise levels without relying on a predefined hierarchical update scheme.

Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory tracking and pose stabilization. However, their reliance on potentially untrusted training pipelines or supply chains introduces significant security vulnerabilities. This paper investigates backdoor (Trojan) attacks against neural controllers, using a differential-drive mobile robot platform as a case study. In particular, assuming that the robot's tracking controller is implemented as a neural network, we design a lightweight, parallel Trojan network that can be embedded within the controller. This malicious module remains dormant during normal operation but, upon detecting a highly specific trigger condition defined by the robot's pose and goal parameters, compromises the primary controller's wheel velocity commands, resulting in undesired and potentially unsafe robot behaviours. We provide a proof-of-concept implementation of the proposed Trojan network, which is validated through simulation under two different attack scenarios. The results confirm the effectiveness of the proposed attack and demonstrate that neural network-based robotic control systems are subject to potentially critical security threats.

Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a mixed-graph-based optimization algorithm to forecast traffic with spatial and temporal dimensions. We construct two graphs: an undirected graph $\mathcal{G}^u$ capturing spatial correlations across geography, and a directed graph $\mathcal{G}^d$ capturing sequential relationships over time. We predict future samples of signal $\mathbf{x}$, assuming it is "smooth" with respect to both $\mathcal{G}^u$ and $\mathcal{G}^d$, where we design new $\ell_2$ and $\ell_1$-norm variational terms to quantify and promote signal smoothness (low-frequency reconstruction) on a directed graph. We design an iterative algorithm based on alternating direction method of multipliers (ADMM), and unroll it into a feed-forward network for data-driven parameter learning. We periodically insert graph learning modules for $\mathcal{G}^u$ and $\mathcal{G}^d$ that play the role of self-attention. Experiments show that our unrolled networks achieve competitive traffic forecast performance as state-of-the-art prediction schemes, while reducing parameter counts drastically.

Uncrewed aerial vehicles (UAVs) have played an important role in the low-altitude economy and have been used in various applications. However, with the increasing number of UAVs and explosive wireless data, the existing bit-oriented communication network has approached the Shannon capacity, which cannot satisfy the quality of service (QoS) with ultra-reliable low-latency communication (URLLC) requirements for command and control (C\&C) transmission in bit-oriented UAV communication networks. To address this issue, we propose a novel semantic-aware C\&C transmission for multi-UAVs under limited wireless resources. Specifically, we leverage semantic similarity to measure the variation in C\&C messages for each UAV over continuous transmission time intervals (TTIs) and capture the correlation of C\&C messages among UAVs, enabling multicast transmission. Based on the semantic similarity and the importance of UAV commands, we design a trigger function to quantify the QoS of UAVs. Then, to maximize the long-term QoS and exploit multicast opportunities of C\&C messages induced by semantic similarity, we develop a proximal policy optimization (PPO) algorithm to jointly determine the transmission mode (unicast/multicast/idle) and the allocation of limited resource blocks (RBs) between a base station (BS) and UAVs. Experimental results show that our proposed semantic-aware framework significantly increases transmission efficiency and improves effectiveness compared with bit-oriented UAV transmission.

The Internet of Underwater Things (IoUT) supports marine sensing, environmental monitoring, subsea inspection, and autonomous underwater operations. However, IoUT communication is constrained by limited bandwidth, long propagation delay, time-varying underwater channels, intermittent connectivity, and strict energy budgets. Semantic Communication (SC) offers a promising alternative by transmitting task-relevant meaning rather than raw data, thereby improving communication efficiency in resource-constrained underwater networks. This paper presents a critical and feasibility-aware survey of SC for IoUT, focusing on opportunities, challenges, limitations, and future research directions. We first review the fundamentals of SC-enabled IoUT systems, including semantic representations, layered architectures, semantic channel modeling, and task-oriented evaluation metrics. We then examine learning-driven approaches based on machine learning (ML), knowledge graphs (KGs), vision-language models (VLMs), generative models, and federated learning (FL), with emphasis on their feasibility under underwater edge constraints. Representative applications, including environmental monitoring, marine ecology, subsea infrastructure inspection, disaster response, and autonomous underwater vehicle (AUV) coordination, are analyzed from an SC perspective. Finally, we identify key research directions involving standardized semantic models, reproducible testbeds, compute--communication trade-offs, trustworthy reconstruction, hybrid underwater links, energy-aware edge intelligence, semantic security, digital twins (DTs), and cross-domain interoperability. This survey provides a structured foundation for developing reliable, efficient, and meaning-driven IoUT communication systems.

