Papers

Automated sleep stage classification based on single-channel EEG is a promising pathway to large-scale sleep monitoring outside the polysomnographic lab. This paper proposes SleepEffFormer TAS, an efficient and interpretable system that consists of a four-stride-block 1D CNN feature extractor, a two-layer pre-normalization Transformer encoder, and a non-parametric Transition-Aware Smoothing (TAS) layer that suppresses physiologically unrealistic transitions between predicted stages. When tested on the Sleep-EDF Expanded dataset using 78 all-night EEG recordings from the Fpz-Cz channel with a subject-wise held-out split, the proposed model achieves 83.9% accuracy, a 78.9% macro F1-score, and a Cohen's kappa of 0.765 with approximately 367K learnable parameters. This performance is comparable to AttnSleep while using 3-5 times fewer parameters. Ablation studies show that the Transformer encoder improves macro F1 by 6.6 percentage points over a CNN-based system, while the TAS layer provides an additional 1.8 percentage point improvement without introducing any trainable parameters. Weighted loss is also critical for improving classification of the minority N1 sleep stage. Attention maps generated by the proposed model reveal physiologically sensible sleep-stage-related EEG features.

Freezing of gait (FoG) is one of the most debilitating episodic motor symptoms of Parkinson's disease (PD). FoG detection from wrist worn inertial signals poses challenging problems such as extreme data class imbalance (only 12-18% of signal windows are FoG), low frequency postural instabilities alongside diagnostically crucial 3-8 Hz rhythmic tremors, and the need for subject independent generalisation. To address these, this paper presents WaveFoG, a novel wavelet gated Transformer architecture that combines multi scale representations from discrete wavelet transform (DWT) with a dual branch encoder. A 1D CNN captures local gait texture, and a Transformer captures global temporal context. They are fused via a sigmoid gating fusion layer that modulates the encoder output based on the DWT sub-band descriptors. Trained with focal loss and evaluated on the public Kaggle TLVMC FoG Prediction dataset under subject independent grouped ten fold cross validation (SI-CV), WaveFoG achieves a mean F1-score of 0.875 +/- 0.017 and AUPRC of 0.833 +/- 0.020, exceeding single branch baselines (1D CNN, Bi-LSTM, and vanilla Transformer) by up to 5.4 pp on F1. Temporal saliency maps highlight temporal patterns that are consistent with reported characteristics of FoG onset. The source code of this project is available at: https://github.com/Shihabul-Shuvo/WaveFoG

Omnimodal large language models (Omni-LLMs) integrate audio, video, and text, yet remain vulnerable to cross-modal hallucinations, where one modality improperly influences predictions about another. Existing training-free decoders modulate modality influence through perturbation or relevance weighting, but do not assess predictive compatibility within the joint audio-visual branch. Because joint-branch discrepancies may indicate either harmful interference or useful complementarity, reliable intervention requires assessing both discrepancy magnitude and actionability. To this end, we propose Conflict-Aware Decoding (CAD), a training-free framework comprising Potential Conflict Magnitude Estimation (PCME) and Conflict Actionability Assessment (CAA). PCME quantifies potential conflict using audio-video disagreement and the deviation of the joint prediction from a relevance-weighted unimodal reference. CAA then applies Dempster-Shafer reliability discounting to task-space answer relations, using query relevance and answer decisiveness to determine whether intervention is warranted. When an actionable conflict is identified, CAD selectively reallocates decoding weight from the joint branch to the unimodal branches. Experiments on CMM, AVHBench, WorldSense, and VideoMME show that CAD consistently outperforms the base decoder and competitive training-free methods across multiple audio-visual backbones. On Qwen2.5-Omni-7B, CAD improves overall accuracy by 14.1 and 8.0 percentage points on CMM and AVHBench, respectively, without model retraining.

