Papers

Satellite anomaly detection is essential for maintaining mission reliability and spacecraft health, yet remains challenging due to the high-dimensional, irregular, and imbalanced nature of spacecraft telemetry data. This paper presents a systematic benchmark study evaluating supervised and unsupervised anomaly detection approaches on the large-scale ESA-ADB dataset across two mission settings of varying temporal scales. Supervised models, including Multiscale Convolutional Neural Networks (Multiscale CNN), Graph Convolutional Networks (GCN), and Graph Attention Networks (GAT), are compared against unsupervised methods, namely Elliptic Envelope (EE) and Empirical Cumulative Distribution Function-based Outlier Detection (ECOD). Beyond detection performance, we rigorously analyze computational runtime and scalability, which are critical for practical deployment in spacecraft operations. Results show that supervised models achieve stronger overall performance, while unsupervised methods offer competitive precision with significantly lower computational overhead. These findings underscore a fundamental trade-off between detection capacity and operational efficiency, offering practical guidance for mission engineers designing scalable satellite health monitoring systems.

Continuous fluid antenna systems (CFASs) represent an upper bound on the spatial diversity performance of fluid antenna systems (FASs), achieved when antennas may be positioned anywhere within a defined spatial region. This article examines the fundamental relationships governing CFAS performance. The focus is on the probability that the signal-to-noise ratio (SNR) exceeds a prescribed high threshold, termed the high SNR probability (HSP). This is among the few FAS performance metrics that admit the derivation of closed-form expressions. Following a survey of recent analytical advances in FAS performance limits, a dimensional scaling law derived for the HSP of a single-user, single-antenna CFAS is examined. This law is then applied to the per-user high signal-to-interference-plus-noise ratio (SINR) probability of a two-antenna, two-user CFAS employing minimum mean-squared error (MMSE) combining. For both scenarios, performance gains are shown to increase consistently with both dimensionality and region size. Remarkably, the scaling law remains accurate in the two-user case, showing that, in both scenarios, the influence of additional dimensions is dominated by the CFAS size and considered threshold. Moreover, the per-user high SINR probability of the two-user system exceeds the single-user HSP, despite the addition of inter-user interference.

UAV-mounted reconfigurable intelligent surfaces (RIS) are a promising enabler for 6G networks, offering dynamic control of wireless propagation for coverage enhancement, integrated sensing and communication (ISAC), and localization. By exploiting UAV mobility, RIS can maintain favorable line-of-sight links, improving channel quality in dynamic environments. However, UAV positioning uncertainties introduce channel distortions that degrade RIS phase alignment and coherent combining. This work develops a GUM-based uncertainty propagation framework for UAV-mounted RIS channels, mapping UAV position uncertainty through the geometric Tx-RIS-Rx model into the complex cascaded channel. We derive a closed-form stochastic propagation model capturing nonlinear phase uncertainty effects and quantify their impact on channel coherence. The results show that phase uncertainty induces exponential coherence loss, dominating performance degradation. To characterize this transition, we introduce a performance-driven coherence threshold (PCT) that defines the boundary where incoherent combining results in a predetermined performance loss. Results based on analytical scaling laws and Monte Carlo simulations confirm the tightness of the PCT in accurately capturing the coherence transition. This validated threshold is then leveraged to derive optimal UAV-mounted RIS placement, revealing that realistic positioning conditions significantly deviate from the conventional RIS intuition, which typically favors placement close to either the transmitter or receiver.

High-frequency communications strongly depend on the line-of-sight (LoS) path, and obstacle blockage can severely degrade the received signal power and achievable rate. Near-field Airy beams with curved trajectories can circumvent obstacles, offering a promising way to alleviate blockage. However, since an Airy beam carries most useful energy along a single curved trajectory, existing Airy beamforming methods are highly sensitive to estimation errors of transmitter-obstacle-receiver geometry. That is to say, even a small error in the estimated geometry may cause the mismatched Airy trajectory, leading to severe performance loss. To address this problem, we propose a multi-Airy beamforming scheme for blockage-robust near-field communications. Specifically, we first reveal and analyze the sensitivity mechanism of single-Airy beamforming. This mechanism motivates us to extend the single-Airy generation method to a coordinated multi-Airy generation method by deriving the phase offsets required to coherently combine multiple Airy beams at the target user. Based on this coordinated generation method, we partition the transmit array into multiple sub-arrays and configure a tailored Airy beam for each sub-array, so that the resulting Airy beams formed by multiple curved trajectories can be coherently combined at the target user. Simulation results verify the sensitivity of single-Airy beamforming and the robustness of multi-Airy beamforming under estimation errors of transmitter-obstacle-receiver geometry. Moreover, the proposed scheme achieves higher achievable rates than single-Airy beamforming in blocked scenarios without geometry estimation errors.

