Papers

As wireless technologies continue to develop and reshape our world, teaching students the fundamental building blocks of RF engineering is paramount. Relatively inexpensive lab equipment now makes teaching concepts such as the Internet-of-Things, beam steering, and MIMO accessible. A new course for students in Electrical and Computer Engineering at Carnegie Mellon University aims to utilize affordable hardware to teach core concepts in RF systems design. This is accomplished through six laboratory exercises, culminating in a live demonstration of RF beam steering technology for students. The course can be run for less than $9,000 in one-time costs and is well-received by students as evidenced by survey data, with lab resources available in an open repository.

The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific information. To address this critical challenge, we propose the Vector Archive Mapping ECAPA (VAM-ECAPA), a novel system designed to enhance feature extraction from short-duration speech. The core of our system is the Transformer-based Vector Archive Mapping with Statistical Pooling (TVAMSP) module, which enriches information-scarce features by mapping them against a learnable Vector Archive of canonical speaker traits. By integrating the TVAMSP module into a strong WavLM+ECAPA-TDNN baseline, our system learns to map sparse features from short segments into robust, discriminative speaker representations. Experiments on the VoxCeleb1 benchmark show that our proposed VAM-ECAPA achieves a highly competitive EER of 8.334% on 1-second test segments, a 54.8% relative error reduction compared to a conventionally-trained baseline.

In this paper, we develop a trust-region framework for understanding the behavior of adaptive moment estimation mechanisms, such as Adam, in stochastic gradient optimization. Specifically, the magnitude of the update step associated with each individual parameter is constrained by a finite-order $p$-moment trust-region, with $p\ge1$. The resulting derivation leads to a family of learning-rate mechanisms based on second-moment estimation and normalized $p$-th-moment estimation. For $p=4$, this involves kurtosis estimation. Subsequent derivations provide a unified interpretation of moment-estimation-based normalization, learning-rate scheduling, momentum as a spectral first-order lowpass regularization, and operator-level spectral-norm normalization within a common trust-region framework. Preliminary experiments on GPT2-124M trained on FineWeb-Edu and TinyStories suggest that the fourth-moment realization provides its greatest benefit when trust-region constraints are weak. As progressively stronger trust-region controls are introduced, the second-moment realization becomes increasingly competitive, often achieving slightly lower validation loss than its corresponding fourth-moment realization.

The Discrete Fourier Transform (DFT), the Discrete Cosine Transform (DCT), and their block-wise variants underpin most deployed image and video codecs. Their effectiveness rests on three properties: their runtime is near-linear (up to a polylogarithmic factor) in the image size, they are exactly invertible, and they carry few to no parameters. We generalize these transforms to dataset-adaptive isometric multilinear bases that keep all three properties at the cost of a polylogarithmic number of parameters, by parameterizing each basis as an isometric tensor network, inspired by quantum many-body theory, and training one shared basis per image dataset with Riemannian optimization. Because the family contains the DFT and the DCT-IV (a variant of the DCT) as exact points, training can start from these transforms, and it improves on its starting point at the compression level it is trained for. We evaluate the bases on natural photographs and line drawings. On photographs, which the cosine basis already fits well, the best trained basis leads the DCT only under aggressive truncation. On Quick Draw line drawings, under a common codec at matched quality, the best trained basis stores each image in about 20% fewer bytes than the 8x8 block cosine transform of the Joint Photographic Experts Group (JPEG) format, not counting the one-off storage of the basis.

Extremely large-scale reconfigurable intelligent surface (XL-RIS)-assisted communication is regarded as a key enabling technology for future 6G networks. However, hybrid-field channel estimation for XL-RIS-assisted systems is challenging due to the high-dimensional cascaded channel and the coexistence of far-field and near-field propagation. In this case, traditional full-dimensional sparse recovery methods require a large cascaded dictionary and suffer from severe computational and storage burdens. To address these challenges, we develop a double-timescale channel estimation framework that decouples sparse dictionary representation and recovery. Then, by exploiting the quasi-static property of the channel at the base station (BS) and RIS side, we propose a Dirichlet kernel-based off-grid dictionary compression (DK-ODC) scheme for sparse representation, which reduces the dimension of the corresponding dictionary as well as mitigates BS-side angular off-grid error. Furthermore, for the dynamic channel at the user equipment (UE) and RIS side, we propose a subspace-aware incremental variational Bayesian learning (SI-VBL) algorithm, which enables incremental learning of sparse channels by exploiting the identified low-dimensional subspace and pruning threshold. Analysis and simulation results confirm that the proposed framework avoids full-dimensional Bayesian recovery and achieves a favorable tradeoff among estimation accuracy, computational complexity, and storage overhead.