In this work, we derive the Cramér-Rao bound for joint Delay-doppler estimation with multi-carrier waveforms

General audio comprehension now covers speech, sound, and music over durations from seconds to hours, driven by large audio-language models (LALMs) that are increasingly omni-modal. Yet the benchmarks that test them still rely on clips of seconds, where scores saturate and models converge; recent long-form efforts extend duration but evaluate long audio much as short clips are. We introduce LongAudioSpan, a benchmark that spans both duration and depth: it pairs audio from 10 minutes to over 2 hours with 3,240 questions across three cognitive levels, namely perception, understanding, and reasoning. Two paths supply the questions, differing in how question content is sourced and how ground truth is obtained. Native QA extracts questions from the audio's content, posing each as a multiple-choice item and an open-ended one graded by detailed rubrics. Anchor QA instead injects ground truth, planting acoustic anchors into the audio and building a perception-to-reasoning chain scored only to the first error. A fully automated pipeline constructs every item through structured captioning, QA generation, and adversarial critic feedback. Evaluating 12 LALMs on LongAudioSpan, we find the hard part comes before reasoning: distilling a few relevant facts from a long, redundant signal. This difficulty grows with audio length and falls hardest on perception, especially temporal grounding. LongAudioSpan is available at https://huggingface.co/datasets/holvan/LongAudioSpan.

Recently, neural directional filtering (NDF) enables reconstruction of a virtual directional microphone (VDM) with a desired directivity pattern, accurately rendering multi-source scenes by preserving spatial cues. In strongly reverberant environments, spatial cues become perceptually difficult to distinguish, limiting NDF-based spatial sound capture. This paper addresses this limitation with three contributions: First, we propose a neural dereverberation and directional filtering (NDDF) approach to reconstruct dereverberated VDM signals. Second, NDDF is implemented with discriminatively trained and generative adversarial network (GAN)-based models, compared with cascaded dereverberation and directional-filtering baselines. Experimental results indicate that the NDDF consistently surpasses the cascaded baselines. Additionally, the GAN-based NDDF outperforms the discriminative variant when addressing a high-order VDM target. Third, we introduce a method for directivity pattern estimation that relies solely on the input and output signals. This method is suitable for signal-mapping-based spatial filtering, which synthesizes the output signal directly without explicit filtering or masking.

A joint communication and control (JCC) framework is proposed, where a base station (BS) simultaneously serves multiple communication users (CUs) and controls a physical plant in a closed loop. In the downlink, BS-generated control inputs are transmitted to and recovered at the plant, with wireless actuation distortion incorporated into the plant-state evolution. In the uplink, the plant state is reported to the BS and tracked by a Kalman filter (KF) for subsequent control-input generation. To characterize long-term control performance under communication-control interference, finite- and infinite-horizon linear quadratic Gaussian (LQG) costs are derived, directly linking beamforming design to plant-state evolution. JCC beamforming problems are then formulated for vector- and scalar-valued control inputs to minimize the infinite-horizon LQG cost subject to per-user communication signal-to-interference-plus-noise ratio (SINR) requirements. For the vector case, a second-order cone programming (SOCP)-based successive convex approximation method is developed for the resulting nonconvex problem. For the scalar case, a closed-form infinite-horizon LQG cost is derived, and the communication-control Pareto boundary is optimally characterized by an SOCP-based bisection method. Its optimality follows from the strict monotonicity of the scalar control cost with respect to the control SINR. Numerical results show that the derived costs closely match Monte Carlo simulations, the KF accurately tracks the ground-truth plant-state trajectory, and the proposed methods consistently outperform the zero-forcing benchmark. This confirms the benefit of balancing communication-control interference, especially with limited spatial degrees of freedom (DoFs).