The certainty equivalence (CE) principle underpins a wide range of control architectures by enabling the separation of estimation and control design. While this property holds for linear systems, its validity in nonlinear settings remains limited and often implicitly assumed. This paper revisits CE from a nonlinear perspective, showing that estimated states induce an intrinsic coupling between estimation and tracking dynamics. By analyzing the closed-loop system in tracking-error coordinates, we demonstrate that nonlinear state dependence gives rise to higher-order interaction terms during aggressive transients. Motivated by this limitation, we propose an estimation-aware (EA) control paradigm that incorporates estimation quality into the feedback law to isolate estimation-induced loops. The formulation remains filtering-agnostic while preserving general applicability to smooth, underactuated nonlinear systems. We derive analytical conditions guaranteeing bounded tracking under uncertainty, validating the framework under high-fidelity quadrotor flight simulation along complex 3D trajectories at speeds up to 57.6 km/h. Frequency-domain evaluations demonstrate that the EA law extends tracking bandwidth by 39% and improves stability margins by up to 55%, effectively mitigating severe cross-couplings to offer a robust alternative to classical CE-based designs.

Efficient optimization and control of photonic computing and communication systems increasingly rely on accurate surrogate models/digital twins. While data-driven models may achieve faster inference than traditional physics-based methods, they typically suffer from poor training data efficiency and limited generalizability. To address this trade-off, physics-informed data-driven modeling has emerged as a powerful hybrid paradigm. This paper presents a comparative analysis of these three modeling paradigms across three test use cases: optical amplifiers, directly modulated lasers, and interferometer meshes. By evaluating model complexity, data efficiency, generalizability, and modularity, this work provides a detailed analysis of the respective trade-offs and highlights the advantages of combining physical insight with data-driven learning.

High-quality system measurement data is critical for power distribution system operation. As deep generative models (e.g., GAN, Diffusion, etc.) have been widely studied to solve the missing data restoration problem to enhance the data quality, their results may look "realistic" but not sufficiently "accurate" due to lacking physical guarantees. To address this limitation, a two-stage physics-guided framework, Flow-PIN, is proposed in this paper for system-wide multivariate profile inpainting. The first stage employs a conditional flow matching model, conditioned on topological and correlation graphs, to generate candidate values. A physical penalty is integrated into the loss function to constrain the generative vector field based on grid physical laws. The second stage introduces a topology-aware power-flow-guided refiner that utilizes Laplacian positional encoding to inject topology information into node embeddings. By coupling alternating current power flow equations with a differentiable correlation alignment mechanism, this refiner further corrects numerical deviations. Evaluations on an active distribution network dataset benchmark the proposed framework against ten representative baselines. The results show that Flow-PIN achieves high-fidelity profile inpainting across three dimensions: maximizing numerical accuracy, capturing temporal fluctuation, and preserving spatial topological correlations.

Power distribution system feeder models (e.g., IEEE 33-bus system, IEEE 13-bus system, etc.) are cornerstones for conducting power distribution system studies. As real-world feeder models are hard to acquire due to energy security concerns, generating high-quality synthetic feeders becomes an important alternative to satisfy the fast-growing and diversified needs of power system researchers and engineers. In this paper, we propose an LLM-based synthetic feeder generation framework that can achieve end-to-end generation from natural language specifications to physically consistent feeder models. First, Supervised Fine-Tuning (SFT) is performed on a dataset created following physical laws to empower the LLM with syntactic understanding of complex feeder structures. Second, Group Relative Policy Optimization (GRPO) with a specially-designed multi-stage gated reward function is introduced to better align the generation results with user intent and physical constraints. Third, a dual-agent architecture is deployed to refine and evaluate the generated feeders. Specifically, a refinement agent calibrates the feeder model parameters referring to the industrial feeder design standards, while a judge agent provides quality assessments. Case studies demonstrate that the proposed framework generates customizable feeders with valid formats, physical consistency and high engineering applicability.

