Papers

Deep learning-based AMC methods have achieved remarkable performance, but their practical deployment remains constrained by the high cost of labeled data. Although self-supervised learning (SSL) reduces the reliance on labels, existing SSL-based AMC methods often rely on task-agnostic pretext objectives misaligned with modulation classification, leading to representations entangled with nuisance factors such as symbol, channel, and noise. In this paper, we identify intra-instance modulation consistency as a task-aware structural prior, whereby different temporal segments of the same signal may differ in waveform while preserving the same modulation type, thus providing a principled cue for task-aligned self-supervision. Based on this prior, we propose Mod-CL, a Modulation consistency-based Contrastive Learning framework that constructs positive pairs from different temporal segments of the same signal instance, to encourage the model to learn shared modulation information while suppressing nuisance variations. We further develop a contrastive objective tailored to Mod-CL, which jointly exploits temporal segmentation and data augmentation to pull together views sharing the same modulation semantics while avoiding supervisory conflicts within each signal instance. Extensive experiments on RadioML datasets show that Mod-CL consistently outperforms strong baselines, especially in low-label regimes, achieving substantial improvements in linear probing accuracy.

Automated analysis of building facades from street-level imagery has great potential for urban analytics, energy assessment, and emergency planning. However, it requires reasoning over spatially arranged elements rather than solely isolated detections. In this work, we model each facade as a graph over window/door detections with a vertical prior on edges. Additionally, we introduce GATA2Floor, a multi-head Graph Attention v2 (GATv2) based model that predicts the global floor count of a building and, via learnable cross-attention queries, softly assigns elements to latent floor slots, yielding interpretable outputs and robustness to irregular designs. To mitigate the lack of labeled datasets, we demonstrate that the proposed graph-based reasoning can be applied without annotations by leveraging a lightweight label-free proposal mechanism based on self-supervised features and vision-language scoring. Our approach demonstrates the value of graph-attention-based relational reasoning for facade understanding.

The accurate recovery of constituent-level optical properties from integrating sphere measurements is a central analytical challenge in pharmaceutical analysis, food science, and biomedical diagnostics. Neural network autoencoders can extract spectrally resolved absorption and scattering coefficients for each constituent without prior knowledge, but their fully connected encoders bind learned features to absolute wavelength indices, causing accuracy loss under spectrometer calibration drift or hardware exchange. This work introduces the Bin Latent Transformer (BiLT)-Autoencoder, in which the dense encoder is replaced by a cross-attention scanner: 16 learnable probe vectors query a convolutional feature map, aggregating morphological spectral information independently of absolute wavelength position. A physics-constrained linear decoder with enforced absorption/scattering separation and a three-phase curriculum augmentation strategy complete the architecture. On a liquid phantom benchmark (intralipid and two ink absorbers; 496 samples), the model achieves $R^2 = 0.979$ and $0.975$ for $\mu_a(\lambda)$ and $\mu_s'(\lambda)$, respectively, on held-out test spectra, maintaining $R^2 > 0.90$ for $\mu_a$ and $R^2 \approx 0.99$ for $\mu_s'$ across the full tested shift range of $\pm 10$ spectral bands. The model generalises to a simulated spectrometer with a broader instrument line shape (${\approx}24$nm FWHM) without retraining, retaining $R^2 \approx 0.96$ and $0.974$ for the two channels. Attention map analysis reveals a physically interpretable two-component probe strategy: sparse anchor probes at absorption-edge wavelengths combined with a diffuse, SNR-driven ensemble at the high-transmittance long-wavelength region, which recruits additional probes dynamically under noise to provide implicit spectral averaging.

Ray tracing (RT) has emerged as a key tool for propagation channel modeling and network planning. Conventional RT is based on electromagnetic (EM) wave theory and its application relies on detailed mesh-based environment representations and material properties. In realistic environments, limited environmental geometry and material uncertainties hinder its scalability to complex scenarios. In this paper, we propose a novel physics aware neural RT surrogate named PointNeRT to address these limitations. The proposed model directly takes point clouds as environmental input, and efficiently reconstruct multipath without explicitly constructing mesh models or manually defining EM interaction rules. PointNeRT adopts a hop-by-hop modeling strategy guided by physical interaction constraints. It supports sequential prediction of multipath propagation and power attenuation. Numerical results and experiments demonstrate that the proposed method implicitly captures surface normal characteristics and EM material effects. It further achieves robust generalization in mobility scenarios and provides a physics-guided neural modeling of multipath propagation.