We propose a novel framework for decomposing nonstationary spiky signals. Unlike classical adaptive non-harmonic models, which represent signals as amplitude- and frequency-modulated (AM–FM) oscillations, the proposed model is designed for signals whose dominant structures are highly localized, impulsive, or spike-like, and contains physiological variability, which is challenging to be modeled as AM–FM representations. Representative examples include electrocardiogram (ECG) complexes, epileptic electroencephalogram (EEG) transients, and other pulse-like physiological signals. We first introduce a fixed-waveform model for repetitive spiky structures and then extend it to accommodate cycle-to-cycle waveform variability. The resulting algorithm, termed Spiky Shape-adaptive Mode Decomposition (SSAMD), estimates waveforms in the Fourier coefficient domain. Fourier coefficients are first estimated via local regression and then regularized by exploiting their low-dimensional manifold structure. Specifically, we combine a PCA-based parametrization with an entropy regularization acting on the singular-value spectrum of the coefficient matrix, promoting morphological consistency while preserving structured waveform variability. The proposed framework is flexible and overcomes the limitations of existing models. We validate the method on synthetic and real biomedical signals, including ECG with atrial fibrillation, epileptic EEG, and trans-abdominal maternal ECG. Experimental results demonstrate effective denoising, waveform tracking, decomposition, and segmentation, while preserving physiologically meaningful morphological variations.

We provide an overview of the problem of jointly testing two hypotheses and estimating a parameter of the selected model. Such problems arise in a variety of applications. First, we present a conceptual introduction to suboptimal and optimal procedures for joint detection and estimation. A numerical example illustrates the advantages of the optimal procedure over suboptimal ones. Next, we discuss how more advanced problem formulations affect the presented results. The second part covers joint detection and estimation in a sequential framework. First, we provide an introduction to sequential analysis through sequential hypothesis testing. Then, suboptimal and optimal sequential procedures for joint detection and estimation are discussed. A numerical example shows the advantages of optimal sequential procedures over suboptimal and optimal sequential procedures with a fixed number of samples. The third part discusses open problems and future research directions in joint detection and estimation.

Large language model (LLM)-based audio-visual speech recognition (AVSR) systems are robust under noise. Contrastive decoding (CD), originally introduced to stabilize LLM generation by contrasting a weaker model against a stronger one at inference time, adjusts predictions without additional training. In this work, we apply CD to AVSR by contrasting audio-only conditioning with full audio-visual conditioning within the same underlying model. However, using a fixed contrastive strength introduces a trade-off across noise levels: stronger intervention helps under severe noise but may over-correct reliable predictions in clean conditions. We propose reliability-aware scaling of CD for AVSR. Instead of using a fixed strength, we adaptively modulate the contrastive influence at each token based on reliability signals derived from attention dynamics and inter-model predictive divergence. Experiments on LRS3 show consistent improvements across clean and low-SNR conditions.

Designing machine learning algorithms for wireless resource management is labour-intensive: the architecture, the loss function and the training recipe are all specified by hand. We demonstrate that this design layer can be surrendered to an autonomous agent in its entirety. We adopt the autoresearch protocol, in which an AI coding agent edits a training script, runs a fixed-budget experiment, and retains or discards the change according to a single immutable metric. We grant the agent authority over the architecture family, the input representation, the output parameterization, the loss function and the task-sampling law, and set it a target chosen for its difficulty: sum-least-percentile-rate power control across a multicell network. The formulation targets cell-edge throughput and is non-convex, non-smooth and strongly NP-hard away from its max-min vertex. Safeguards render the results trustworthy: a hash-pinned evaluator, an enforced inference contract and a pre-registered falsifier per experiment. In eighty-one unattended experiments over twenty-six hours, the agent reached $99.5\%$ of a converged minorization-maximization reference in one fixed-cost inference pass, at roughly $600\times$ lower inference cost, closing $94\%$ of the gap from its first working architecture, with one parameter set serving every network size and percentile target. It recovered provable structure rather than tuned constants: the output parameterization it discovered reproduces the exact max-min-optimal allocation at the minimum percentile, for every value of the trained weights.