Designing feedback controllers that satisfy predefined performance specifications while enforcing hard input constraints is a challenging task. Our work is motivated by the idea that state trajectory data, e.g., obtained from an expert controller, often implicitly encode feasible performance attributes and input limitations. We propose an optimization-based framework that uses state trajectory data to jointly learn: (i) a performance funnel that mimics the transient and steady-state behavior encoded within the observed trajectories, and (ii) a feedback controller that enforces the learned performance specifications under hard input constraints. Unlike imitation learning methods, the proposed approach does not rely on control input data and does not reconstruct an expert policy. Instead, it synthesizes a prescribed performance controller by combining nominal model compensation with a learned state-dependent feedback gain. The resulting synthesis problem is nonconvex, for which we develop a feasibility-driven active-set synthesis procedure. Finally, we establish two complementary guarantees: a semi-global conservative actuator-authority-based certificate for prescribed performance and input satisfaction, and a local data-driven certificate ensuring these properties near sufficiently dense demonstrated trajectories.

Trajectory tracking performance of Uncrewed Aerial Vehicles (UAVs) degrades during an agile high-speed flight due to the depletion of the battery and subsequent loss of maximum available thrust. In applications such as drone racing, this leads to a failure to complete the race due to possible collisions with obstacles. In this paper, we present a novel method for integrating battery and propulsion system models into a Nonlinear Model Predictive Controller (NMPC) framework to enable real-time prediction of the voltage, current, power, and maximum available thrust of the platform. Our proposed approach achieves lower trajectory tracking error as a result of its real-time thrust awareness, and with the help of trajectory replanning, it allows the UAV to fly in time-optimal regime throughout the mission. The accuracy of this proposed model was verified in real-world flight experiments, while the effectiveness of the replanning algorithm was evaluated in simulation. By the end of the battery capacity, compared to an unaware controller, our novel controller achieved a 25% reduction in mean position error without replanning, and an 88 % reduction with replanning.

Path Integral (PI) control is a powerful sampling-based method for stochastic optimal control, but it requires a restrictive coupling between the noise covariance and the control cost matrix that is rarely satisfied in practice, particularly in aerospace and cyber-physical systems. We propose Bound-Optimized Task Choice (BOTC), a framework that optimizes over the entire space of valid approximations, termed tasks, satisfying the PI coupling constraint. We prove that every task provides an upper bound on the true cost-to-go and that BOTC minimizes this bound. We derive a change-of-measure formulation that enables evaluation of all candidate tasks from a single set of Monte Carlo samples, eliminating the need to resample for each candidate task. The resulting optimization is parameterized by a positive semi-definite matrix. Furthermore, we propose a novel Normal-Inverse-Wishart distribution-based importance sampling scheme to improve global optimization. We validate BOTC on a finite-horizon stochastic linear-quadratic regulator problem, demonstrating that it tracks the constrained optimum.

This paper presents a data-driven approach to automatic blind equalization of audio by predicting log-mel spectral features and deriving an inverse filter. The method uses a deep neural network, where a pre-trained model provides semantic embeddings as a backbone, and only a lightweight head is trained. This design is intended to enhance training efficiency and generalization. Trained on both music and speech, the model is robust to noise and reverberation. Objective evaluations confirm its effectiveness, and subjective tests show performance comparable to that of an oracle that uses true log-mel spectral features, indicating that the model accurately estimates the desired characteristics, with remaining limitations attributed to the filtering stage. Overall, the results highlight the potential of the method for real-world audio enhancement applications.