Continued progress towards energy-neutral Internet of Things (IoT) nodes expose the wireless communication link as the dominant energy bottleneck. While low-power wide-area network (LPWAN) technologies achieve long-range communication with multiple years of battery life, their active radios hinder reaching full energy neutrality. Long-range backscatter communication emerged as a key enabler, reaching one to three order of magnitude lower power consumption. New advancements leverage concepts from active radio systems such as chirp spread spectrum (CSS) modulation and integrate them on a low-power backscatter tag. This paper presents a comprehensive survey of long-range backscatter communication, using a bottom-up analysis spanning system topologies, hardware architecture, modulation techniques and medium access. Backscatter communication requires different topologies compared to active radios to reach longer communication distances. Different hardware architectures support backscattering a modulated signal with differing complexity, power consumption and spectral efficiency. At the physical layer binary switch-based modulation are well known and provide an easy form of modulation while chirp spread spectrum (CSS)-based modulation gain traction due to their robustness. Medium Access Control (MAC) techniques are examined with a focus on synchronization, concurrency and lightweight feedback mechanisms requiring low-power, low-complexity hardware. Building on these established solutions the paper evaluates the feasibility of long-range backscatter communication in different energy-neutral Internet of Things (IoT) applications. Starting from the available energy budget, harvested through solar, radio frequency (RF) or capacitive harvesting, feasible hardware, modulation and Medium Access Control (MAC) solutions are explored.

This paper presents a novel position control strategy for a single-link flexible manipulator, tailored for applications where precise position must be achieved within strict time constraints. To accomplish this objective, firstly, a nested non-singular terminal sliding mode controller is designed for the system, enabling precise and robust control. Furthermore, a fixed-time sliding mode observer is designed to estimate unmeasured system states accurately in a fixed time, thereby enabling closed-loop control implementation. A stability analysis is presented to guarantee the robustness and efficacy of the proposed composite control algorithm. The effectiveness of the proposed fixed-time controller is demonstrated through numerical simulation on accuracy, stability, and convergence speed. The proposed controller's performance is also compared with that of other state-of-the-art control schemes. The proposed controller is further validated through experiments conducted on a real hardware setup.

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the behavioral integrity verification (BIV) problem: a typed set comparison between declared and actual capabilities over a shared taxonomy that bridges code, instructions, and metadata. The BIV framework instantiates this comparison by pairing deterministic code analysis with LLM-assisted capability extraction. The resulting structured evidence supports three downstream analyses: deviation taxonomy, root-cause classification, and malicious-skill detection. On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap: 80.0% of skills deviate from declared behavior, with four novel compound-threat categories surfaced. Root-cause classification finds that deviations are mostly oversight, not malice: 81.1% trace to developer oversight and 18.9% to adversarial intent, with 5.0% of skills carrying predicted multi-stage attack chains. On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.946, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.

This work describes and assesses different methods for estimating the time-of-arrival (TOA) of impact-induced waves in isotropic plate-like structures. The methods considered include threshold crossing (TC), continuous wavelet transform (CWT), short/long term average (SLA), modified energy ratio (MER), and the Akaike information criterion (AIC). Their advantages, limitations, and sensitivities to method-specific parameters are systematically investigated. The assessment is based on synthetic data from transient finite element simulations that are experimentally calibrated with respect to excitation and dispersion characteristics. Wave propagation is monitored using piezoceramic patch sensors bonded to the plate surface, and robustness is evaluated for impacts of varying positions and force profiles, including noise-contaminated sensor signals in order to account for practically relevant measurement conditions. The results show that the methods are capable of detecting the fundamental Lamb wave modes, with nearly all capturing both the symmetric and anti-symmetric mode arrivals under noise-free conditions. In particular, noise primarily impairs the detection of the earliest symmetric-mode arrivals, while meaningful anti-symmetric-mode TOA-estimates can still be obtained by suitable preprocessing or time-frequency analysis. Besides, new contributions to the assessed TOA-estimation methods include a frequency-domain threshold crossing within the CWT framework that improves both robustness and accuracy of TOA-estimation, and the consideration of local minima in the AIC that proves effective for detecting the TOA of the fundamental symmetric mode. Beyond these findings, the research provides practical guidelines and insights into the specific characteristics of each assessed method, supporting accurate and reliable TOA-estimation for applications such as impact localization.