This paper develops a generalized finite horizon recursive solution to the discrete time stage bound disturbance attenuation regulator (StDAR) for state feedback control. This problem addresses linear dynamical systems subject to stage bound disturbances, i.e., disturbance sequences constrained independently at each time step through stagewise squared two-norm bounds. The term generalized indicates that the results accommodate arbitrary initial states. By combining game theory and dynamic programming, this work derives a recursive solution for the optimal state feedback policy. The optimal policy is nonlinear in the state and requires solving a tractable convex optimization for the Lagrange multiplier vector at each stage; the control is then explicit. For systems with constant stage bound, the problem admits a steady-state optimization expressed as a tractable linear matrix inequality (LMI) whose empirical computational cost is approximately cubic in $n$. Numerical examples illustrate the properties of the solution. This work provides a complete feedback solution to the StDAR for arbitrary initial states. Companion papers address the signal bound disturbance attenuation regulator (SiDAR): the finite horizon solution in Part~I-A and convergence properties in Part~I-B.

Dynamic control of soft continuum robots (SCRs) holds great potential for expanding their applications, but remains a challenging problem due to the high computational demands of accurate dynamic models. While data-driven approaches like Koopman-operator-based methods have been proposed, they typically lack adaptability and cannot reconstruct the full robot shape, limiting their applicability. This work introduces a real-time-capable nonlinear model-predictive control (MPC) framework for SCRs based on a domain-decoupled physics-informed neural network (DD-PINN) with adaptable bending stiffness. The DD-PINN serves as a surrogate for the dynamic Cosserat rod model with a speed-up factor of up to 44,000. It is also used within an unscented Kalman filter for estimating the model states and bending compliance from end-effector position measurements. We implement a nonlinear evolutionary MPC running at 70 Hz on the GPU. In simulation, it demonstrates accurate tracking of dynamic trajectories and setpoint control with end-effector position errors below 3 mm (2.3\% of the actuator's length). In real-world experiments, the controller achieves similar accuracy and accelerations up to 3.55 m/s2.

Biophysical models in diffusion MRI (dMRI) hold promise for characterizing gray matter tissue microstructure. Yet, the reliability of their parameter estimates remains largely under-studied, especially in models that incorporate water exchange. In this study, we investigate the accuracy, precision, and presence of degeneracy of two recently proposed gray matter models, NEXI and SANDIX, using established acquisition protocols, on both simulated and \textit{in vivo} data. We employ $\mu$GUIDE, a Bayesian inference framework based on deep learning, to quantify parameter uncertainty and detect degeneracies, enabling a more interpretable assessment of model fits. Our results show that while some microstructural parameters, such as extra-cellular diffusivity and neurite signal fraction, are robustly estimated, others, including exchange time and soma radius, are often associated with high uncertainty and estimation bias, particularly under realistic noise conditions and reduced acquisition protocols. Comparison with non-linear least squares fitting highlights the critical advantage of uncertainty-aware methods: the ability to flag and filter out unreliable estimates. Together, these findings emphasize the need to report uncertainty and account for model degeneracies when interpreting model-based estimates. Our study advocates for the integration of probabilistic fitting approaches into imaging pipelines to improve reproducibility and biological interpretability.

