Papers

The high directionality of wave propagation at millimeter-wave (mmWave) carrier frequencies results in only a small number of significant transmission paths between user equipments and the basestation (BS). This sparse nature of wave propagation is revealed in the beamspace domain, which is traditionally obtained by taking the spatial discrete Fourier transform (DFT) across a uniform linear antenna array at the BS, where each DFT output is associated with a distinct beam. In recent years, beamspace processing has emerged as a promising technique to reduce baseband complexity and power consumption in all-digital massive multiuser (MU) multiple-input multiple-output (MIMO) systems operating at mmWave frequencies. However, it remains unclear whether the DFT is the optimal sparsifying transform for finite-dimensional antenna arrays. In this paper, we extend the framework of Zhai et al. for complete dictionary learning via $\ell^4$-norm maximization to the complex case in order to learn new sparsifying transforms. We provide a theoretical foundation for $\ell^4$-norm maximization and propose two suitable learning algorithms. We then utilize these algorithms (i) to assess the optimality of the DFT for sparsifying channel vectors theoretically and via simulations and (ii) to learn improved sparsifying transforms for real-world and synthetically generated channel vectors.

This paper investigates a six-dimensional movable antenna (6DMA)-aided cell-free multi-user multiple-input multiple-output (MIMO) communication system. In this system, each distributed access point (AP) can flexibly adjust its array orientation and antenna positions to adapt to spatial channel variations and enhance communication performance. However, frequent antenna movements and centralized beamforming based on global instantaneous channel state information (CSI) sharing among APs entail extremely high signal processing delay and system overhead, which is difficult to be practically implemented in high-mobility scenarios with short channel coherence time. To address these practical implementation challenges and improve scalability, a two-timescale decentralized optimization framework is proposed in this paper to jointly design the beamformer, antenna positions, and array orientations. In the short timescale, each AP updates its receive beamformer based on local instantaneous CSI and global statistical CSI. In the long timescale, the central processing unit optimizes the antenna positions and array orientations at all APs based on global statistical CSI to maximize the ergodic sum rate of all users. The resulting optimization problem is non-convex and involves highly coupled variables, thus posing significant challenges for obtaining efficient solutions. To address this problem, a constrained stochastic successive convex approximation algorithm is developed. Numerical results demonstrate that the proposed 6DMA-aided cell-free system with decentralized beamforming significantly outperforms other antenna movement schemes with less flexibility and even achieves a performance comparable to that of the centralized beamforming benchmark.

Triangular tethered formation system (TTFS) provide a promising platform for deep space exploration and distributed sensing due to its intrinsic spatial-orientation stability and capability of adjusting distances among node satellites through deployment and retrieval of tethers. However, due to the coupled tether-satellite dynamics and disturbance sensitivity of TTFS, traditional control methods struggle to achieve a balanced trade-off among configuration accuracy requirements, tension constraints, and energy efficiency consumption throughout the deployment process.In this paper, a novel model-reference reinforcement learning control framework is proposed for TTFS. By integrating baseline model-based control with a Soft Actor-Critic (SAC) compensator, the proposed method simultaneously achieves high-precision tracking, fuel efficiency, and compliance with tension limits. A hierarchical training scheme is developed to address the convergence difficulties arising from strongly coupled states in centralized training, while tailored reward functions, reset conditions, and normalization criteria are designed to accelerate training convergence. Closed-loop stability of the overall control law is rigorously proven using Lyapunov methods. Simulation results demonstrate that the proposed controller reduces steady-state tracking errors by over 96% for tethers and 99% for node satellites, while cutting fuel consumption by two orders of magnitude compared with the baseline method. These results validate the effectiveness and stability of the proposed approach for TTFS deployment control.