Decentralized wireless collectives including vehicular swarms, IoT clusters, and edge AI networks require communication protocols that maintain robustness under dynamic topologies and heterogeneous link quality. While Random Linear Network Coding (RLNC) provides algebraic resilience against packet erasures, its performance degrades significantly when peers exhibit diverse channel conditions. This paper presents Adaptive Peer Clustering with Hierarchical RLNC (APC-RLNC), a system that dynamically groups peers by exponentially weighted moving average (EWMA) reliability metrics and applies multi-tier network coding within and across clusters. We formalize the clustering optimization problem, derive closed-form decoding probability bounds for Markov erasure channels, and prove O(sqrt(T)) regret for online reconfiguration under the Follow-the-Regularized-Leader (FTRL) framework. Our implementation includes both a high-fidelity network simulator and a proof-of-concept testbed deployment on Jetson Nano edge devices. Evaluation across diverse scenarios including high-mobility vehicular networks, burst-error channels, and adversarial interference demonstrates 5.2-9.8 percentage-point packet delivery ratio (PDR) improvements, 10-23% latency reductions, and up to 30% higher node retention compared to state-of-the-art baselines. The system exhibits linear scalability to 500+ nodes and maintains real-time reconfiguration overhead below 3%. APC-RLNC establishes adaptive clustering as a foundational primitive for AI-native 6G wireless systems.

In medical imaging, it is common to use learned perceptual image patch similarity (LPIPS) to compare images semantically in feature space. Although backbones pretrained on natural images are widely used for LPIPS computation, B-mode ultrasound images possess distinct speckle patterns and acoustic-specific image statistics that are fundamentally different from natural images and even from other images in radiology. Consequently, we propose that domain-specific models are needed to measure perceptual similarity in ultrasound data, a finding which is not necessarily the case for other imaging modalities. We compare LPIPS metrics across downstream tasks like classification, segmentation and reconstruction using natural image, medical generalist and ultrasound backbone models and show that selection of LPIPS backbone is a non-trivial design choice. In particular, the ultrasound backbone models were more correlated with downstream performance of supervised models than classical and natural image models, and optimization of the LPIPS loss with an ultrasound backbone achieved a strong balance between reconstruction quality and realism. Our code is available at https://github.com/talg2324/UltraPIPS and introduces the UltraPIPS library, a set of LPIPS metrics based on the open-source foundation models analyzed in this paper.

Datacenters consume many megawatts of power, and regularly encounter scenarios that require modulating their power draw. These scenarios include datacenter infrastructure failures, power grid failures, grid services, and more, spanning a diverse range of requirements in terms of the power magnitude, the scope of the reduction, the notice time, and other dimensions. To address these scenarios, we have built Slasher, a general system for modulating the power of \azure datacenters to handle scenarios ranging from individual racks to regional multi-datacenter grid events. Slasher coordinates datacenter resources with the goal of meeting power targets while minimizing negative impact on hosted workloads. In this paper, we review the main power modulation scenarios, characterize the power reduction levers using data from production cloud datacenters, describe Slasher's system architecture, and formulate the cloud datacenter power modulation control problem. We also develop a high-fidelity datacenter simulator and propose a workload impact model, using them to design and evaluate power control algorithms.

Redirecting unmanned aerial vehicles (UAVs) from their intended mission trajectories has been an active area of research. However, existing UAV redirection attacks lack reliability, precision, and covertness for a targeted diversion. They primarily rely on physical capture, communication hijacking, or sensor spoofing. Yet, physical interception is costly, offers only a single opportunity for success, and poses a high risk of collateral damage; network-based attacks demand deep technical expertise and access to encrypted communication channels; and sensor spoofing techniques typically fall short in achieving the accuracy and robustness required to steer a UAV toward a specified target. Consequently, we propose Phantom Navigator, a UAV redirection attack to mislead drones to a designated spoofing target, covertly and precisely. Our approach combines offline pre-redirection reachability analysis, which provides high-fidelity estimates of achievable redirect ranges, with an online closed-loop, stealthy execution layer that ensures successful redirection in practice. Based on this approach, we build a physical attack platform equipped with a LiDAR–camera detection, tracking, and spoofing stack that performs real-time identification, pose estimation, and computation of targeted spoofing signals to covertly and accurately redirect victim UAVs to a designated location. We demonstrate the effectiveness of our redirection methodology and the attack implementation in real-world case studies.