Estimating the region of attraction (RoA) of nonlinear systems is fundamental for assessing closed-loop stability and ensuring safe operation. While Lyapunov-based approaches provide certified stability guarantees, they often yield conservative inner approximations of the RoA. This paper combines a certified Lyapunov-based positively invariant set with a predecessor-based implicit representation to compute a significantly less conservative inner approximation of the RoA while preserving formal stability guarantees. In addition, the robust positive invariance of the initial certified Lyapunov-based invariant set is analyzed under bounded additive input disturbances, providing formal robustness guarantees. The proposed methodology is demonstrated on a nonlinear two-wheeled inverted pendulum stabilized by a saturated linear quadratic regulator. The resulting RoA approximation is compared with the initial Lyapunov-certified invariant set and validated through Monte Carlo simulations and hardware experiments, showing a substantially enlarged certified operating region that matches the empirical closed-loop behavior. These results demonstrate the practical applicability of combining certified Lyapunov analysis with predecessor-based set propagation for RoA approximation and robustness assessment of nonlinear systems.

Background: Automated 3D segmentation of muscles and adipose tissue from CT is vital for body composition analysis, but multi-source data heterogeneity and high CPU memory demands hinder clinical deployment. Methods: We propose a coarse-to-fine hierarchical framework to segment ten tissue structures. Efficiency is optimized using Dynamic Spacing and Anisotropic Patching, a Group Inference mechanism for low-memory sliding-window processing, and Topology-Aware Asymmetric Resampling for fast post-processing. Results: The framework was trained on 1,558 CT volumes from seven public and two private datasets, and evaluated on an independent test cohort (N=105), per-structure Dice coefficients ranged from 0.924 to 0.982. Eight major structures met the +-10% relative error clinical acceptance limit. On a 12-core CPU workstation, the GPU-free pipeline averaged 44.5 seconds per volume with 4.73 GB peak memory. Conclusion: This framework balances accuracy and efficiency, enabling robust, large-scale body composition analysis on standard CPU workstations.

Recent full-duplex spoken dialogue models have demonstrated compelling progress toward human-like interaction, enabling agents to respond with low latency, produce backchannels, and handle user barge-ins. Yet these improvements in conversational dynamics often come with weaker reasoning and instruction-following abilities, revealing a potential tension between interactive dynamics and intelligence capability. In this paper, we argue that such an intelligence–dynamics trade-off is not fundamental: conversational dynamics can instead be learned as a separate real-time decision policy from human dialogue data. To this end, we propose DuplexPO, a reinforcement learning (RL) framework that decouples when to speak from what to say. It preserves the semantic response capability of an instruction-tuned assistant, while optimizing its temporal interaction behavior over selected high-impact windows from long human conversations. To quantitatively optimize these dynamics, we formulate the Factorized Conversational Dynamics Reward (FCDR) to enable fine-grained temporal credit assignment for turn initiation, backchanneling, yielding, and regularized participation. The policy is then optimized with a GRPO-style objective. Experiments show that DuplexPO substantially improves full-duplex behaviors, including timely backchannels, smooth turn-taking, and barge-in handling, while maintaining strong reasoning and instruction-following performance. Moreover, improvements in dynamics-oriented metrics are reflected in better user experience, suggesting that optimizing conversational timing as a standalone objective can promote more natural full-duplex interaction.

The Internal Waves Service screens the Sentinel-1 Wave-mode archive for internal solitary waves, routing detections to experts whose adjudication time is the resource the effort exists to conserve. Because attention is the cost of error, precision leads. Its classifier was trained and reported at a one-to-one class balance, fixed before the operational rate could be known. That rate has since emerged at roughly one scene in twenty, and a balanced-test score badly overstates the precision a validator meets. A model that scores 0.794 balanced-test precision scores 0.192 in real operation: the gap is a systematic artefact of reporting at the wrong prior, invisible to the metric most work quotes. We show the mismatch to be an evaluation problem in the costume of a training one at a fixed recall, prior correction and calibration cannot move precision, and answer it with a prior-matched reporting method based on three numbers: balanced-test, operational-prior, and real post-deployment, whose contrast is the honest measure. A precision-first, leakage-controlled development cycle then improves the classifier lever by lever, each promoted only against a pre-registered margin; negative variety and the aggregation head lifting, capacity paying once then stopping, calibration inert, so the honest negatives are as much a result as the gains. Holding recall at a floor of 0.80 and certifying against a sealed, single-read lockbox, the promoted model reports 0.927 precision at the operational prior; an out-of-time check confirms discrimination transfers to unseen periods while a fixed operating point does not. Prior-matched reporting, begin balanced, then move to the prior as the stream reveals it, transfers to any operational Earth-observation service bootstrapping a rare-event detector under a prior it has yet to discover.