Modulation effects such as phasers, flangers and chorus effects are heavily used in conjunction with the electric guitar. Machine learning based emulation of analog modulation units has been investigated in recent years, but most methods have either been limited to one class of effect or suffer from a high computational cost or latency compared to canonical digital implementations. Here, we build on previous work and present a framework for modelling flanger, chorus and phaser effects based on differentiable digital signal processing. The model is trained in the time-frequency domain, but at inference operates in the time-domain, requiring zero latency. We investigate the challenges associated with gradient-based optimisation of such effects, and show that low-frequency weighting of loss functions avoids convergence to local minima when learning delay times. We show that when trained against analog effects units, sound output from the model is in some cases perceptually indistinguishable from the reference, but challenges still remain for effects with long delay times and feedback.

The spectral and energy efficiency (SE-EE) trade-off in pinching-antenna systems (PASS) is investigated in this paper. In particular, two practical operating protocols, namely waveguide multiplexing (WM) and waveguide switching (WS), are considered. A multi-objective optimization problem (MOOP) is formulated to jointly optimize the baseband and pinching beamforming for maximizing the achievable SE and EE, which is then converted into a single-objective problem via the {\epsilon}-constraint method. For WM, the problem is decomposed within the alternating-optimization framework, where the baseband beamforming is optimized using the successive convex approximation, and the pinching beamforming is updated through the particle swarm optimization. For WS, due to the time-division transmission and interference-free nature, the pinching beamforming in each time slot is first adjusted to maximize the served user channel gain, followed by the baseband power allocation. Simulation results demonstrate that 1) PASS outperforms conventional antennas by mitigating large-scale path losses; 2) WS leads to a higher maximum achievable EE by activating a single RF chain, whereas WM yields a higher SE upper bound by serving all users concurrently; and 3) increasing the number of users substantially enhances SE under WM, whereas WS shows more pronounced benefits in low-signal-to-noise ratio regimes.

Motivated by single-particle cryo-electron microscopy, multi-reference alignment (MRA) models the task of recovering an unknown signal from multiple noisy observations corrupted by random rotations. The standard approach for computing the maximum likelihood estimator (MLE) is the expectation-maximization (EM) algorithm; however, it often becomes computationally prohibitive, particularly in low signal-to-noise ratio (SNR) settings. We introduce a fast approximate MLE for MRA over the special orthogonal groups $\mathrm{SO}(2)$ and $\mathrm{SO}(3)$ in the low-SNR regime. A low-SNR Taylor expansion of the likelihood reveals a closed-form, non-iterative approximate MLE. We show that this approach yields a consistent estimator in the low-SNR limit and requires substantially lower computational complexity than both EM and invariant-based alternatives. Numerical experiments generated from molecular volumes show that the proposed method provides a favorable accuracy-runtime trade-off, especially in challenging low-SNR regimes, and can serve as an effective initialization for EM.

The sixth generation of mobile networks (6G) can play a central role in shaping a sustainable future, the most compelling contemporary challenge. Connecting the unconnected, reducing carbon emissions of vertical sectors, and allowing heterogeneous types of intelligence (including humans) to safely and constructively interact in complex environments, are only a few of the several challenges that can be supported by 6G. However, this requires a careful design that balances positive and negative impacts of 6G, towards a sustainable and sustainability-enabling technology. This paper presents a holistic view that translates the complex interplay between the 6G enabling effects and the sustainability of 6G by design, into concrete trade-offs and research questions. Starting from today's challenges for society and associated key values, we unfold the dilemma into a set of technical trade-offs, whose solutions span from technological innovations to standardization actions towards applicability.

The passivity index, a quantitative measure of a system's passivity deficiency or excess, has been widely used in stability analysis and control. Existing studies mostly rely on scalar forms of indices, which are restrictive for multi-input, multi-output (MIMO) systems. This paper extends the classical scalar indices to a systematic matrix-valued framework, referred to as passivity matrices. A broad range of classical results in passivity theory can be naturally generalized in this framework. We first show that, under the matrix representation, passivity indices essentially correspond to the curvature of the dissipativity functional under a second-variation interpretation. This result reveals that the intrinsic geometric structure of passivity consists of its directions and intensities, which a scalar index cannot fully capture. For linear time-invariant (LTI) systems, we examine the structural properties of passivity matrices with respect to the Loewner partial order and propose two principled criteria for selecting representative matrices. Compared with conventional scalar indices, the matrix-valued indices capture the passivity coupling among different input-output channels in MIMO systems and provide a more comprehensive description of system passivity. This richer information leads to lower passivation effort and less conservative stability assessment.