Conversational systems, such as duplex speech language models (SLMs), still lack a streaming, accurate, and empathetic memory system as their soul. We introduce VoiceMem, a simple memory architecture with a parallel informational left brain, an emotional right brain, and streaming memory I/O mechanisms. We further build a complete pipeline for memory-aware SLM training, long-horizon evaluation, and decoupled deployment with interchangeable memory backends. Experiments and real-world deployment show three advantages: i) Accuracy: under top-5 retrieval, the left brain outperforms classical systems such as Mem0 at top-200 by nearly 30 points; ii) Emotional & Personal: the right brain, with short- and long-horizon affective attribution and dual-node persona modeling, achieves state-of-the-art performance across three persona benchmarks and improves the aggregate score by 4.29 points over the previous best system; and iii) Real-Time & Cheap: VoiceMem completes retrieval in 134 ms, well within standard VAD latency, adding no extra conversational delay while maintaining high accuracy and low cost. These results show that VoiceMem provides a practical memory foundation for real-time, personalized, and emotionally aware speech interaction.

Wearable electrocardiogram (ECG) and photoplethysmogram (PPG) sensors are complementary but individually fragile: motion artifact, poor contact, and sensor dropout can degrade one or both signals. Fusion strategies that assume both modalities are equally trustworthy can become less reliable than a single clean modality under degradation. We present CardioFusion-AI, a framework whose signal-processing front end, including R-peak and systolic-peak detection, an Orphanidou-type signal-quality index, and beat-by-beat pulse transit time estimation, is validated on 53 real intensive-care recordings (848 windows; heart-rate mean absolute error 1.61 bpm for ECG and 2.78 bpm for PPG) and a real annotated fetal ECG database (R-peak F1 0.89-0.98). We then conduct a controlled synthetic degradation study comparing eight ECG-PPG fusion strategies across six degradation regimes spanning graded corruption and complete modality loss, using five independent training seeds. Attention fusion achieved the lowest descriptive overall error (1.66+/-0.43 bpm). Both adaptive gates reallocated weight toward the healthy modality under complete modality loss, but showed near-zero correlation between gate weight and signal quality under graded degradation (r = 0.10-0.24). Signal-quality conditioning produced a specific improvement under missing-PPG conditions (1.56+/-0.59 bpm), approaching the 1.48 bpm unimodal ceiling. With only five training seeds, no pairwise comparison survives Holm-corrected significance testing; effect sizes and confidence intervals are therefore reported. These results indicate that modality availability and modality quality are functionally distinct problems for adaptive fusion.

Wireless multipath propagation, beamforming, and polarization are central concepts in radio systems, but they are difficult to observe directly because radio-frequency fields are invisible to humans. This paper presents an augmented-reality visualization system that turns phase-coherent WiFi channel measurements from the ESPARGOS antenna array into a live camera overlay. The system estimates a two-dimensional beamspace representation, registers it with the optical camera view, and overlays the resulting angular spectrum onto the physical scene. Additional visual layers show relative path delay and polarization, the latter computed using Jones calculus from channel measurements captured from two separate antenna feeds. The result is an intuitive “WiFi camera” for science communication, teaching, and experimental debugging, while all displayed quantities remain directly derived from measured channel data.