Segmenting slender curvilinear structures such as retinal vessels, cracks, and roads demands topological correctness, as even a single-pixel discontinuity can fragment a continuous network and invalidate downstream analysis. Under standard binary-mask supervision, models optimized for pixel-level overlap frequently produce topologically broken predictions. We trace this to a fundamental mismatch: pixel-wise losses distribute gradients uniformly, yet connectivity hinges on a sparse set of bottleneck pixels. These pixels are vastly outnumbered by thick structures and background, rendering their aggregate gradient contribution negligible. We term this phenomenon topological gradient starvation (TGS). To address it, we propose Widest-Path Reachability Fields (WPRF), a differentiable Max-Min reachability objective that redirects gradient flow to connectivity bottlenecks. The module is plug-and-play, backbone-agnostic, and incurs no inference overhead. WPRF implements a differentiable Max-Min objective via dynamic programming on a domain-restricted graph, coupled with a bottleneck-aware observation term that balances gradient contributions across varying structures. Compared to prior topology-aware losses that rely on post-hoc skeletonization or homology computation, WPRF directly optimizes end-to-end reachability via differentiable Max-Min algebra, enabling gradient flow to concentrate on connectivity bottlenecks without auxiliary structures. We introduce OMVIS, a new oral microvessel segmentation dataset. Experiments across nine architectures and six datasets validate the bottleneck-focused gradient routing mechanism. WPRF improves 87% of experiments with fixed hyperparameters and achieves clDice gains of 7.2 percentage points on structurally fragile datasets.

Subsampling significantly reduces the number of measurements, thereby streamlining data processing and transfer overhead, and shortening acquisition time across diverse real-world applications. The recently introduced Active Deep Probabilistic Subsampling (A-DPS) approach jointly optimizes both the subsampling pattern and the downstream task model, enabling instance- and subject-specific sampling trajectories and effective adaptation to new data at inference time. However, this approach does not fully leverage valuable dataset priors and relies on top-1 sampling, which can impede the optimization process. Herein, we enhance A-DPS by integrating a deterministic (fixed) prior-informed sampling pattern derived from the training dataset, along with group-based sampling via top-k sampling, to achieve more robust optimization, method we call Prior-aware and context-guided Group-based Active DPS (PGA-DPS). We also provide a theoretical analysis supporting improved optimization via group sampling, and validate this with empirical results. We evaluated PGA-DPS on three tasks: classification, image reconstruction, and segmentation, using the MNIST, CIFAR-10, fastMRI knee, and hyperspectral AeroRIT datasets, respectively. In every case, PGA-DPS outperformed A-DPS, DPS, and all other sampling methods.

Data-Enabled Predictive Control (DeePC) has recently emerged as a framework for controlling unknown systems from data. However, its performance relies on the relevance of the collected data, and as such, disturbances lead to inevitable errors. This paper addresses this problem by proposing an augmentation of DeePC using Model-Free Disturbance Observer with Online Modification (MFDOOM). The method corrects output predictions based on previous prediction errors using a dedicated continuously updated Hankel matrix. We compare our method, both theoretically and through simulation, to other recent algorithms designed for time-varying systems in the DeePC framework. It is shown that for disturbances that can be modeled as the output of an autonomous linear time-invariant system, this approach can reduce tracking error and online-update burden compared with existing online DeePC variants.