The mechanical complexity of soft robots creates significant challenges for their model-based control. Specifically, linear data-driven models have struggled to control soft robots on complex, spatially extended paths that explore regions with significant nonlinear behavior. To account for these nonlinearities, we develop here a model-predictive control strategy based on the recent theory of adiabatic spectral submanifolds (aSSMs). This theory is applicable because the internal vibrations of heavily overdamped robots decay at a speed that is much faster than the desired speed of the robot along its intended path. In that case, low-dimensional attracting invariant manifolds (aSSMs) emanate from the path and carry the dominant dynamics of the robot. Aided by this recent theory, we devise an aSSM-based model-predictive control scheme purely from data. We demonstrate the effectiveness of our data-driven model in tracking dynamic trajectories across diverse tasks. We validate on high-fidelity, high-dimensional finite-element models of a soft trunk robot and Cosserat-rod-based elastic soft arms, with additional experiments confirming robust performance even in the presence of experimental noise. Notably, we find that five- or six-dimensional aSSM-reduced models outperform the tracking performance of other data-driven modeling methods by a factor up to 10 across all closed-loop control tasks.

The Hamilton-Jacobi skeleton, also known as the medial axis, is a powerful shape descriptor that represents binary objects in terms of the centres of maximal inscribed discs. Despite its broad applicability, the medial axis suffers from sensitivity to noise: Minor boundary variations can lead to disproportionately large and undesirable expansions of the skeleton. Classical pruning methods mitigate this shortcoming by systematically removing extraneous skeletal branches. This sequential simplification of skeletons resembles the principle of sparsification scale-spaces that embed images into a family of reconstructions from increasingly sparse pixel representations. We combine both worlds by introducing skeletonisation scale-spaces: They leverage sparsification of the medial axis to achieve hierarchical simplification of shapes. Unlike conventional pruning, our framework inherently satisfies key scale-space properties such as hierarchical architecture, controllable simplification, and equivariance to geometric transformations. We provide a rigorous theoretical foundation in both continuous and discrete formulations and extend the concept further with densification. By growing the skeleton successively instead of shrinking it, we allow inverse progression from coarse to fine scales. Densification scale-spaces can even reach beyond the original skeleton to produce overcomplete shape representations with relevancy for practical applications. Through proof-of-concept experiments, we demonstrate the effectiveness of our framework for practical tasks including robust skeletonisation, shape compression, and stiffness enhancement for additive manufacturing.

Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rollouts; MCFM instead builds the conservative-dissipative split into both the vector field and a structure preserving sampler. MCFM trains via conditional flow matching on short transitions, avoiding long rollout adjoints. In inference, a Strang-prox scheme alternates a symplectic update with a proximal metric step, ensuring discrete energy decay; an optional projection enforces strict decay when a trusted energy is available. We provide continuous and discrete time guarantees linking this parameterization and sampler to conservation, monotonic dissipation, and stable rollouts. On a controlled mechanical benchmark, MCFM yields phase portraits closer to ground truth and markedly fewer energy-increase and positive energy rate events than an equally expressive unconstrained neural flow, while matching terminal distributional fit.

Networked Control Systems (NCSs) have been instrumental in realizing fully connected and responsive intelligent environments within the context of real-time virtual control and management. However, traditional NCSs face considerable challenges in handling the vast amounts of data generated by large-scale control applications, particularly in terms of data acquisition, storage, and computational processing. To address these challenges, the emergence of cloud computing and advancements in control theory have empowered the new paradigm known as Cloud Control Systems (CCSs). Recently, CCSs have received substantial attention from industries for their potential properties, such as large-scale data management, complex computations, and data-centric optimized decisions. This study presents an extensive review of recent progress in CCSs spanning over multiple studies published between 2012 and 2025. Specifically, the focus is on providing a taxonomy of the current findings in CCS research, encompassing various perspectives, such as its efficient implementations in industrial automation, security and privacy considerations, and cloud-based control techniques. Each category is examined in depth through selected state-of-the-art analyses of different approaches and contrasting methodologies. Furthermore, we discuss future directions aimed at designing more efficient and practical CCSs. The insights gained from this study can help researchers, practitioners, and decision-makers in their domain for effective CCS design and deployment.