This paper presents an adaptive safety-critical control framework for flight envelope protection (FEP) of hypersonic glide vehicles (HGVs) under model uncertainty. The proposed architecture treats input and state constraints through two complementary but distinct mechanisms. At the input end, an adaptive controller with a calibrated closed-loop reference model (CCRM) is designed to accommodate magnitude-limited control inputs and the effects of actuator saturation. Building on this input-constrained adaptive control architecture, flight envelope state constraints are enforced at the state end by an error-based safety filter (EBSF) based on control barrier functions (CBFs). The EBSF modifies the reference command and adapts the admissible safe set online using the measured mismatch between the reference model and the uncertain plant, thereby preserving forward invariance during transient adaptation. Simulation results for the DLR generic hypersonic glide vehicle 2 (GHGV-2) demonstrate stable, high-performance tracking under magnitude-limited control inputs while maintaining flight envelope constraints in the presence of model uncertainty.

In model predictive control (MPC) with time-varying objectives, predicted signals need to be often incorporated in the cost function, such as prices in energy system operation. These are, however, often difficult to predict from the historical trajectory of these signals alone, as they may depend on other contextual events. We propose LiFT-MPC, an MPC framework that integrates a LiFT (Language-in-the-Loop Feedback Tuning) correction scheme to refine such predictions within the MPC loop. The prediction mechanism is updated online via a control-performance loss function, and we establish a performance guarantee for the resulting closed loop system. Numerical experiments using a realistic example of energy-storage management with real prices and news context to improve predictions, demonstrate an improved economic performance

This paper investigates the validity of the unilateral approximation in near-field non-line-of-sight (NLoS) propagation for large-scale linear antenna arrays. Utilizing multiport communication theory, the study evaluates whether the electromagnetic interaction from the receiver back to the transmitter can be neglected. The analysis examines both discrete arrays with fixed spacing and continuous arrays with fixed aperture as the number of antennas increases. Results show the approximation is asymptotically satisfied on average for both cases. This provides a theoretical foundation for using correlated Rayleigh fading models in physically consistent next-generation wireless systems.

Rapid preliminary design of low-thrust interplanetary rendezvous trajectories requires parameterizations that combine computational efficiency, flexibility, and sufficient solution quality. This work presents a shape-based method in which the heliocentric cylindrical coordinates are parameterized using clamped B-splines. The differential flatness of the low-thrust cylindrical dynamics is exploited to recover the control acceleration algebraically from the shaped trajectory and its derivatives. The clamped B-spline parameterization satisfies the endpoint position and velocity conditions analytically, reducing the original fixed-time, minimum delta-v problem to a finite-dimensional nonlinear program in the free interior B-spline control points. The formulation therefore requires no numerical propagation of the equations of motion; numerical quadrature is used only to evaluate the objective function. Numerical campaigns are conducted for low-thrust rendezvous transfers from Earth to Mars, Mercury, the near-Earth asteroid 1989 ML, and comet Tempel 1, and the results are compared with high-order hodographic shaping. Across the tested fine-grid campaigns and among the finite solutions retained, all B-spline configurations reduce the mean, median, and minimum accumulated velocity increment relative to the hodographic benchmark. In particular, a ten control-point quintic B-spline is identified as a favorable compromise between solution quality and computational efficiency, while higher-dimensional parameterizations are effective for refining selected transfer opportunities.

In this paper, we propose an integrated sensing and communications (ISAC) and vision fusion framework for fine-grained low-altitude target recognition. Specifically, we first utilize ISAC system to estimate the position of the low-altitude target. Then we adjust the working parameters of the Pan-TiltZoom (PTZ) camera based on the estimated target position, such that the camera can capture the image of tiny low-altitude target from several hundred meters away. After obtaining the wireless echo signal and visual image of low-altitude target, we employ the short-time Fourier transform (STFT) to obtain the micro-Doppler (mD) spectrum of the target from wireless echo signal, and design a conditional generative adversarial network (cGAN)-based denoising network to optimize the quality of the mD spectrum. Meanwhile, we employ YOLOv11 to detect the low-altitude target from visual image, and then crop the smallsized feature image of the target from the original image. Next, we design a fine-grained low-altitude target recognition network with MobileViT, which can fuse the optimized mD spectrum and the cropped feature image to distinguish the subcategory of low-altitude target. Moreover, we generate a joint ISAC and vision dataset (JIVD) for low-altitude target monitoring based on AirSim and Wireless InSite, which includes diverse target subcategories, scenarios, and weather conditions. The effectiveness and superiority of the proposed scheme have been demonstrated by simulation results.