To achieve the desired coverage and capacity levels, future terahertz (THz) wireless systems are envisioned to utilize extremely large antenna arrays. At THz frequencies, the combination of short wavelengths and large array apertures often makes many of the conventional far-field assumptions invalid in practice. As a result, many UEs operate in the radiative near-field zone, where novel near-field beam synthesis methods become viable. This paper studies phase-only Bessel-like near-field beam configurations for downlink THz multiple-input multiple-output links under imperfect UE location knowledge. We first formulate a spectral efficiency maximization problem with respect to the "Bessel cone angle”. We then derive low-complexity closed-form approximations for the optimal Bessel beam configuration for: (i)deterministic UE location; (ii)Gaussian and (iii)uniform error in the UE location. Finally, through extensive simulations across multiple signal frequencies, UE locations, and array sizes, we show that our proposed simple closed-form approximations closely match (under 0.1% difference) the best performance achieved via exhaustive search, while simultaneously reducing the configuration complexity down to as low as O(1).

Industrial sealing and dispensing cells often reuse a pressure chain, nozzle, substrate path, and vision interface across product recipes. For a narrow bead recipe, however, a calibrated static pressure can remain correct while small corrective moves are absorbed by actuator deadband; delivered pressure changes only after a direction- and history-dependent threshold is crossed. Commissioning is defined here as the target setup and retuning interval after such a recipe change. A physical gluing and dispensing cell provides pressure-to-width calibration, a fixed probing sequence, signal-interface limits, residual scales, and actuator bounds. The controller comparison is then run on an anonymized digital twin calibrated from those measurements. The actuator-deadband-aware Koopman model predictive controller (AK-MPC) initializes from probe-conditioned memory (PCM) that links the pressure setpoint to probe-inferred actuator behavior, a predictor, a controller prior, and a fallback filter. During commissioning, a sixteen-move probe selects a nearby historical case, fits the current pressure-width relation, updates a small local dynamic correction, and supplies a feasible receding-horizon pressure policy. In the main \(1.00\) mm benchmark, where delivered-pressure loss is visible in the probe, AK-MPC reaches 0.0487 mm tracking mean absolute error (MAE) over 60 paired cases; the calibration-only inverse, adaptive proportional-integral, online recursive-least-squares ARX, and probe-fitted ARX controllers range from 0.2492 to 0.3956 mm. This large gap reflects the full constrained Koopman-MPC and online-correction workflow. The isolated PCM contribution is measured by ablation: removing PCM raises the error to 0.0655 mm. In this regime, a short actuator characterization makes historical runs useful before much target data are available.

Mobile C-arm cone-beam computed tomography (CBCT) has been widely used for real-time intraoperative 3D imaging. However, current practice often mechanically applies the fan-beam CT criterion of "180{\deg} plus fan angle" in pursuit of "data completeness" in reconstruction. This review argues that, under the single circular trajectory of three-dimensional cone-beam geometry, complete data are mathematically unattainable; moreover, blindly increasing sampling may exacerbate the trade-off among intraoperative image quality (Q), imaging time (T), and radiation dose (D). Against this background, this review reframes the evaluation of intraoperative CBCT around "data sufficiency" rather than "data completeness." This perspective moves beyond the excessive pursuit of absolute mathematical and analytic accuracy, and instead emphasizes task-specific minimum image-quality thresholds required for clinical decision-making. By synthesizing evidence from multiple clinical scenarios, this review suggests that approximation errors can be acceptable when clinical decision-making requirements are satisfied, thereby achieving a Q-T-D balance.

This paper addresses observer-based target control for linear time-delay systems subject to simultaneous, mismatched input and output latencies. While full-state regulation is often conservative and computationally intensive, practical engineering objectives typically require controlling only specific linear combinations of states, or target outputs. To overcome the challenges posed by these asymmetric, dual-channel delays, we propose a reduced-order modeling framework inspired by the structural philosophy of Fernando and Darouach \cite{Fernando2025}. By projecting the high-dimensional plant dynamics onto the row space of the target output matrix $F_o$, the controller focuses strictly on the lower-dimensional target subspace. Based on this projection, an observer-based control scheme is developed to ensure precise target stabilization despite the simultaneous, mismatched input, state, and output latencies.