Unsupervised segmentation of pulmonary pathologies in CT remains an open challenge due to the absence of annotated multi pathology cohorts and the failure of existing diffusion-based methods to exploit the quantitative Hounsfield Unit (HU) signal that physically distinguishes tissue classes. To address this, we propose DiffSegLung,a framework that introduces Diffusion Radiomic Distillation, in which handcrafted radiomic descriptors serve as a physics grounded teacher to shape the bottleneck of a 3D diffusion U-Net via a contrastive objective, transferring pathology discriminative structure into the learned representation without any annotations. At inference, the teacher is discarded and multitimestep bottleneck features are clustered by a Gaussian Mixture Model with HU-guided label assignment, followed by Sobel Diffusion Fusion for boundary refinement. Evaluated on 190 expert annotated axial slices drawn from four heterogeneous CT cohorts, Diff-SegLung improves segmentation across all four pathology classes over unsupervised baselines and improves generation fidelity over prior CT diffusion models.

Accurate spatio-temporal cellular traffic analysis is fundamental to the reliable operation of modern mobile networks, as it underpins load forecasting for congestion avoidance and missing-data imputation for continuity despite transmission errors. While deeply connected, forecasting and imputation have historically evolved as separate sub-fields. Existing models are typically task-specific, decouple temporal and spatial modeling, and rely on cascaded designs that accumulate errors and latency. Meanwhile, adapting pre-trained LLMs for this domain often leaves spatial structure under-guided and tends to overfit on limited data. To bridge these gaps, we propose U-STS-LLM, a unified framework built on a partially frozen spatio-temporally attentive (PFSTA) LLM backbone. A Dynamic Spatio-Temporal Attention Bias Generator synthesizes a persistent functional graph with transient nodal states to steer attention, while a lightweight parallel branch yields a stable local estimate fused via a Gated Adaptive Fusion, confining the LLM to residual correction. Trained under a unified multi-task objective, the model attains state-of-the-art results with low trainable-parameter overhead. Extensive experiments on real-world cellular traffic datasets demonstrate the effectiveness and transferability of U-STS-LLM, achieving average RMSE improvements of 23.7% over the strongest baselines in forecasting and 13.1% in imputation, with further gains exceeding 33% in zero-shot transfer to unseen network regions.

We propose a Byzantine-resilient federated conformal prediction (FCP) method that leverages partial model sharing, where only a subset of model parameters is exchanged each round. Unlike existing robust FCP approaches that primarily harden the calibration stage, our method protects both the federated training and conformal calibration phases. During training, partial sharing inherently restricts the attack surface and attenuates poisoned updates while reducing communication. During calibration, clients compress their non-conformity scores into histogram-based characterization vectors, enabling the server to detect Byzantine clients via distance-based maliciousness scores and to estimate the conformal quantile using only benign contributors. Experiments across diverse Byzantine attack scenarios show that the proposed method achieves closer-to-nominal coverage with substantially tighter prediction intervals than standard FCP, establishing a robust and communication-efficient approach to federated uncertainty quantification.

Affine frequency division multiplexing (AFDM) has emerged as a promising modulation scheme for doubly selective channels, but its canonical continuous-time realization, referred to herein as piecewise continuous AFDM (PC-AFDM), has been observed to exhibit high out-of-band emission (OOBE) whose mechanism has not been analytically characterized. This paper shows that the underlying cause is frequency wrapping, which introduces internal envelope jumps between AFDM sampling instants and generates a high-frequency spectral tail distinct from ordinary block truncation. To eliminate these discontinuities without altering the inverse discrete affine Fourier transform (IDAFT) output sequence, we propose stepped frequency division multiplexing (SFDM). In SFDM, the instantaneous frequency is kept constant at the midpoint of the wrapped chirp within each sampling interval, while the phase is continuously accumulated across interval boundaries. We prove that, under continuous phase accumulation and without additional phase correction, the midpoint choice is the unique sample-preserving choice for arbitrary chirp-rate parameter. The resulting waveform is continuous within each AFDM block, reduces OOBE, and preserves the standard AFDM modulation matrix, guard-interval structure, and receiver processing. Moreover, under fractional-delay propagation, SFDM mitigates the receiver sensitivity that arises when delayed sampling points fall near wrapping-induced discontinuities in PC-AFDM. Numerical results verify the theoretical tail coefficients, demonstrate OOBE reduction, and show improved receiver robustness in the high-percentile and worst-case regimes. These findings establish SFDM as a spectrally cleaner and more reliable physical layer for AFDM systems.