The demand for high-resolution, non-invasive imaging continues to drive innovation in magnetic resonance imaging (MRI), but long acquisition times remain a major practical limitation. Although deep learning-based reconstruction methods have enabled accelerated imaging, their predominant supervised paradigm relies on fully-sampled reference data that are difficult to acquire in practice. Self-supervised learning (SSL) has therefore emerged as a promising alternative, among which splitting methods are a widely used strategy. However, most existing splitting-based methods are empirically designed, and a unified theoretical understanding remains limited. In this work, we introduce UNITS (Unified Theory for Splitting-based self-supervision), a general theoretical framework for splitting-based self-supervised MRI reconstruction. Theoretically, we show that the self-supervised risk can be expressed as a weighted supervised risk. Consequently, self-supervision admits the same pointwise Bayes-optimal predictor as supervised learning. We further relate the training residual to the prediction bias, revealing how different sampling mechanisms affect training behavior. UNITS makes a broad class of existing methods interpretable as special cases within a common framework, and provides a general design space through sampling stochasticity and flexible data utilization. Together, these contributions establish UNITS as a theoretical foundation, a practical paradigm, and a benchmark for interpretable, generalizable, and applicable self-supervised MRI reconstruction.

Without requiring operational costs such as cabling and powering while maintaining reconfigurable phase-shift capability, self-sustainable reconfigurable intelligent surfaces (ssRISs) can be deployed in locations inaccessible to conventional relays or base stations, offering a novel approach to enhance wireless coverage. This study assesses the feasibility of ssRIS deployment by analyzing two harvest-and-reflect (HaR) schemes: element-splitting (ES) and time-splitting (TS). We examine how element requirements scale with key system parameters, transmit power, data rate demands, and outage constraints under both line-of-sight (LOS) and non-line-of-sight (NLOS) ssRIS-to-user equipment (UE) channels. Analytical and numerical results reveal distinct feasibility characteristics. The TS scheme demonstrates better channel hardening gain, maintaining stable element requirements across varying outage margins, making it advantageous for indoor deployments with favorable harvesting conditions and moderate data rates. However, TS exhibits an element requirement that exponentially scales to harvesting difficulty and data rate. Conversely, the ES scheme shows only linear growth with harvesting difficulty, providing better feasibility under challenging outdoor scenarios. These findings establish that TS excels in benign environments, prioritizing reliability, while ES is preferable for demanding conditions requiring operational robustness.

This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous transcription and censorship tasks to prevent the exposure of harmful content. Instruction tuning of the LLM to mask hate-related words with specific tokens requires an annotated hate speech dataset, which is limited. We generate text samples using an LLM with the Chain-of-Thought (CoT) prompting technique guided by cultural context and examples and then convert them into speech samples using a text-to-speech (TTS) system. However, some of them contain non-hate speech samples with hate-related words, which degrades the censorship performance. This paper filters the samples which text classification models correctly label as hate content. By adjusting the threshold for the number of correct answer models, we can control the level of hate in the generated dataset, allowing us to train the LLMs through curriculum learning in a gradual manner. Experimental results show that the proposed method achieves a masking accuracy of 58.6% for hate-related words, surpassing previous baselines. We also confirm that the curriculum training contributes to the efficiency of both transcription and censorship tasks.

As wireless networks progress toward sixthgeneration (6G), understanding the spatial distribution of directional beam coverage becomes increasingly important for beam management and link optimization. Multiple-input multipleoutput (MIMO) beam map provides such spatial awareness, yet accurate construction under sparse measurements remains difficult due to incomplete spatial coverage and strong angular variations. This paper presents a tensor decomposition approach for reconstructing MIMO beam map from limited measurements. By transforming measurements from a Cartesian coordinate system into a polar coordinate system, we uncover a matrix-vector outer-product structure associated with different propagation conditions. Specifically, we mathematically demonstrate that the matrix factor, representing beam-space gain, exhibits an intrinsic Toeplitz structure due to the shift-invariant nature of array responses, and the vector factor captures distance-dependent attenuation. Leveraging these structural priors, we formulate a regularized tensor decomposition problem to jointly reconstruct line-of-sight (LOS), reflection, and obstruction propagation conditions. Simulation results confirm that the proposed method significantly enhances data efficiency, achieving a normalized mean square error (NMSE) reduction of over 20% compared to state-of-the-art baselines, even under sparse sampling regimes.