Integrating the Alternating Direction Method of Multipliers (ADMM) with Differential Dynamic Programming (DDP) provides a scalable framework for distributed multi-agent trajectory optimization. In practice, ADMM is typically truncated for computational efficiency, tightly coupling parameters that would otherwise separately govern coordination quality and task performance. In this paper, we propose Differentiable Coordination (DiffCoord), a unified framework that jointly meta-learns these coupled parameters for the truncated ADMM-DDP pipeline. These parameters are generated by agent-wise neural networks for task adaptation, and the same networks are shared among isomorphic agents to enable scalability to varying agent counts. We achieve efficient meta-learning by differentiating the ADMM-DDP pipeline end-to-end. Notably, this yields an auxiliary ADMM-LQR distributed gradient solver that computes and coordinates meta-gradients with respect to these parameters. This solver inherits the computational structure of the pipeline, enabling reuse of key computation results and efficient parallelization over agents and along trajectory horizons. We validate DiffCoord through numerical and physical experiments on a cooperative aerial transport system, where it reconfigures quadrotor formations for safe 6-DoF load manipulation in tight spaces. It adapts robustly to varying team sizes and load dynamics, while reducing per-agent gradient computation time by up to 70% compared with state-of-the-art trajectory-gradient methods.

Deploying reliable bioacoustic monitoring systems requires models that generalize under high-noise, low-SNR conditions and evaluation protocols that expose deployment-relevant failure modes, gaps largely unaddressed in current UPAM practice. Intrinsic noise, variable propagation, and mixed biological and anthropogenic sources induce distribution shifts that conventional models and single-split evaluations obscure, inflating performance and masking instability. We introduce GetNetUPAM, a hierarchical nested cross-validation framework that uses the nested stage to quantify model stability rather than tune for inflated hold-out scores. By partitioning data into site-year blocks, GetNetUPAM preserves ecological heterogeneity and forces each outer fold to represent a distinct environmental regime, preventing overfitting to localized noise or sensor artifacts. Inner stratified folds measure generalization across the full UPAM signal distribution, enforcing strict separation between model development and the outer held-out deployment condition. Using GetNetUPAM, we evaluate the Adaptive Resolution Pooling and Attention Network (ARPA-N), a CNN architecture for irregular spectrogram dimensions. ARPA-N integrates CBAM spatial attention as a learned noise suppressor, producing attention maps that localize true call structure and avoid the global, non-biological cues exploited by standard CNNs on long-window data. Under GetNetUPAM, ARPA-N generalizes robustly across diverse environmental regimes. In the zero-training support Balleny Islands region, it reduces false positives per hour by over an order of magnitude (approximately 10x) at fixed 90 percent recall, yielding consistently improved metrics across folds. These advances provide a reproducible benchmark and move UPAM toward scalable, deployment-reliable ecological monitoring.

This paper investigates a low Earth orbit (LEO) satellite communication system enhanced by an active stacked intelligent metasurface (ASIM), mounted on the backplate of the satellite solar panels to efficiently utilize limited onboard space and reduce the main satellite power amplifier requirements. The system serves multiple ground users via rate-splitting multiple access (RSMA) and IoT devices through a symbiotic radio network. Multi-layer sequential processing in the ASIM improves effective channel gains and suppresses inter-user interference, outperforming active RIS and beyond-diagonal RIS designs. Three optimization approaches are evaluated: block coordinate descent with successive convex approximation (BCD-SCA), model-assisted multi-agent constraint soft actor-critic (MA-CSAC), and multi-constraint proximal policy optimization (MCPPO). Simulation results show that BCD-SCA converges fast and stably in convex scenarios without learning, MCPPO achieves rapid initial convergence with moderate stability, and MA-CSAC attains the highest long-term spectral and energy efficiency in large-scale networks. Energy-spectral efficiency trade-offs are analyzed for different ASIM elements, satellite antennas, and transmit power. Overall, the study demonstrates that integrating multi-layer ASIM with suitable optimization algorithms offers a scalable, energy-efficient, and high-performance solution for next-generation LEO satellite communications.