Graph processing systems are essential for analyzing large-scale data with complex relationships, yet most existing frameworks rely on statically provisioned clusters, resulting in poor elasticity and inefficient resource utilization under dynamic workloads. Serverless computing offers automatic scaling and fine-grained billing, but existing serverless graph systems suffer from performance limitations due to inefficient state management and high communication overhead through external storage. We present GraphFlash, a fast and elastic graph processing framework built on serverless infrastructure. GraphFlash adopts a subgraph-centric programming model and leverages shared external storage for coordination and communication, enabling stateless, fine-grained function execution. It supports two execution modes: rotating mode for resource-constrained environments and pinned mode for higher performance when resources are sufficient. To address serverless limitations, GraphFlash introduces system-level optimizations, including partition-aware key aggregation, intra-function partition co-location, and superstep-aware activation. Across multiple graph algorithms and datasets, GraphFlash outperforms existing serverless-compatible systems by up to 127x in execution time and reduces resource consumption by up to 98% under higher-resource configurations, while matching the performance of traditional distributed frameworks on large workloads. Even with limited resources, it achieves up to 48x speedup and 99.97% cost reduction over prior serverless solutions, demonstrating that GraphFlash makes serverless graph processing practical and performant.

We unify the discrete Fourier transform (DFT), discrete cosine transform (DCT), Walsh-Hadamard, Haar wavelet, Karhunen-Loève transform (KLT), and several others along with their continuous counterparts (Fourier transform, Fourier series, spherical harmonics, fractional Fourier transform) under one representation-theoretic principle: each is the eigenbasis of every covariance invariant under a specific finite or compact group, with columns constructed from the irreducible matrix elements of the group via the Peter-Weyl theorem. The unification rests on the Algebraic Diversity (AD) framework, which identifies the matched group of a covariance as the foundational object of second-order signal processing. The data-dependent KLT emerges as the trivial-matched-group limit; classical transforms emerge as the cyclic, dihedral, elementary Abelian, iterated wreath, and hybrid wreath cases, with composition rules for direct, wreath, and semidirect products. The dihedral case is split by action: the Hartley basis is the matched transform of the dihedral group on the $M$-cycle (symmetric circulants), while the DCT belongs to the dihedral group on the even-reflected extension, with the finite-window AR(1) covariance an approximation to that class. A polynomial-time algorithm, the DAD-CAD relaxation cast as a double-commutator generalized eigenvalue problem, discovers the matched group of any empirical covariance without expert judgment, with noise-aware variants via the commutativity residual $\delta$ and algebraic coloring index $\alpha$. The fractional Fourier transform is treated as the metaplectic $SO(2)$ case, and a structural principle relates matched group size inversely to transform resolution. Modern applications (massive-MIMO, graph neural networks, transformer attention, 3D vision, brain connectivity, single-cell genomics, quantum informatics) are sketched with their matched groups.

Modern low-field magnetic resonance imaging (MRI) technology offers a compelling alternative to standard high-field MRI, with portable, low-cost systems. However, its clinical utility is limited by a low Signal-to-Noise Ratio (SNR), which hampers diagnostic image quality. A common approach to increase SNR is through repetitive signal acquisitions, known as NEX, but this results in excessively long scan durations. Although recent work has introduced methods to accelerate MRI scans through k-space sampling optimization, the NEX dimension remains unexploited; typically, a single sampling mask is used across all repetitions. Here we introduce NexOP, a deep-learning framework for joint optimization of the sampling and reconstruction in multi-NEX acquisitions, tailored for low-SNR settings. NexOP enables optimizing the sampling density probabilities across the extended k-space-NEX domain, under a fixed sampling-budget constraint, and introduces a new deep-learning architecture for reconstructing a single high-SNR image from multiple low-SNR measurements. Experiments with raw low-field (0.3T) brain data demonstrate that NexOP consistently outperforms competing methods, both quantitatively and qualitatively, across diverse acceleration factors and tissue contrasts. The results also demonstrate that NexOP yields non-uniform sampling strategies, with progressively decreasing sampling across repetitions, hence exploiting the NEX dimension efficiently. Moreover, we present a theoretical analysis supporting these numerical observations. Overall, this work proposes a sampling-reconstruction optimization framework highly suitable for low-field MRI, which can enable faster, higher-quality imaging with low-cost systems and contribute to advancing affordable and accessible healthcare.