This paper presents a method for estimating significant wave height (Hs) from sparse S_pectral P_oint using a T_ransformer-based approach (SPT). Based on empirical observations that only a minority of spectral points with strong power contribute to wave energy, the proposed SPT effectively integrates geometric and spectral characteristics of ocean surface waves to estimate Hs through multi-dimensional feature representation. The experiment reveals an intriguing phenomenon: the learned features of SPT align well with physical dispersion relations, where the contribution-score map of selected points is concentrated along dispersion curves. Compared to conventional vision networks that process image sequences and full spectra, SPT demonstrates superior performance in Hs regression while consuming significantly fewer computational resources. On a consumer-grade GPU, SPT completes the training of regression model for 1080 sea clutter image sequences within 4 minutes, showcasing its potential to reduce deployment costs for radar wave-measuring systems. The open-source implementation of SPT will be available at https://github.com/joeyee/spt

Generating accurate circuit schematics from high-level natural language descriptions remains a persistent challenge in electronic design automation (EDA), as large language models (LLMs) frequently hallucinate components, violate strict physical constraints, and produce non-machine-readable outputs. To address this, we present CircuitLM, a multi-agent pipeline that translates user prompts into structured, visually interpretable $\texttt{CircuitJSON}$ schematics. The framework mitigates hallucination and ensures physical viability by grounding generation in a curated, embedding-powered component knowledge base through five sequential stages: (i) component identification, (ii) canonical pinout retrieval, (iii) chain-of-thought reasoning, (iv) JSON schematic synthesis, and (v) interactive force-directed visualization. We evaluate the system on a dataset of 100 unique circuit-design prompts using five state-of-the-art LLMs. To systematically assess performance, we deploy a rigorous dual-layered evaluation methodology: a deterministic Electrical Rule Checking (ERC) engine categorizes topological faults by strict severity (Critical, Major, Minor, Warning), while an LLM-as-a-judge meta-evaluator identifies complex, context-aware design flaws that bypass standard rule-based checkers. Ultimately, this work demonstrates how targeted retrieval combined with deterministic and semantic verification can bridge natural language to structurally viable, schematic-ready hardware and safe circuit prototyping. Our code and data are publicly available at https://github.com/Khandakar227/CircuitLM.

Increasing concerns over the scarcity of inertia have motivated the procurement of inertia as an ancillary service (AS). Despite numerous academic and practical efforts, there remains a lack of consensus regarding the definition and treatment of inertia service in market operations, particularly the specification of inertia variables and the separation between synchronous inertia (SI) from synchronous generators and virtual inertia (VI) from inverter-based resources. To address these issues, this paper proposes a power-oriented (P-oriented) definition based on inertial response, which establishes conceptual consistency between SI and VI and makes the inertia service commensurable with other ASs. This definition explicitly incorporates both positive and negative inertial responses during frequency drop events. We then formulate a security-constrained economic dispatch framework based on this P-oriented definition and demonstrate its practical effectiveness through simulations. Case studies on a modified IEEE 30-bus system show that the proposed bidirectional service definition ensures price signals that reflect the economic value of inertial provision.