Table tennis, a dynamic, compact, and popular sport, has received significant attention as a robotics benchmark over the last decades. Most of the research has focused on the rally aspect - returning an incoming ball - requiring high-speed vision, agile motion planning, and tight closed-loop control. However, the other component of table tennis gameplay - the serve - is comparatively a quite unexplored research problem, that in fact requires pushing physics modeling and control to the extremes. Achieving competitive serves with a robot presents domain-specific challenges, such as high-spin generation from a spinless ball, precise aiming, or multi-objective optimization. In this work, we present a novel approach for generating official rule-compliant serves by combining motion primitives, Model Predictive Control, and Bayesian Optimization. Serves generated in this way offer a wide and controllable variation of spins of up to 550 rad/s, and speeds of up to 6.7 m/s, matching and even surpassing those of elite table tennis players.

This paper examines the subspace consensus problem for matrix-weighted multi-agent networks. In this setting, each agent holds a high-dimensional state vector in $\mathbb{R}^{d}$, and matrix-valued edge weights characterize inter-agent interactions across different dimensions. Unlike the classical scalar-weighted consensus problem, where all dimensions of agents' states must converge to respective common values, this paper examines scenarios in which agents must agree along certain dimensions while preserving prescribed relative configurations in the remaining ones. To address this need, we introduce the concept of subspace consensus for a matrix-weighted network, which is said to achieve consensus on a subspace $\mathbb{V}\subseteq\mathbb{R}^{d}$ if the projections of all pairwise state differences onto $\mathbb{V}$ asymptotically vanish. This formulation subsumes the conventional consensus problem as the special case $\mathbb{V}=\mathbb{R}^{d}$. We first derive a purely algebraic necessary and sufficient condition for subspace consensus by characterizing the interplay between the null spaces of the matrix-valued Laplacian and those of the individual matrix-valued edge weights. Then, we propose the limiting constraint network as a means to analyze the steady state of matrix-weighted networks. We establish the relationship between the steady state of a matrix-weighted network and the null space of the matrix-valued Laplacian of the associated limiting constraint network. Under mild assumptions, we further show that a matrix-weighted network achieves subspace consensus on $\mathbb{V}$ if and only if the associated limiting constraint network contains a $\mathbb{V}$-spanning tree. We further show that a matrix-weighted network achieves consensus if and only if the associated limiting constraint network contains a positive spanning tree, as a special case with $\mathbb{V}=\mathbb{R}^{d}$.

The rapid growth of artificial intelligence workloads is increasing the scale and concentration of data center demand, creating new concerns for power system resilience under disruptive events. This paper extends a validated multi-time-step DC optimal power flow framework to evaluate the impact of aggregated data center demand on contingency-induced unserved energy. Using an IEEE 30-bus system with flexible resources, we replace a conventional load at a contingency-exposed bus with an energy-matched constant data center load and examine two capacity-growth levels under generator derating, transmission line derating, and coupled derating. The results show that data center capacity growth substantially increases both system-level and data-center-bus unserved energy under transmission-constrained contingencies. Under coupled derating, the high-growth case increases total unserved energy from 3.203 MWh in the energy-matched case to 22.891 MWh. A supplementary energy-matched coincident-demand case further increases total unserved energy by 34.4%, indicating that temporally concentrated data center demand can amplify resilience impacts even without increasing total energy consumption.

Sampling-based model predictive control methods handle nonlinear dynamics and complex cost landscapes through Monte Carlo rollouts, yet typically employ fixed constraint penalties that do not adapt to model-plant mismatch. This paper proposes Residual-Conservative Model Predictive Path Integral Control (RC-MPPI), a sampling-based MPC framework that modulates safety conservatism online using the prediction-execution residual. RC-MPPI combines three coupled mechanisms: residual-dependent constraint tightening, adaptive safety-cost shaping, and residual-adaptive sampling modulation through exploration contraction and temperature relaxation. The temperature adaptation reflects a key insight: when the model is inaccurate, rollout cost evaluations become unreliable, and increasing temperature reduces overcommitment to apparent cost rankings. Under Lipschitz dynamics and sub-Gaussian disturbances, we derive probabilistic bounds on constraint violation and show that the joint effect of the adaptive mechanisms reduces violation probability as the residual grows. A rollout-cost uncertainty analysis further shows that model-plant mismatch perturbs MPPI importance weights in proportion to residual magnitude and inversely with temperature, providing theoretical justification for residual-adaptive temperature relaxation. Simulations on an LTI point-mass system and a planar 2R manipulator show improved safety margin, success rate, and control efficiency compared with vanilla MPPI under significant model-plant mismatch.