Air traffic control procedures are executed through spoken exchanges between controllers and pilots. These interactions are essential to the safety of air transportation: failures in their execution can create severe operational hazards, as evidenced by past fatal accidents. Assessing whether an instruction has been followed requires relating what was said to the aircraft concerned, its state, and the obligations that pilots must meet. We present a runtime verification framework that monitors such procedures by checking controller-pilot exchanges, surveillance data, and onboard observations. The framework parses radio communications into events linked to the entities they concern and merges them with surveillance and onboard observations into a time-stamped trace. The ICAO-derived obligations as formalized as temporal formulas with explicit time bounds and evaluated over execution traces. Every violation is reported along with the breached obligations and the observations that support the verdict. With real traffic, the complete pipeline reaches an F1 of 0.85 against blind human-annotated violations; in 1,495 synthetic situations derived from two public corpora, the monitor logic returns the expected verdict in every case. In two historical accidents reconstructed from official investigation reports, the monitor identifies the same procedural deviations documented by the investigators.

Driver behavior is heterogeneous, context-dependent, and changes over time, and these properties shape the traffic phenomena we observe. Most models, however, fix in advance which behavioral variables interact and how. Behavior outside that form is absorbed as noise, while models flexible enough to capture it tend to lose interpretability. We introduce a quantum-inspired representation of driver behavior that combines properties usually treated separately or in part: it is continuous, probabilistic, context-dependent, history-dependent, and represents interactions among behavioral variables as learned from data. Each driver is encoded as an evolving density matrix, providing a unified representation of behavioral uncertainty, temporal evolution, and context-dependent behavioral variation. Trained without supervision on the I-24 MOTION dataset, the framework recovers three interpretable driving profiles representing three regimes: free flow, transition, and congestion. The profiles capture the behavioral range of the data and the smooth transitions drivers make between regimes as conditions change. The same representation also reproduces known macroscopic phenomena, aligning with the fundamental diagram and reproducing hysteresis loops. We also show how the representation supports practical use: it supplies context-dependent parameters to classical car-following models, and gives an autonomous vehicle a live behavioral read of the surrounding drivers with a short-horizon forecast of their motion. The framework points toward models of traffic that are interpretable and trustworthy by construction. We release an open-source toolkit on GitHub (https://github.com/mselayan/quantum-driver-representation) spanning data processing, training, inference, and analysis.

This paper proposes a maximum-likelihood (ML) framework for estimating nonlinear frequency-selective channels in orthogonal frequency-division multiplexing (OFDM) communication systems. The nonlinear distortions are modeled using a Discrete Cosine Transform (DCT)-based representation, which results in a well-conditioned estimation problem with favorable convergence properties. The proposed method combines a compact parameterization with low computational complexity, enabling fast adaptation and efficient real-time implementation. Numerical results show that the proposed channel estimation can be used for multiple nonlinear compensation methods and achieve near-ideal BER performance with very limited training overhead. This performance is maintained down to approximately 15 dB SNR in the presence of both amplitude and phase nonlinearities, and down to -10 dB when only amplitude distortions are present.

Cough acoustics are promising for non-invasive tuberculosis (TB) screening, yet whether machine learning (ML) models capture disease-related acoustics or artifacts of data collection remains unresolved. We evaluated the cross-dataset generalizability of classical ML and deep learning (DL) cough-based TB classifiers across three independent datasets. Despite moderate within-dataset performance (ROC-AUC up to $0.755 \pm 0.056$), both pipelines fail to generalize, with external performance frequently below 0.6, indicating a possible limitation of the data. We further observed audio representations are organized by recording device and dataset rather than TB status, predicted TB probability tracks country-level prevalence in CODA, and device mismatch degrades transfer while device-diverse training improves it. Additionally, a clinical-variable baseline generalizes more consistently (ROC-AUC $0.655 - 0.711$), indicating acquisition-specific variability is a stronger driver of poor generalizability than population shift. High within-dataset performance is not enough. External validation is essential before cough-based TB models are clinically ready.