The environmental and target-related information inherently carried in wireless signals, such as channel state information (CSI), has brought increasing attention to integrated sensing and communication (ISAC). However, it also raises pressing concerns about privacy leakage through eavesdropping. While existing efforts have attempted to mitigate this issue, they either fail to account for the needs of legitimate communication and sensing or rely on hardware with high cost. To overcome these limitations, we propose PrivISAC, a plug-and-play, low-cost solution that leverages reconfigurable intelligent surface (RIS) to protect user privacy while preserving ISAC performance. At its core, PrivISAC constructs a small set of RIS configurations from two beamforming vectors per RIS row and randomly activates one configuration per time slot to perturb CSI and mask sensitive sensing information from eavesdroppers. The two vectors are designed to maintain similar communication-direction responses while creating distinct sensing-direction responses, thereby preserving transmission quality and masking sensitive CSI from eavesdroppers. To enable legitimate sensing, we introduce a time-domain masking and demasking method that maps CSI samples to their RIS configurations and removes configuration-induced discrepancies. We implement PrivISAC on commodity wireless devices and conduct extensive experiments. Results show that PrivISAC provides effective privacy protection while preserving high-quality communication and sensing performance for legitimate receivers.

Federated learning (FL) and federated distillation (FD) are distributed learning paradigms that train UE models with enhanced privacy, each offering different trade-offs between noise robustness and learning speed. To mitigate their respective weaknesses, we propose a hybrid federated learning (HFL) framework in which each user equipment (UE) transmits either gradients or logits, and the base station (BS) selects the per-round weights of FL and FD updates. We derive convergence of HFL framework and introduce two methods to exploit degrees of freedom (DoF) in HFL, which are (i) adaptive UE clustering via Jenks optimization and (ii) adaptive weight selection via a damped Newton method. Numerical results show that HFL achieves superior test accuracy at low SNR when both DoF are exploited.

Bioelectrical properties of cells such as relative permittivity, conductivity, and characteristic time constants vary significantly between healthy and malignant cells across different frequencies. These distinctions provide a promising foundation for diagnostic and classification applications. This study systematically reviewed 20 scholarly articles to compile 535 datasets of quantitative bioelectric parameters in the kHz-MHz frequency range and evaluated their utility in predictive modeling. Three supervised machine learning algorithms- Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) were implemented and tuned using key hyperparameters to assess classification performance. In the second stage, a physics informed framework was incorporated to derive additional dielectric descriptors such as imaginary permittivity, loss tangent and charge relaxation time from the measured parameters. Random Forest based feature importance analysis was employed to identify the most discriminative dielectric parameters influencing the classification process. The results indicate that dielectric loss related parameters, particularly imaginary permittivity and conductivity, contribute significantly to the classification of cellular states. While the incorporation of physics-derived features improves model interpretability and reduces overfitting tendencies, the overall classification accuracy remains comparable to models trained using primary dielectric descriptors. The proposed approach highlights the potential of physics-informed machine learning for improving the analysis of dielectric spectroscopy data in the biomedical diagnostics.

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent recognition improvements due to residual distortions and mismatches with the latent space of the ASR encoder. In this letter, we introduce a complementary strategy termed latent-level enhancement, where distorted representations are refined during ASR inference. Specifically, we propose a plug-and-play Flow Matching Refinement module (FM-Refiner) that operates on the output latents of a pretrained CTC-based ASR encoder. Trained to map imperfect latents-either directly from noisy inputs or from enhanced-but-imperfect speech-toward their clean counterparts, the FM-Refiner is applied only at inference, without fine-tuning ASR parameters. Experiments show that FM-Refiner consistently reduces word error rate, both when directly applied to noisy inputs and when combined with conventional SE front-ends. These results demonstrate that latent-level refinement via flow matching provides a lightweight and effective complement to existing SE approaches for robust ASR.

We present a systematic study of multimodal emotion recognition using the EAV dataset, investigating whether complex attention mechanisms improve performance on small datasets. We implement three model categories: baseline transformers (M1), novel factorized attention mechanisms (M2), and improved CNN baselines (M3). Our experiments show that sophisticated attention mechanisms consistently underperform on small datasets. M2 models achieved 5 to 13 percentage points below baselines due to overfitting and destruction of pretrained features. In contrast, simple domain-appropriate modifications proved effective: adding delta MFCCs to the audio CNN improved accuracy from 61.9% to 65.56% (+3.66pp), while frequency-domain features for EEG achieved 67.62% (+7.62pp over the paper baseline). Our vision transformer baseline (M1) reached 75.30%, exceeding the paper's ViViT result (74.5%) through domain-specific pretraining, and vision delta features achieved 72.68% (+1.28pp over the paper CNN). These findings demonstrate that for small-scale emotion recognition, domain knowledge and proper implementation outperform architectural complexity.