The concept of spatial coupling is among the most significant breakthroughs in coding theory over the past decade. The excellent waterfall and error floor performance of spatially coupled codes has positioned them as promising coding candidates for future communication and data storage systems. This article presents an overview of recent advances in spatially coupled codes. In particular, we first review several representative examples of recently proposed spatially coupled codes and highlight their unique features that make them appealing for different applications. Next, we discuss the useful properties of spatially coupled codes and how to design good spatially coupled codes. The article concludes with some future research directions and open problems.

Uncrewed aerial vehicles (UAVs) are increasingly deployed in complex networked environments, yet the joint optimization of multi-UAV motion control and connectivity remains a fundamental challenge. In this paper, we study a multi-UAV system operating in an integrated terrestrial and non-terrestrial network (ITNTN) comprising terrestrial base stations and high-altitude platform stations (HAPS). We consider a three-dimensional (3D) aerial highway scenario where UAVs must adapt their motion to ensure collision avoidance, efficient traffic flow, and reliable communication under dynamic and partially observable conditions. We first model the problem as a hierarchical multi-objective partially observable Markov decision process (H-MO-POMDP), capturing the coupling between control and communication objectives. Based on this formulation, we propose a large language model (LLM)-driven hierarchical multi-rate control framework. At the global level, an LLM-based controller on the HAPS performs long-term planning for load balancing and handover decisions. At the local level, each UAV employs a hybrid controller that integrates a slow-timescale LLM for high-level spatial reasoning with a reinforcement learning agent for faster UAV-to-infrastructure (U2I) communication and motion control. We further develop a high-fidelity 3D simulation platform by integrating the gym-pybullet-drones environment with 3GPP-compliant RF/THz channel models. Numerical results demonstrate that the proposed framework significantly outperforms state-of-the-art baselines, achieving a 14% increase in transportation efficiency and a 25% improvement in telecommunication throughput. Additionally, it achieves a 23% reduction in physical collision rates, demonstrating strong handover stability and zero-shot generalization in dynamic scenarios.

System identification (SysID) is critical for modeling dynamical systems from experimental data, yet traditional approaches often fail to capture nonlinear behaviors. While deep learning offers powerful tools for modeling such dynamics, incorporating uncertainty quantification is essential to ensure reliable predictions. This paper presents a systematic framework for constructing and training interval Neural Networks (INNs) for uncertainty-aware SysID. By extending crisp neural networks into interval counterparts, we develop Interval LSTM and NODE models that propagate uncertainty through interval arithmetic without probabilistic assumptions. This design allows them to represent uncertainty and produce prediction intervals. For training, we propose two strategies: Cascade INN (C-INN), a two-stage approach converting a trained crisp NN into an INN, and Joint INN (J-INN), a one-stage framework jointly optimizing prediction accuracy and interval precision. Both strategies employ uncertainty-aware loss functions and parameterization tricks to ensure reliable learning. Comprehensive experiments on multiple SysID datasets demonstrate the effectiveness of both approaches and benchmark their performance against well-established uncertainty-aware baselines: C-INN achieves superior point prediction accuracy, whereas J-INN yields more accurate and better-calibrated prediction intervals. Furthermore, to reveal how uncertainty is represented across model parameters, the concept of channel-wise elasticity is introduced, which is used to identify distinct patterns across the two training strategies. The results of this study demonstrate that the proposed framework effectively integrates deep learning with uncertainty-aware modeling.