We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application. RMAB problems are solved using the Whittle index policy. The goal in RMAB is to maximize the expected cumulative discounted reward maximization. The Whittle index policy maximizes reward, but is not fair among two classes. In this paper, we introduce fairness criteria and study an outcome-fair model for RMAB which allows fairness for jobs and users structurally disadvantaged demographic classes. We formulate an outcome fair stochastic deadline scheduling problem as RMAB, and we develop the outcome fair Whittle index policy. We define a virtual queue mechanism that dynamically enforces long-term completion rate guaranties across demographic groups. We analyze a standard Whittle index policy and the outcome-fair index policy. We demonstrate the performance of our algorithms with numerical examples. We compare policies—Whittle index policy (no fairness), input-fairness Whittle index policy, outcome fair Whittle index policy. We observe that the outcome-fair Whittle index policy provides better fairness among classes compared to other policies. We demonstrate a trade off between fairness and profit. This decreases as the server capacity increases.

The companion of this paper reformulated cascaded second-order (biquad) recursive filtering as a block-tridiagonal linear system and developed two parallel solution algorithms, PH factorization and cyclic reduction, reaching over 600 Megasamples per second on a single SIMD core. This paper scales that framework to multi-core CPUs and GPUs, where a new obstacle appears: the terminal outputs of each signal block group are the initial conditions of the next, so naively distributed groups serialize. The dependency is resolved by superposition – each group's output splits into a zero-state response, computable immediately, and a homogeneous correction applied when the state arrives – and by a divide-and-conquer form of cyclic reduction that exposes both terminal blocks before back substitution, as asynchronous state propagation requires. Two implementations pair the two dominant deployment scenarios with opposite treatments of the dependency. For real-time streaming, a wavefront pipeline realized with TBB flow graphs parallelizes across cascade sections, preserves first-in-first-out order, and achieves 3.95x scaling on six performance cores, about 2.4 Gigasamples per second for a 16th-order filter. For batched processing, a single-kernel GPU implementation carries each group through the entire cascade in registers and parallelizes across groups with a decoupled look-back protocol; a communication-based cost model, comprising a memory roof, a barrier price, and a latency-hiding floor, reduces tuning to two parameters and predicts the measured behavior across two GPU generations. The best kernels reach 38.2 Gigasamples per second for a single second-order section on an RTX~3060, 85% of the memory-bandwidth roof, exceed the strongest published parallel recurrence baseline at every filter order, and remain numerically valid at order 16, where the direct-form baseline fails.

This paper investigates an unmanned aerial vehicle (UAV)-enabled Internet of Things (IoT) architecture that integrates wake-up radio (WuR) and energy harvesting for sustainable device operation. In the proposed system, UAVs transmit radio-frequency (RF) signals that both trigger device activation and replenish stored energy. The IoT device's behavior is modeled as a discrete-time Markov chain, which captures the evolution of its battery level and operational state (asleep or awake), accounting for both energy harvesting and energy consumption. Leveraging stochastic geometry and discrete-time Markov-chain analysis, we develop a comprehensive mathematical framework to assess system performance. We reveal a tradeoff between transmission frequency and energy consumption, and demonstrate that tuning of system parameters, such as UAV density, can significantly improve both energy efficiency and transmission reliability.

Adapting learning-based precoding across different system configurations is challenging due to multiple types of variables and constraints. While large-scale neural networks have been proposed for cross-task adaptation, whether such adaptability requires large models remains unclear. In this paper, we identify a structural property of a class of precoding problems: the subproblems associated with each type of variable in alternative optimization (AO) share a common computational structure across systems when other variables are fixed. This structural consistency enables the reuse of update rules across systems. Based on this observation, we propose a cross-system neural precoder (XNP), where each layer implements AO-inspired update equations, which define the layer-wise input-output mappings. By reusing common update structures and learning only lightweight nonlinear mappings, the XNP enables efficient adaptation across systems only with several thousand trainable parameters. Simulation results show that pre-trained XNPs achieve fast adaptation to new configurations with significantly fewer training samples and epochs than a graph neural network-based baseline. This demonstrates that cross-system adaptability can be achieved by exploiting shared computational structure, rather than relying on large models.