Speech-based detection of cognitive impairment offers a scalable, non-invasive screening, yet algorithmic bias across demographic and linguistic subgroups remains critically underexplored. We present the first comprehensive fairness analysis framework for speech-based multi-class cognitive impairment detection, systematically evaluating bias mitigation across architectures, and demographic subgroups. We developed two transformer-based architectures, SpeechCARE-AGF and Whisper-LWF-LoRA, on the multilingual NIA PREPARE Challenge dataset. Unlike prior work that typically examines single mitigation techniques, we compared pre-processing, in-processing, and post-processing approaches, assessing fairness via Equality of Opportunity and Equalized Odds across gender, age, education, and language. Both models achieved strong performance (F1: SpeechCARE-AGF 70.87, Whisper-LWF-LoRA 71.46) but exhibited substantial fairness disparities. Adults >=80 showed lower sensitivity versus younger groups; Spanish speakers demonstrated reduced TPR versus English speakers. Mitigation effectiveness varied by architecture: oversampling improved SpeechCARE-AGF for older adults (80+ TPR: 46.19%=>49.97%) but minimally affected Whisper-LWF-LoRA. This study addresses a critical healthcare AI gap by demonstrating that architectural design fundamentally shapes bias patterns and mitigation effectiveness. Adaptive fusion mechanisms enable flexible responses to data interventions, while frequency reweighting offers robust improvements across architectures. Our findings establish that fairness interventions must be tailored to both model architecture and demographic characteristics, providing a systematic framework for developing equitable speech-based screening tools essential for reducing diagnostic disparities in cognitive healthcare.

Congenital Heart Disease (CHD) remains a significant global health concern affecting approximately 1% of births worldwide. Phonocardiography has emerged as a supplementary tool to diagnose CHD cost-effectively. However, the performance of these diagnostic models highly depends on the quality of the phonocardiography, thus, noise reduction is particularly critical. Supervised UNet effectively improves noise reduction capabilities, but limited clean data hinders its application. The complex time-frequency characteristics of phonocardiography further complicate finding the balance between effectively removing noise and preserving pathological features. In this study, we proposed a self-supervised phonocardiography noise reduction model based on Noise2Noise to enable training without clean data. Augmentation and contrastive learning are applied to enhance its performance. We obtained an average SNR of 12.98 dB after filtering under 10~dB of hospital noise. Classification sensitivity after filtering was improved from 27% to 88%, indicating its promising pathological feature retention capabilities in practical noisy environments.

In this paper, we propose a high-efficiency deep joint source-channel coding (JSCC) method for video transmission based on conditional coding with asymmetric context. The conditional coding-based neural video compression requires to predict the encoding and decoding conditions from the same context which includes the same reconstructed frames. However in JSCC schemes which fall into pseudo-analog transmission, the encoder cannot infer the same reconstructed frames as the decoder even a pipeline of the simulated transmission is constructed at the encoder. In the proposed method, without such a pipeline, we guide and design neural networks to learn encoding and decoding conditions from asymmetric contexts. Additionally, we introduce feature propagation, which allows intermediate features to be independently propagated at the encoder and decoder and help to generate conditions, enabling the framework to greatly leverage temporal correlation while mitigating the problem of error accumulation. To further exploit the performance of the proposed transmission framework, we implement content-adaptive coding which achieves variable bandwidth transmission using entropy models and masking mechanisms. Experimental results demonstrate that our method outperforms existing deep video transmission frameworks in terms of performance and effectively mitigates the error accumulation. By mitigating the error accumulation, our schemes can reduce the frequency of inserting intra-frame coding modes, further enhancing performance.