Model Predictive Path Integral (MPPI) control is directly implementable on nonlinear systems because its online update requires only forward rollouts of the dynamics, not gradients, linearizations, or convex optimization. However, this algorithmic flexibility does not by itself provide a closed-loop stability certificate. This paper establishes such a certificate through a stability-inheritance argument. We assume that there exists a deterministic nonlinear MPC policy whose disturbance-free closed loop is certified by a Control Lyapunov Function terminal cost and a contraction metric, and we show that finite-sample MPPI inherits the nominal contraction when its sampling-based update approximates this reference policy with sufficient accuracy. The approximation error decomposes into a finite-temperature bias floor and a Monte Carlo term that vanishes at the inverse square-root rate in the sample count. Under an explicit small-gain condition, the resulting MPPI closed loop satisfies a finite-horizon, high-probability localized mean practical stability bound with residual floors due to MPPI approximation error, Gaussian process noise, and bad sampling events. The paper also gives an ISS-type restatement and a finite-horizon design procedure for choosing the localization set, temperature, and sample count.

Variable-speed pumped storage hydropower (VS-PSH) must honor short-block dispatch commitments while limiting the operational degradation that intensified regulation duty inflicts on its components. When a single controller pursues both aims at once, every tracking gain is paid for in degradation, a conflict that persists even under full model knowledge and look-ahead. This paper proposes a two-layer control architecture that separates the guaranteed commitment from the bounded learning. A deterministic feedforward-PI gate controller, auditable and certifiable for grid-connected operation, secures average power delivery over each five-minute block, while a residual reinforcement learning policy adjusts only the rotor speed within a fixed bound the gate loop can always absorb, so the worst-case command is bounded by construction. The speed policy tracks a demand-dependent best-efficiency-point reference and is trained against an operation-degradation index that combines off-best-efficiency hydraulic loss with power and actuation variation into one physically interpretable signal. Across normal and stressed dispatch, the proposed policy lowers best-efficiency-point tracking error by roughly 96% relative to a fixed-speed baseline and cuts total degradation by up to about 56% under the most demanding dispatch. It matches or slightly exceeds a full-information model-based optimizer in efficiency while preserving substantially tighter block tracking.

Audio-Visual speech recognition systems often degrade in real-world scenarios due to signal corruption and distribution shifts. To address this, we propose a unified uncertainty-modeling framework, namely the uncertainty-aware Bayesian gating network (UBG-Net). UBG-Net features a Modality Uncertainty-aware Bayesian Fusion (MUBF) mechanism that injects signal-level aleatoric uncertainty into a Bayesian network to model epistemic uncertainty, thereby ensuring robust fusion of pre-trained backbone features. For inference, we introduce Distribution Uncertainty-aware Hierarchical Voting (DUHV) to select transcripts from Monte Carlo samples, prioritizing frequency and using inference scores in case of a tie. Experiments on the AVCocktail and LRS2 datasets demonstrate the overall superiority of UBG-Net compared to SOTA baselines. Ablation studies confirm that MUBF and DUHV effectively filter noise, enhancing fusion and decoding robustness.

This paper addresses the problem of non-adaptive global robust disturbance rejection for two distinct classes of nonlinear systems. The first class, denoted by C1, consists of nonlinear systems in strict-feedback form, with linear and Hurwitz zero-dynamics (whose states are unavailable for feedback), and enhanced - within this work - by forcing, unmatched, additive disturbances. Nonlinear tools are herein employed to demonstrate that the proposed control architecture - based on the high-gain paradigm - achieves closed-loop input-to-state stability with respect to the forcing disturbances, along with global asymptotic convergence towards an attractor which can be rendered as small as desired. Then, owing to the established input-to-state stability property, a uniformly bounded control action is additionally embedded within the control architecture. The additional unit, designed following the sliding-mode paradigm, is aimed at improving the disturbance rejection task, by potentially lowering the required high-gain control expenditure. The second class of systems, denoted by C2, is constituted by minimum-phase, uncertain, nonlinear systems with relative degree greater than one, featuring possibly unbounded, with possibly unbounded derivatives, output-dependent nonlinearities, with matched additive forcing disturbances. To solve the problem of output-feedback, non-adaptive, global robust disturbance rejection for systems within C2, first, an open-loop observer is employed in lieu of a classic dynamic extension adopted in earlier works, as the latter is no longer implementable due to the presence of unknown forcing disturbances. Subsequently, the results derived for C1 are then adapted to C2, to yield an output-feedback dynamic controller providing closed-loop global uniform boundedness, along with asymptotic regulation towards an attractor which can be rendered as small as desired.