In this work, a direct band-energy estimation approach using finite sampled data under explicit time- and frequency-domain regularity and concentration assumptions is proposed. Standard two-stage methods always estimate the power spectral density and then integrate it over the target band, thereby accumulating error through spectral smearing, leakage, and numerical band integration. Instead, we formulate the band-energy estimation as a finite-sample approximation problem. We then construct a computable direct estimator based on sampled continuous prolate spheroidal wave functions (PSWFs) in a multitaper-type framework, which links continuous-time/frequency assumptions to discrete observations. The estimator is obtained by first constructing a band $L^2$-norm estimator and then squaring it to estimate the band energy. We derive deterministic and non-asymptotic error bounds that explicitly separate four sources of approximation error: time limitation, sampling, band limitation, and finite-term truncation. In addition, several theories are derived to show how the accuracy of the estimation depends on the length, bandwidth, sampling step, time-frequency smoothness, and concentration. We also establish deterministic stability under additive noise, analyze computational complexity, and show that the method admits an efficient multiple-band implementation through offline reuse of PSWF-related computations. Numerical experiments across multiple observation lengths, bands of interest, and noise levels are conducted to show that the proposed approach achieves excellent performance compared to integrated-periodogram-type methods.

Wireless intelligence requires not only large foundation models for network-wide planning and decision-making, but also a compact "cerebellum" for fast and precise physical-layer inference. Unlike the computation-intensive architectures used at upper layers, the physical-layer cerebellum must operate within stringent microsecond-to-millisecond latency constraints. This article presents ScoreFM, a lightweight score-based foundation model designed for this role. ScoreFM learns reusable score functions that characterize the priors of wireless channels, source signals, and structured interference. During inference, these learned priors are embedded into task-specific message-passing algorithms as plug-and-play denoisers, allowing the same compact score networks to support diverse downstream tasks. This design combines the expressive power of score-based generative learning with the efficiency, interpretability, and modularity of model-based inference. Case studies on channel estimation, localization, and blind semantic communication demonstrate the flexibility and effectiveness of ScoreFM. Finally, we discuss future directions and open challenges toward realizing a practical wireless cerebellum.

In high-mobility orthogonal frequency division multiplexing (OFDM) systems, rapid channel variation can make the channel state information (CSI) estimated from pilots inaccurate for data subcarriers, leading to a mismatch with their effective channel. To address this issue, this paper proposes a CSI RefineNet receiver, where the CSI is iteratively refined using soft symbol decisions in a data-aided manner. Specifically, a pilot-driven initialization module is first employed to obtain a coarse CSI estimation and the corresponding symbol posterior probabilities. Based on these posteriors, soft data-aided channel observations are constructed over all subcarriers and fused with the initial CSI to refine the channel estimation. The refined CSI is subsequently fed back to the equalization and detection modules, thereby forming an iterative receiver structure. To improve training stability and fully exploit the refinement capability, a two-stage training strategy is also developed. Simulation results demonstrate that the proposed CSI RefineNet receiver achieves superior BER performance and strong robustness under different velocities, modulation orders, and pilot spacing configurations in high-mobility OFDM systems.

This paper develops an observer-assisted control architecture for 3D trajectory tracking of torpedo-type underactuated AUVs with non-minimum-phase sway/heave dynamics under unknown ocean currents. A three-stage state-current observer provides relative-velocity estimates to a nonlinear feedforward term for dominant current rejection and to an LMI-certified LPV-$\mathcal{H}_\infty$ correction layer. Feedback-linearising cancellation yields a constant input matrix, enabling convex synthesis without pairwise cross terms. A residual-level break-even law shows that the effective surge disturbance depends on current-estimation error, while a singular-perturbation analysis proves local practical uniform ultimate boundedness on the embedded LPV model. REMUS simulations over three trajectories and four current scenarios show 89-96% current-estimation reduction, about 99% translational residual reduction, and RMS tracking-error reduction from 4.04 m to 0.24 m.