This paper presents a large language model (LLM)-based framework that adapts and fine-tunes compact LLMs for detecting cyberattacks on transformer current differential relays (TCDRs), which can otherwise cause false tripping of critical power transformers. The core idea is to textualize multivariate time-series current measurements from TCDRs, across phases and input/output sides, into structured natural-language prompts that are then processed by compact, locally deployable LLMs. Using this representation, we fine-tune DistilBERT, GPT-2, and DistilBERT+LoRA to distinguish cyberattacks from genuine fault-induced disturbances while preserving relay dependability. The proposed framework is evaluated against a broad set of state-of-the-art machine learning and deep learning baselines under nominal conditions, complex cyberattack scenarios, and measurement noise. Our results show that LLM-based detectors achieve competitive or superior cyberattack detection performance, with DistilBERT detecting up to 97.62% of attacks while maintaining perfect fault detection accuracy. Additional evaluations demonstrate robustness to prompt formulation variations, resilience under combined time-synchronization and false-data injection attacks, and stable performance under realistic measurement noise levels. The attention mechanisms of LLMs further enable intrinsic interpretability by highlighting the most influential time-phase regions of relay measurements. These results demonstrate that compact LLMs provide a practical, interpretable, and robust solution for enhancing cyberattack detection in modern digital substations. We provide the full dataset used in this study for reproducibility.

The integration of multicarrier modulation and multiple-input-multiple-output (MIMO) is critical for reliable transmission of wireless signals in complex environments, which significantly improve spectrum efficiency. Existing studies have shown that popular orthogonal time frequency space (OTFS) and affine frequency division multiplexing (AFDM) offer significant advantages over orthogonal frequency division multiplexing (OFDM) in uncoded doubly selective channels. However, it remains uncertain whether these benefits extend to coded systems. Meanwhile, the information-theoretic limit analysis of coded MIMO multicarrier systems and the corresponding low-complexity receiver design remain unclear. To overcome these challenges, this paper proposes a multi-slot cross-domain memory approximate message passing (MS-CD-MAMP) receiver as well as develops its information-theoretic (i.e., achievable rate) limit and optimal coding principle for MIMO-multicarrier modulation (e.g., OFDM, OTFS, and AFDM) systems. The proposed MS-CD-MAMP receiver can exploit not only the time domain channel sparsity for low complexity but also the corresponding symbol domain constellation constraints for performance enhancement. Meanwhile, limited by the high-dimensional complex state evolution (SE), a simplified single-input single-output variational SE is proposed to derive the achievable rate of MS-CD-MAMP and the optimal coding principle with the goal of maximizing the achievable rate. Numerical results show that coded MIMO-OFDM/OTFS/AFDM with MS-CD-MAMP achieve the same maximum achievable rate in doubly selective channels, whose finite-length performance with practical optimized low-density parity-check (LDPC) codes is only 0.5 $\sim$ 1.8 dB away from the associated theoretical limit, and has 0.8 $\sim$ 4.4 dB gain over the well-designed point-to-point LDPC codes.

Radar sensing has emerged in recent years as a promising solution for unobtrusive and continuous in-home gait monitoring. This study evaluates whether a unified processing framework can be applied to radar-based spatiotemporal gait analysis independent of radar modality. The framework is validated using collocated impulse-radio ultra-wideband (IR-UWB) and frequency-modulated continuous-wave (FMCW) radars under identical processing settings, without modality-specific tuning, during repeated overground walking trials with 10 healthy participants. A modality-independent approach for automatic walking-segment identification is also introduced to ensure fair and reproducible modality performance assessment. Clinically relevant spatiotemporal gait parameters, including stride time, stride length, walking speed, swing time, and stance time, extracted from each modality were compared against gold-standard motion capture reference estimates. Across all parameters, both radar modalities achieved comparably high mean estimation accuracy in the range of 85-98%, with inter-modality differences remaining below 4.1%, resulting in highly overlapping accuracy distributions. Correlation and Bland-Altman analyses revealed minimal bias, comparable limits of agreement, and strong agreement with reference estimates, while intraclass correlation analysis demonstrated high consistency between radar modalities. These findings indicate that no practically meaningful performance differences arise from radar modality when using a shared processing framework, supporting the feasibility of radar-agnostic gait analysis systems.