Coupled feedback networks are often monitored channel by channel even though cross-channel paths alter both stability margins and transmitted disturbances. We study identification of a structured feedback matrix L_t = Phi diag(gamma_t) in an output-only setting: no commanded, probing, or reference input exists – only temporally separated outputs and the scheduling gains gamma_t are observed, while the coupling response Phi and the clearing-window inputs are not. Identification rests jointly on the persistent excitation of the observed pre-window output and on two structural features separating coupling from confounds: the known time variation of the gains, which modulates the closed-loop response in a predictable pattern, and a partial-reversal moment by which a known fraction of transient displacement is corrected in a subsequent window. We give a hierarchy of results: exact local identification of the coupling under a Jacobian rank condition on the gain regimes; a first-order interaction estimator whose identification strength is the minimum eigenvalue of the residualized interaction information matrix (provably unidentified under constant gains); and a characterization of the estimand as a resolvent sensitivity – the right object for screening transmitted disturbances and a first-stage input to spectral-margin recovery – with sqrt(T) asymptotics for the first-order estimator, a cross-identification theorem mapping each varying gain to exactly identified resolvent rows and columns, and bootstrap validity under consistent selection; the implemented heuristic's empirical coverage (90% at nominal 95%) quantifies the remaining gap. Simulations verify sharpness of the rank condition and quantify benchmark failures under confounding. A case study on leveraged-fund rebalancing feedback, where daily fund disclosures play the role of the known gains, illustrates the method on real data.

A variety of tasks require sampling from unnormalized Boltzmann distributions supported on manifolds. Building upon the foundations of adjoint matching and adjoint Schrödinger bridge sampling, this paper provides a theoretically justified method, through the lens of stochastic optimal control, to address this problem on smooth, compact, path-connected embedded Riemannian manifolds. As an element of novelty compared to existing literature, feasibility is enforced at the level of the state space, meaning the controlled diffusion is defined intrinsically on the curved space. Empirical validations are provided for several physics applications.

Mission-adaptive low-Earth-orbit (LEO) satellite networks with integrated sensing and communication (ISAC) must retarget radio resources as operator goals change. To enable this adaptation from flexible operator language, we develop a generative-AI-enabled radio-orchestration framework in which a large language model (LLM) maps each mission into a structured policy comprising communication, sensing, and fairness weights, mandatory quality-of-service thresholds, power-allocation guidance, and solver initialization. Deterministic validation and physical-layer optimization then enforce feasibility and realize the policy through beam, power, and reconfigurable intelligent surface (RIS) configuration. This mixed-timescale design uses generative AI for semantic adaptation at the mission timescale while retaining conventional wireless optimization at the faster channel timescale. We compare zero-shot (LLM-ZS) and in-context (LLM-ICL) operation on familiar and held-out compositional missions. On held-out instructions, LLM-ZS and LLM-ICL achieve $91.7\%$ and $94.4\%$ priority-order accuracy, respectively, with ICL mainly improving numerical calibration. Their downstream radio-performance difference is statistically unresolved because both usually recover the hard constraints that determine admissible actions. Accordingly, LLM-ZS is the low-context default, while LLM-ICL is useful for semantically difficult missions requiring finer calibration. Explicit alternating optimization preserves the qualitative ordering when active beams and RIS phases are optimized directly. The results show how generative AI can enhance next-generation radio orchestration without replacing feasibility-critical physical-layer optimization.

Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global models. In this paper, we propose pFedMARL, a novel approach leveraging Multi-Agent Reinforcement Learning (MARL) with Twin Delayed Deep Deterministic Policy Gradient (TD3) to dynamically adapt aggregation strategies in FL settings. Our method employs a server-side agent adjusting client contributions to optimize global model robustness and client-side agents balancing global and local updates to personalize models effectively without pre-training. We demonstrate superior performance of pFedMARL for training a semi-supervised audio spectrogram transformer, matching or outperforming FedAvg, Ditto, and local training approaches across multiple non-IID scenarios and in the presence of adversarial clients. Our results indicate that pFedMARL actively improves accuracy, robustness, and fairness, making it suitable for real-world deployments.