A secure two-party computation protocol for running dynamic controllers over secret sharing has recently been proposed. Unlike encrypted control schemes based on homomorphic encryption, this protocol enables operating dynamic controllers for an infinite time horizon without controller-state decryption, controller-state reset, or input re-encryption. However, the two-party setting introduces additional online communication between the computing parties, which may hinder real-time feasibility. In this study, we demonstrate the feasibility of the protocol through implementation on a commercial cloud platform with an inverted pendulum testbed. Experimental results show that the proposed protocol successfully stabilized the pendulum despite the online communication overhead.

Accurate segmentation of organs and lesions in medical images is essential for clinical applications including diagnosis, prognosis, and treatment planning. While Vision Transformers (ViTs) have shown impressive segmentation performance, they face key challenges in module and architecture design. Specifically, self-attention struggles to capture fine-grained local features critical for understanding detailed anatomical structures, standard MLP modules lack explicit mechanisms to preserve spatial information, conventional encoder-decoder architectures rely on naive feature fusion strategies that cannot handle large semantic discrepancies, and existing designs lack explicit mechanisms to propagate low-level information from encoder to decoder. To address these limitations, we propose a Frequency-enhanced Vision Transformer (FEFormer) for robust and efficient volumetric medical image segmentation that explicitly models frequency information to jointly capture global context and fine structural details. FEFormer comprises four novel components: a Frequency-enhanced Dynamic Self-Attention (FDSA) module that jointly captures fine-grained local details and global long-range dependencies through locality-preserving convolution with frequency-domain attention; a Frequency-decomposed Gating MLP (FGMLP) that adaptively models low- and high-frequency components for enhanced semantic and structural representation; a Wavelet-guided Adaptive Feature Fusion (WAFF) module that enables semantically consistent encoder-decoder feature integration in the frequency domain; and a Frequency-enabled Cross-scale Stem Bridge (FCSB) that enhances low-level feature propagation across scales. Evaluated on four diverse volumetric medical image segmentation tasks, FEFormer achieved superior segmentation performance with high computational efficiency compared to state-of-the-art methods.

Channel modeling is fundamental to the analysis, design, and optimization of wireless communication systems, which, however, accurate wireless channel modeling remains challenging, especially given the increasingly complex wireless environments. As an emerging paradigm, 3D Gaussian Splatting (3DGS)-based channel modeling methods achieve accurate wireless radiation field (WRF) reconstruction and high-fidelity spatial spectrum synthesis. However, existing works only consider a single carrier frequency and fail to adapt to wide-range cross-frequency channels. To address this challenge, we propose XFreq-GS, a cross-frequency Gaussian splatting framework for WRF reconstruction. It employs 3D Gaussian primitives with shared geometry and frequency-adaptive radio frequency (RF) attributes to reconstruct cross-frequency WRF, and synthesizes power angular spectrum (PAS) maps for wireless channel modeling. Experiments show that XFreq-GS outperforms state-of-the-art 3DGS-based methods in PAS synthesis and achieves superior cross-frequency generalization. Code is available at https://github.com/KINGAZ1019/XFreq-GS.

We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible audio-label alignments. The recently introduced Aligner reduces this cost by discarding explicit alignments, but this modification makes it unsuitable for streaming. Our approach overcomes this limitation by dividing the audio into chunks and aligning each label to the leftmost frames of its chunk, whereas transitions between chunks are managed by a learned end-of-chunk probability. Experiments show that the Chunkwise Aligner not only matches the Transducer's accuracy in both offline and streaming scenarios, but also offers superior training and decoding efficiencies.

We study the problem of estimating a parametric discrete memoryless channel \( p(y \mid x; \boldsymbol{\theta}) \) when the transmitter selects its input distribution \( \pi \) to maximize mutual information under the true parameter \( \boldsymbol{\theta}^* \). Using only i.i.d.\ observations of the channel output, we aim to jointly estimate the capacity-achieving input distribution \( \boldsymbol{\pi}^* \) and the true channel parameter \( \boldsymbol{\theta}^* \). In general, recovery of \( \boldsymbol{\pi}^* \) and \( \boldsymbol{\theta}^* \) can be challenging. To that end, we propose two efficient algorithms based on the Blahut–Arimoto (BA) optimality conditions: (i) a bilevel fixed-point method and (ii) an augmented Lagrangian method. Empirical results demonstrate that both proposed algorithms successfully recover the true \( \boldsymbol{\theta}^* \) and \( \boldsymbol{\pi}^* \), whereas a naive maximum-likelihood approach that ignores the mutual-information maximization constraint fails to do so.