This paper introduces a fuzzy reinforcement learning framework, Enhanced-FQL($\lambda$), that integrates novel Fuzzified Eligibility Traces (FET) and Segmented Experience Replay (SER) into fuzzy Q-learning with the Fuzzified Bellman Equation (FBE) for continuous control. The proposed approach employs an interpretable fuzzy rule base instead of complex neural architectures, while maintaining competitive performance through two key innovations: a fuzzified Bellman equation with eligibility traces for stable multi-step credit assignment, and a memory-efficient segment-based experience replay mechanism for enhanced sample efficiency. Theoretical analysis proves the proposed method convergence under standard assumptions. On the Cart–Pole benchmark, Enhanced-FQL($\lambda$) improves sample efficiency and reduces variance relative to $n$-step fuzzy TD and fuzzy SARSA($\lambda$), while remaining competitive with the tested DDPG baseline. These results support the proposed framework as an interpretable and computationally compact alternative for moderate-scale continuous control problems.

Large-scale neural recording with high spatio-temporal resolution is essential for understanding information processing in brain, yet current neural interfaces fall far short of comprehensively capturing brain activity due to extremely high neuronal density and limited scalability. Although recent advances have miniaturized neural probes and increased channel density, fundamental design constraints still prevent dramatic scaling of simultaneously recorded channels. To address this limitation, we introduce a novel electro-optic sensor that directly converts ultra-low-amplitude neural electrical signals into optical signals with high signal-to-noise ratio. By leveraging the ultra-high bandwidth and intrinsic multiplexing capability of light, this approach offers a scalable path toward massively parallel neural recording beyond the limits of traditional electrical interfaces. The sensor integrates an on-chip photonic microresonator with a graphene layer, enabling direct detection of neural signals without genetically encoded optical indicators or tissue modification, making it suitable for human translation. Neural signals are locally transduced into amplified optical modulations and transmitted through on-chip waveguides, enabling interference-free recording without bulky electromagnetic shielding. Arrays of wavelength-selective sensors can be multiplexed on a single bus waveguide using wavelength-division multiplexing (WDM), greatly improving scalability while maintaining a minimal footprint to reduce tissue damage. We demonstrate detection of evoked neural signals as small as 25 $\mu$V with 3 dB SNR from mouse brain tissue and show multiplexed recording from 10 sensors on a single waveguide. These results establish a proof-of-concept for optically multiplexed neural recording and point toward scalable, high-density neural interfaces for neurological research and clinical applications.

Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed and degraded audio, requiring the reversal of both production effects and real-world degradations. We present the inaugural MSR Challenge, which features objective evaluation on studio-produced mixtures using Multi-Mel-SNR, Zimtohrli, and FAD-CLAP, alongside subjective evaluation on real-world degraded recordings. Five teams participated in the challenge. The winning system achieved 4.46 dB Multi-Mel-SNR and 3.47 MOS-Overall, corresponding to relative improvements of 91% and 18% over the second-place system, respectively. Per-stem analysis reveals substantial variation in restoration difficulty across instruments, with bass averaging 4.59 dB across all teams, while percussion averages only 0.29 dB. The dataset, evaluation protocols, and baselines are available at https://msrchallenge.com/.

This paper presents a batteryless wireless communication node for the Internet of Things, powered entirely by ambient light and capable of receiving data through visible light communication. A solar panel serves dual functions as an energy harvester and an optical antenna, capturing modulated signals from LED light sources. A lightweight analog front-end filters and digitizes the signals for an 8-bit low-power processor, which manages the system's operational states based on stored energy levels. The main processor is selectively activated to minimize energy consumption. Data reception is synchronized with the harvester's open-circuit phase, reducing interference and improving signal quality. The prototype reliably decodes 32-bit VLC frames at 800\,Herz, consuming less than 2.8\,mJ, and maintains sleep-mode power below 30\,uW.