Secure real-time grid operation requires fast AC optimal power flow (AC-OPF) tools that stay accurate and feasible as operating conditions and topology change. Learning-based methods have advanced, but most are trained per system or per topology, and delivering an operating point that satisfies every operational limit remains challenging. This paper proposes UNION, a unified graph-based AC-OPF framework for heterogeneous systems and topology-varying operation. UNION proposes a shared graph encoder, a scalar-gated aggregation with explicit consensus correction, and a sparse-aware differentiable implicit layer embedding the AC power-flow equations. The remaining inequalities are handled by primal-dual training and the deterministic restoration layer. A single model trained jointly across seven systems, including a real-world 4,492-bus Korean transmission grid, attains a 1.23% mean objective gap and satisfies every operational limit on 99.56% of test instances. It sustains this under zero-shot $N-1$ contingencies, i.e., line and generator outages, and over five days of time-varying Korean topologies; it retains full snapshot coverage at a 2.51% gap under lightweight online fine-tuning. UNION pre-restoration inference takes 55$-$58 ms per instance on the three largest systems, and 108$-$114 ms including restoration. These results indicate that one jointly trained, physics-consistent model can support real-time AC-OPF across heterogeneous systems and evolving topologies.

Due to their importance, traction control and anti-lock braking systems have become standard equipment in modern vehicles. However, accurate models of tire dynamics are often difficult to obtain and usually include nonlinearities, making their use in control systems challenging. This paper describes a traction control system based on model predictive control and Koopman operator theory, which aims to approximate nonlinear systems with linear ones through a state space transformation. A linear model predictive controller based on the Koopman predictor is compared to a standard nonlinear model predictive controller. Experiments in a high-fidelity vehicle dynamics simulation environment show a comparable reference tracking performance of the two controllers, with a reduced execution time for the proposed Koopman operator-based algorithm, both on a standard PC and embedded hardware.

The variability of photovoltaic (PV) generation poses significant challenges to the reliable and efficient operation of grid-connected microgrids. Accurate PV output power forecasting and efficient energy scheduling strategies are essential not only for optimizing PV system operation but also for improving the overall performance and reliability of the system. This study proposes a long short-term memory (LSTM)-based PV power forecasting model integrated with a multi-objective scheduling framework for a grid-connected PV-battery energy storage system (BESS). The proposed approach enables detailed performance monitoring and assessment by quantifying how PV forecast accuracy influences key operational metrics, including PV self-consumption ratio, grid energy cost, grid injection, and battery utilization. Three forecasting scenarios (perfect forecast, persistence model, and LSTM-based forecast) are compared to evaluate their impact on system performance and operational reliability. Results show that the LSTM-based forecast reduces root mean squared error (RMSE) by 6% compared with the persistence model, increases the PV self-consumption ratio from 78.1% to 84.5%, and reduces grid injections by 82%. The analysis also highlights trade-offs, as higher battery throughput associated with improved performance may contribute to accelerated aging. These findings demonstrate the importance of accurate PV forecasting in improving system performance and ensuring reliable operation. Future work will focus on probabilistic forecasting to properly quantify uncertainties, incorporate load prediction, and develop smart control strategies that allow grid-support functionalities from the PV side.

Semi-blind channel estimation offers an attractive tradeoff between pilot overhead and estimation accuracy in large-scale wireless systems. However, reliable channel acquisition becomes particularly challenging in highly dynamic environments such as non-terrestrial networks (NTNs), where rapidly varying channels and high system dimensionality significantly degrade the performance of conventional covariance-based estimators due to sampling noise. In this paper, we propose a robust semi-blind channel estimation framework for multi-user uplink systems operating in NTN systems. The proposed approach introduces an optimally regularized least-squares formulation that balances training-based information and blind subspace structure. By exploiting the spiked covariance model within a random matrix theory (RMT) framework, we derive a closed-form characterization of the resulting channel mean-squared error and obtain an analytically tractable design of the optimal regularization parameter. The resulting estimator is computationally efficient and particularly well suited to high-dimensional regimes. Simulation results under realistic Third Generation Partnership Project (3GPP) NTN channel models demonstrate substantial performance improvements over conventional semi-blind and training-based estimators.