Voice conversion (VC) poses a significant threat to biometric security by allowing attackers to impersonate target speakers. In forensic contexts, recovering the source speaker's identity from converted audio is vital for narrowing the field of suspects. To address this, we propose TRIDENT, a retracing framework designed to restore a source speaker's original identity from a converted audio sample. TRIDENT utilizes a three-pronged architecture consisting of a primary extractor and two auxiliary branches. The first auxiliary branch identifies the underlying voice conversion mechanism. This design acknowledges that even if the exact conversion strategy is unknown, a high-performance model adopted by the attacker is typically a derivative or variant of established mainstream ones. The second auxiliary branch extracts a latent representation of the target speaker, facilitating the isolation of target-specific traits from the composite converted audio sample. Finally, the main extractor leverages insights from both auxiliary branches to decouple confounding factors and distill a highly discriminative representation of the source speaker's identity. Experimental results demonstrate that TRIDENT achieves an accuracy as high as 90.99% against 7 state-of-the-art voice conversion methods. Furthermore, TRIDENT maintains robust performance under challenging conditions, including telephony channels, unseen languages, and adaptive scenarios.

Sky-image irradiance studies often compare forecasting systems in which the image encoder, temporal model, fusion block, target definition, and training recipe all change together. We use a narrower protocol: the multimodal forecasting pipeline is fixed, and only the visual backbone is varied. The shared setup keeps preprocessing, clear-sky-index normalization, weather-history encoding, fusion, regression head, loss, optimizer schedule, seed, and chronological split policy unchanged. We compare ConvNeXt, Swin Transformer, VMamba, Spatial Mamba, and MambaVision backbones for 10min-ahead forecasting on Folsom and a strict matched NREL split. Forecast skill is measured against clear-sky-index smart persistence, and temporal-only rows are reported as weather-history diagnostics rather than as the main ranking criterion. On the Folsom strict split, all evaluated visual-backbone runs improve over smart persistence. In the evaluated single-seed strict runs, VMamba Small and Swin Base reach matched Folsom RMSE values of 65.39 W/m^2 and 65.50 W/m^2; the temporal-only diagnostic reaches 69.51 W/m^2. On the 313-sample NREL strict split, smart persistence remains strongest at 17.48 W/m^2, while the lowest visual RMSE is obtained by Swin Tiny at 23.76 W/m^2. These results provide a reproducible encoder comparison under one fixed multimodal operating point rather than establishing architecture-level dominance, statistically resolved ranking, or fully optimized forecasting performance. Code available here: https://github.com/Oshadha345/irradiance_benchmark

Radiomic biomarkers derived from magnetic resonance imaging (MRI) have been widely investigated as non-invasive tools for tumor characterization and prognostic modeling in glioblastoma (GBM). However, their clinical translation remains limited, in part due to sensitivity to tumor segmentation variability. In this study, we systematically investigate the relationship between feature robustness and predictive utility in GBM survival modeling using the University of Pennsylvania Glioblastoma Imaging, Genomics, and Radiomics (UPENN-GBM) cohort. A total of 4,752 radiomic features were obtained from multiparametric MRI across three tumor subregions: enhancing tumor (ET), peritumoral edema (ED), and necrotic core (NC). Feature robustness was quantified using the intraclass correlation coefficient (ICC) based on the automatic and expert-refined segmentation versions. Among features with valid ICC estimates, 48.1% were classified as robust. Survival prediction was evaluated using cross-validation with Coxnet, Random Survival Forest, and Gradient Boosting Survival Analysis models. In this cohort, radiomic feature inclusion showed no consistent improvement over the clinical baseline, and robustness filtering produced no detectable performance gain. Model-selected features were less robust than the overall feature pool, indicating a lack of enrichment for robustness. These findings suggest that robustness alone is not a reliable criterion for feature selection in radiomics-based survival modelling.

Recent Phonetic Foundation Models (PFMs) for Speech-to-IPA transcription rely on Grapheme-to-Phoneme (G2P) labels, but the phoneme labels are not necessarily phonetically faithful. To investigate this issue, we evaluate zero-shot phonetic classification on Chinese aspiration and Japanese moraic nasals. A PFM trained on G2P-labeled data excluding these two languages yields poor accuracy on both tasks, showing that multilingual coverage with discrete IPA tokens is not sufficient for unseen settings. To overcome this limitation, we propose a classification method based on continuous Articulatory Feature (AF) vectors extracted from each frame. This AF-based approach outperforms discrete token-based methods, particularly for rare phones. We further show that it is crucial to adopt the optimal temporal aggregation of AF vectors for the target distinction: single-frame classification is best for aspiration, while segmental classification substantially improves nasal classification.