Cardiovascular stability estimation from wearable photoplethysmography (PPG) requires a principled nonlinear framework, yet major gaps persist in heuristic parameter selection and evaluation protocols that inflate reported performance. We introduce a Stability-Constrained Cardiovascular Stability Index (SCSI) grounded in Cardiac Stability Theory and validate it across 176,742 segments from four heterogeneous PPG datasets at three temporal scales. Cross-dataset analysis demonstrates a large Kruskal-Wallis effect size (eta2 = 0.351, p < 0.001), strong cross-scale consistency (kappa > 0.97), and significant correlation with respiratory rate across 53 ICU records (Spearman r = 0.346, p = 0.011). We identify three evaluation artifacts that inflate heuristic AUC from a true baseline of 0.573 to 0.752: segment-level cross-validation leakage, test-set normalization leakage, and pooled-AUC overweighting that conceals per-patient failure. Correcting these artifacts and applying Bayesian optimization over 15 joint parameters yields SCSI with cross-validation AUC of 0.720. On 18 held-out records, SCSI achieves pooled AUC of 0.757 (95% CI: 0.686-0.828) and negative predictive value of 0.966 for tachypnea screening, while per-record AUC of 0.497 +/- 0.207 is disclosed for transparency. External validation on 42 elective-surgery records yields AUC of 0.621, confirming cross-population generalization. Ablation analysis identifies the nonlinear complexity module as the dominant component. A sparse three-component architecture is proposed as the minimal deployable configuration. The corrected protocol provides a reproducible benchmark for future wearable cardiovascular stability indices.

Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multimodal language models (MLLMs). We introduce SpecX, a large-scale benchmark for multi-modal spectroscopy with cross-paradigm evaluation. SpecX contains 1.7M molecules with diverse spectral modalities, including NMR (1H, 13C, HSQC), IR, MS,UV,Raman and FL, and is organized into three tiers: a large-scale dataset for pretraining, an aligned multi-spectral subset for benchmarking, and a high-quality experimental subset for evaluation. SpecX supports a range of tasks such as molecular elucidation, spectrum simulation, and spectral understanding, and enables unified evaluation across both specialized spectral models and MLLMs. Experiments show that specialized models excel at signal-level modeling, while MLLMs exhibit strengths in high-level reasoning but lack precise spectral grounding. SpecX establishes a unified benchmark for spectral intelligence and highlights the need for spectrum-native foundation models.

Haptic rendering of viscoelastic materials that exhibit creep and stress relaxation is crucial for many applications, such as medical training with realistic biological tissue models. Fractional-order viscoelastic models provide an effective means of describing intrinsically time-dependent dynamics with few parameters, as these models can naturally capture memory effects. In this study, we present analyses of passivity and rendering performance for fractional-order viscoelastic models under finite-memory discretization. We derive closed-form expressions to ensure the passivity of haptic rendering with a fractional-order (FO) standard linear solid (SLS) model based on Grunwald-Letnikov derivative under short-memory discretization. We also provide symbolic expressions for the effective stiffness and damping of such FO-SLS models. The resulting passivity conditions constitute a unified framework that generalizes previously reported results for integer-order Kelvin-Voigt, Maxwell, and SLS models, since these results are special cases of the newly derived condition. Furthermore, we provide experimental validations of the theoretical passivity bounds and human-subject evaluations of perceived realism of FO-SLS models. Overall, this study establishes a unified theoretical framework and experimental evaluations for FO viscoelastic rendering under short-memory discretization.

Improving patient outcomes depends on the prompt and accurate diagnosis of brain tumors, but manual MRI scan analysis is still time-consuming and unreliable. Although deep learning has shown promise, many of the models that are now in use are computationally intensive and have difficulty handling the intrinsic complexity and variety of different types of brain tumors. In this work, we propose a lightweight yet high-performing Convolutional Neural Network (CNN) for multi-class brain tumor classification, employing MRI images to target gliomas, meningiomas, pituitary tumors, and healthy (no tumor) instances. The model was rigorously evaluated on two publicly accessible datasets from Figshare and Kaggle. Leveraging efficient feature extraction and optimized training strategies, our CNN achieved classification accuracies of 99.03% and 99.28%, along with ROC scores of 99.88% and 99.94% on Dataset 1 and Dataset 2, respectively-all while utilizing significantly fewer parameters than popular pre-trained architectures. In contrast to cutting-edge models like DenseNet201, MobileNetV2, VGG19, Xception, InceptionV3, and ResNet50, our approach consistently demonstrated superior performance with reduced computational overhead. These findings highlight the potential of the proposed model as a practical and reliable diagnostic aid in clinical environments.