Deep learning-based machine listening is broadening the scope of industrial acoustic analysis, yet its widespread implementation on live shop floors is hindered by the reliance on large, task-specific annotated datasets for every new task. While emerging general-purpose sound foundation models aim to alleviate data dependency, they reveal critical dilemmas in practice. General-purpose sound foundation models are computationally expensive and fail in industrial scenarios characterized by tonal harmonics, broadband noise, and transient fault events, making instant, on-site deployment impractical. These challenges combined mean that a practical, end-to-end system for deploying a sound foundation model on a live shop floor has remained elusive. To address this challenge, this study introduces LISTEN (Lightweight Industrial Sound-representable Transformer for Edge Notification), the first lightweight foundation model specialized for industrial sound. Through Knowledge Distillation (KD) from the large-scale teacher model IMPACT (Industrial Machine Perception via Acoustic Cognitive Transformer), we construct LISTEN optimized for resource-constrained edge environments. By freezing the backbone and training only a shallow head on minimal target-process data, rather than performing full fine-tuning or retraining, LISTEN achieves nearly identical performance to IMPACT across diverse manufacturing processes. This study further demonstrates a complete system for real-time machine monitoring, encompassing data acquisition with Industrial Internet of Things (IIoT) devices, rapid model adaptation using minimal annotated data, and real-time monitoring on a low-cost edge device. By validating the entire system on a live CNC machine, this work establishes the first feasible end-to-end system for deploying a lightweight industrial sound foundation model in an active industrial environment.

Plug-and-Play (PnP) algorithms are a class of iterative algorithms that address image inverse problems by combining a physical model and a deep neural network for regularization. Even if they produce impressive image restoration results, these algorithms rely on a non-standard use of a denoiser on images that are less and less noisy along the iterations, which contrasts with recent algorithms based on Diffusion Models (DM), where the denoiser is applied only on re-noised images. We propose a new PnP framework, called Stochastic deNOising REgularization (SNORE), which applies the denoiser only on images with noise of the adequate level. It is based on an explicit stochastic regularization, which leads to a stochastic gradient descent algorithm to solve ill-posed inverse problems. A convergence analysis of this algorithm and its annealing extension is provided. Experimentally, we prove that SNORE is competitive with respect to state-of-the-art methods on deblurring and inpainting tasks, both quantitatively and qualitatively.

In this article, we employ active simultaneously transmitting and reflecting reconfigurable intelligent surfaces (ASRIS) to enhance the quality of 6G cellular network services. The network integrates commensal symbiotic radio (CSR) subsystems to facilitate communication between passive Internet of Things (IoT) users and active users, referred to as symbiotic backscatter devices (SBDs) and symbiotic user equipments (SUEs), respectively. Since the SBDs are passive, transmitting information to the SUEs poses significant challenges. To overcome this challenge, we harness the capabilities of massive multiple input multiple output (MIMO) antennas within the base station (BS) to relay the information transmitted by SBDs with greater power. This scheme uses the non-orthogonal multiple access (NOMA) technique for multiple access among all users, and potential interferences are eliminated using successive interference cancellation (SIC). The primary objective is to maximize the throughput between SBDs and SUEs. To achieve this, we formulate an optimization problem involving variables such as active beamforming coefficients at the BS and ASRIS, phase adjustments of ASRIS, and scheduling parameters between CSR and cellular networks. To solve this optimization problem, we used three deep reinforcement learning (DRL) methods: proximal policy optimization (PPO), twin delayed deep deterministic policy gradient (TD3), and asynchronous advantage actor critic (A3C). These methods were simulated, and the results demonstrate that A3C, TD3, and PPO have the best convergence speeds and achieve the highest increases in network throughput, respectively. Finally, the proposed scheme was evaluated using passive simultaneously transmitting and reflecting RIS (STAR-RIS), which demonstrated poorer performance compared to ASRIS.