This paper investigates age-of-information (AoI) aware federated learning over wireless networks with finite speed pinching antennas. In contrast to existing studies that assume an infinitely high antenna moving speed, a practical round based training procedure is considered, where the pinching antenna is repositioned during the local training phase and its feasible movement range depends on the selected devices. This creates a new coupling among device selection, antenna placement, local training time, model uploading time, and AoI evolution. To characterize the impact of antenna moving speed, the rate gain over the fixed antenna and the gap to the infinite speed benchmark are analyzed. Subsequently, an overall AoI minimization problem is formulated under a round latency deadline by jointly optimizing the selected device set and the pinching antenna position. A coalitional game based device selection algorithm is proposed, where finite speed antenna placement is incorporated into the coalition utility evaluation. For antenna placement, the optimal search region is derived by exploiting the mobility constraint and device location span, based on which a branch-and-bound (BnB) algorithm is developed to obtain the global optimum. Simulation results show that the proposed scheme can accelerate learning convergence, reduce the sum AoI, and improve device participation compared with baseline schemes, demonstrating the potential of pinching antennas for enhancing federated learning through flexible spatial reconfiguration.

In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoencoder (MAE) paradigm for large-scale representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals. By integrating convolutional operations with Transformer-based self-attention, MAEConformer effectively captures both local temporal patterns and long-range contextual dependencies in physiological time series. To enhance reconstruction fidelity and representation quality, a multi-resolution short-time Fourier transform (MR-STFT) loss is incorporated alongside the reconstruction objective, enabling the model to jointly learn temporal and spectral characteristics across multiple scales. Modality-specific EEG and HRV MAEConformer models were pretrained on 6,030h and 4,868h of unlabelled recordings, respectively, and subsequently transferred to expert-annotated downstream tasks. Experimental results demonstrate that the learned representations provide strong transferability and data efficiency. In EEG-based hypoxic ischemic encephalopathy (HIE) severity classification, the pretrained MAE-EEG model achieved test AUCs of 97.19% and 96.56% for binary and four-class classification tasks, respectively, outperforming a range of state-of-the-art supervised and self-supervised baselines. On the HRV-based HIE severity classification task, MAE-HRV achieved a test AUC of 82.42%, surpassing both self-supervised Transformer-based and supervised convolutional baselines. These findings demonstrate the effectiveness of MAEConformer for learning robust and transferable representations across multiple physiological modalities.

Screen-shooting poses a significant threat to confidential information protection. While existing screen-shooting watermarking methods enable copyright verification, the copyrighted images carrying the same copyright watermark across different screens often exhibit highly similar and estimable watermark patterns. These shared patterns can be exploited for watermark removal and forgery, a threat we term the multi-screen collusion attack. To mitigate this threat, we propose CoMSMark, a collusion-resistant image-agnostic watermarking framework for multi-screen shooting, which reduces shared residual components across screens to resist multi-screen collusion attacks. Specifically, we incorporate screen ID through a style modulation mechanism, enabling the encoder to generate screen-specific watermark residuals for reliable source attribution. We further introduce a collusion suppression loss that reduces shared residual components and encourages high-entropy predictions for forged samples, improving resistance to collusion attacks. Finally, to enable efficient large-scale distribution, CoMSMark employs an image-agnostic encoding paradigm that generates watermark residuals independently of image content. Extensive experiments demonstrate that CoMSMark effectively resists both collusion-based watermark removal and forgery. It maintains an average watermark accuracy above 90% under removal attacks while keeping forged-watermark accuracy near 50%. Moreover, CoMSMark achieves competitive robustness under diverse screen-shooting conditions, including varying capture distances and angles.

Ocean thermal energy conversion (OTEC) is a zero-carbon technology that harnesses the ocean's thermal gradient to generate electricity. Among OTEC variants, open-cycle OTEC is particularly attractive to island communities, as it can co-generate electricity and freshwater. This paper develops an integrated model that captures both the thermodynamic process of open-cycle OTEC and its operational role in an island microgrid. A two-stage robust scheduling model is formulated for the island microgrid, with a budget uncertainty set to capture the renewable output deviations. The resulting model is solved via an inexact column-and-constraint generation algorithm, which accelerates convergence by permitting inexact solutions of the first-stage problem in early iterations. Numerical experiments demonstrate that open-cycle OTEC can fully substitute for conventional generators on island microgrids and provide more reliable and dispatchable output than volatile renewable sources.