Integrated Sensing and Communications (ISAC) is emerging as a key paradigm for future Sixth-Generation (6G) networks, with communication-centric designs favored for their compatibility with existing standards. Communication signals contain both known deterministic pilot symbols and unknown random data payloads. Most localization approaches rely solely on pilots, discarding the position information contained in the data symbols, which constitute the majority of each transmitted frame. Alternatively, Decision-Directed (DD) approaches exploit data decisions, thereby inherently limiting positioning performance to that of the communication system. In this paper, we derive a Marginal Maximum Likelihood (MML) estimator that jointly leverages pilot and data payloads without requiring data decoding, enabling operation with high-order constellations and under challenging noise conditions. We consider an opportunistic scenario in which an Orthogonal Frequency-Division Multiplexing (OFDM) signal transmitted by a User Equipment (UE) is captured by a distributed receiver array. Through numerical simulations, we demonstrate that the proposed method achieves superior localization performance compared to existing approaches and consistently converges to the genie bound (where data symbols are assumed perfectly known) at a lower Signal-to-Noise Ratio (SNR) than any DD method. Furthermore, the proposed method remains robust to constellation size, unlike DD approaches, whose performance degrades with increasing modulation order. Finally, we provide a computational complexity analysis of the proposed method and the considered baselines, highlighting the impact of system parameters on their respective computational costs.

Accurate channel state information (CSI) prediction is essential for improving the reliability and spectral efficiency of massive MIMO-OFDM systems in high-mobility scenarios. Existing deep learning methods struggle to jointly capture short-term local variations and long-range nonlinear dependencies in CSI sequences. To address this challenge, we propose ChannelKAN, a hybrid CNN-KAN channel prediction model with multi-scale frequency domain information enhancement. The key insight is that CNNs and Kolmogorov-Arnold Networks (KANs) are naturally complementary: CNNs extract intra-time-step local spatial-frequency correlations, while KANs with learnable Chebyshev polynomial activations fit inter-time-step nonlinear temporal evolution in a holistic manner. Specifically, a dual-domain expansion module first generates complementary frequency-domain and delay-domain CSI representations. A multi-scale frequency information enhancement module then retains dominant spectral components at multiple scales to strengthen key features and suppress noise. Next, a CNN-KAN feature extraction module captures local correlations via cascaded convolutions and models long-range dependencies via Chebyshev KAN layers. Finally, a dual-domain fusion module adaptively integrates features from both branches to produce the prediction. Experiments on 3GPP-compliant QuaDRiGa datasets demonstrate that ChannelKAN outperforms RNN, LSTM, GRU, CNN, and Transformer baselines in normalized mean square error (NMSE), spectral efficiency (SE), and bit error rate (BER) across various velocities and signal-to-noise ratios. Ablation studies further confirm the effectiveness of each proposed module.

Directional antenna systems are gaining substantial traction for aerial networks due to their higher gain, extended transmission range, and enhanced security. However, the requirement of beam alignment makes the task of finding and reaching neighbors challenging, particularly in a mobile setting. For wireless networks, privacy concerns play an equally critical role. However, the problem of ensuring network-wide connectivity while maintaining limited exposure when probing around is still unexplored. We address this trade-off by proposing an adaptive transceiver selection protocol based on the Deep Q-Network (DQN) framework. Each node acts as an independent DQN agent and interacts with the environment to learn how to balance the trade-off. Since the directional nodes operate only based on local observations, we adopt a weighted mechanism that guides them in prioritizing either high reachability or privacy by adaptively tuning the probing patterns. Results show that DQN framework surpasses the Random and Q-Learning baselines. Weights favoring discovery provide higher probing efficiency and reachability, while weights prioritizing privacy ensure limited exposure at the cost of low reachability, eventually attaining higher objective value.