Multilayer cloud detection from active–passive observation is vital for numerical weather prediction. In this study, channel selections derived from threshold-based algorithms are embedded as feature-engineering priors into a 1D-CNN, and machine learning (ML) is used to learn latent physical relationships to simplify physical retrievals for operational deployment. The results show that the 1D-CNN achieves a multilayer-cloud probability of detection ($\mathrm{POD}{\mathrm{mul}}$) of 0.620 and a false alarm rate ($\mathrm{FAR}{\mathrm{mul}}$) of 0.240, outperforming the conventional threshold algorithm ($\mathrm{POD}{\mathrm{mul}} = 0.558$, $\mathrm{FAR}{\mathrm{mul}} = 0.369$). These results demonstrate that prior physical knowledge derived from radiative transfer theory can serve as an effective feature-engineering prior. Further experiments show that ML-revealed physical mechanisms can also enhance traditional algorithms. Replacing AGRI channel 12 (C12, centered at $10.8~\mu\mathrm{m}$) with channel 13 (C13, centered at $12.0~\mu\mathrm{m}$) increased $\mathrm{POD}{\mathrm{mul}}$ from 0.558 to 0.609 without materially affecting $\mathrm{FAR}{\mathrm{mul}}$. However, for AHI, substituting the $11.2~\mu\mathrm{m}$ channel with the $12.3~\mu\mathrm{m}$ channel yielded negligible improvement. In addition to spectral response function (SRF) mismatches, a primary contributing factor is the channels' on-orbit radiometric stability. Hence, physics-informed machine-learning methods appear promising for advancing remote-sensing AI, while sensor-specific characteristics must be considered during operational transfer.

Integrated sensing and communications (ISAC) is moving from proof-of-concept demonstrations to system-level deployment in sixth-generation (6G) networks. Because sensing and communication share hardware, spectrum, and waveform resources, ISAC design now involves many tightly coupled choices, including waveform selection, sensing algorithm setup, resource scheduling, and deployment planning. This design space is already too large to manage well through manual tuning or isolated optimizers. This article introduces the Agent Compiler, a large language model (LLM)-enabled compilation layer that translates high-level engineering intent into complete and executable ISAC system configurations. The Agent Compiler works in four stages: intent parsing, task decomposition, policy graph synthesis, and infrastructure mapping. It produces a verifiable intermediate representation called the ISAC Policy Graph (IPG). A runtime engine then deploys the compiled configuration and supports closed-loop adaptation at three levels: fast parameter updates, partial recompilation of affected subgraphs, and full workflow recompilation. The core design principle is strict time-scale separation: the LLM handles slow-loop strategic decisions, while proven algorithms retain real-time control in the fast loop. A UAV-assisted disaster rescue example illustrates the full compilation process. We also discuss open issues, including compilation latency, output reliability, constraint verification, and pipeline security, to guide future research.

Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may generate plausible outputs while remaining difficult to verify under non-determinism, confidentiality constraints, limited context, and weak observability. This paper formulates a bounded verification protocol for adaptive agentic controllers represented by finite symbolic rules, explicit diagnostic predicates, explanation logs, and held-out re-evaluation. The central research question is: when an adaptive agentic controller is represented through finite rules, explicit diagnostic predicates, explanation logs, and held-out re-evaluation, which classes of controller failure can be detected, locally repaired, or rejected without relying on unrestricted human-in-the-loop judgment? The proposed framework treats the controller as a finite revisable object. Diagnostic failures are mapped to predefined rule-level edits, including rule addition, rule deletion, and priority revision. Repaired controllers are then evaluated on held-out simulation seeds or cloned initial states. Experiments in a stylized financially constrained inventory-control benchmark show three outcomes: resource-induced failures that remain non-repairable by one rule edit, partial repairs that are rejected because they violate thresholds or guardrails, and a local one-step repair of an order-volatility failure induced by removing a smoothing rule. The contribution is methodological and provides a simulation-compatible procedure for testing whether specific controller-level failures can be made observable, explainable, locally revisable, and empirically re-tested under controlled conditions.