Papers

This work studies resilient output containment for heterogeneous linear multi-agent systems with actuator cyber-attacks over directed network topologies. The leaders generate bounded locally absolutely continuous trajectories; however, their dynamics, velocity bounds, and motion envelopes are undisclosed to the followers. The cyber-attack model includes state- and input-correlated, as well as bounded exogenous actuator false-data terms. A continuous two-layer adaptive control architecture is proposed. The first layer is a virtual-actuator reconfiguration layer that uses partial state measurements to compensate for actuator attacks in the local tracking-error dynamics. The second layer is a network interface that generates task-space commands via an adaptive interaction protocol. This protocol uses only neighbor-exchanged network-interface states whose dimensions match those of the plant output, and it does not require global graph knowledge for parameter tuning. For directed graphs, under a leader-rooted united spanning-tree condition, a nonsmooth Lyapunov analysis yields asymptotic containment at the command level. The physical outputs then converge to the leader convex hull up to a residual determined by the command-tracking local controllers. Simulation results using a network of quadrotors with damped suspended loads illustrate the performance of attack recovery and containment tracking.

Indoor multipath is shaped by surrounding reflectors, scatterers, and blockages, so a relative power-delay profile (PDP) can serve as a location fingerprint without an identifiable LoS path, angle information, or absolute time-of-arrival ranging. However, a communication receiver observes finitely many noisy pilot-frequency samples rather than an ideal PDP. This paper models the resulting Dirichlet blur, delay folding, and off-grid mismatch, and reconstructs a posterior-power profile using expectation-maximization sparse Bayesian learning. In spatially consistent QuaDRiGa simulations, twofold SBL raises 20-dB Top-1 accuracy from 75.79% (native PDP) and 87.24% (threefold zero-padding) to 93.27%, with 0.392~m mean error.

Reliable organ localization in abdominal CT can provide spatial priors for downstream trauma analysis. We propose CT-3GDINO, a lightweight 3D detector that adapts a Grounding-DINO-style query-based architecture to fixed organ localization using frozen pseudo-text class tokens instead of a real text encoder. The model combines a Swin3D visual backbone, bidirectional feature enhancement, pseudo-text-guided query selection, and a cross-modality decoder to predict normalized 3D boxes for liver, spleen, left kidney, right kidney, and bowel. We train and evaluate on 193 matched RSNA/RATIC CT volumes with segmentation-derived boxes. The best multi-scale model, trained from scratch, achieves 0.5830 overall top-1 class-wise mAP over 3D IoU thresholds from 0.1 to 0.7, outperforming fixed- and trainable-backbone classification-pretrained variants with 0.5570 and 0.4657 mAP. Performance is strong for coarse localization, with 0.9649 AP at IoU 0.1, but remains limited for strict box alignment, with 0.1552 AP at IoU 0.7. These results establish CT-3GDINO as an open-source baseline for pseudo-text-conditioned 3D organ localization and motivate future work on localization-aware pretraining, richer multimodal conditioning, and injury-focused detection.

Physical layer authentication (PLA) allows to authenticate the user by comparing measurements over time, assuming their time consistency or by modeling their evolution. However, these assumptions become problematic when devices are in motion and in indoor environments due to multipath propagation and obstructions. In this paper, we propose a PLA mechanism for moving devices in indoor environments, where multiple access points (APs) estimate the dominant channel tap path loss (PL) and angle of arrival (AoA) from the received signals and compare them with previously collected channel knowledge maps (CKMs). Specifically, the measurements are compared to those in the neighborhood of the previously known position obtained from CKMs. A comprehensive security analysis is conducted under both random and optimal attacks. Numerical results in a representative indoor scenario, with CKM obtained via ray tracing, validate the effectiveness of the proposed PLA approach.

This paper proposes and demonstrates experimentally for the first time a Kolmogorov-Arnold Network (KAN)-based digital predistortion (DPD) model, named envelope time-delay KAN (ETDKAN), for mitigating nonlinear distortions in analog radio-over-fiber (A-RoF) systems. The ETDKAN model incorporates physical constraints of radio-frequency (RF) nonlinear devices and, through KAN symbolization, achieves a significant reduction in computational complexity while improving interpretability. The proposed model is numerically implemented and optimized alongside multilayer perceptron (MLP) and memory-polynomial-based DPDs. Results show that the resulting symbolic ETDKAN (symbETDKAN) attains ACLR and EVM performance comparable to neural network-based models, while maintaining a computational complexity close to that of memory polynomials. Experimental validation using an A-RoF system confirms the practical feasibility of the proposed approach, which resulted in a 4-5 dB reduction in ACLR in the analyzed scenario.

This study introduces a particle-based computational framework to investigate the scalability of morality and the systemic decoupling of formal law from decentralized social ethics in expanding populations. While micro-societies reinforce ethical conduct through local reciprocity, macroscale systems introduce anonymity that strains cognitive memory limitations. We model individual agents as discrete particles with finite memory capacities ($L$) and dynamically evolving, stochastic choice profiles ($\mu$) regulated by non-linear social pressure switches. Monte Carlo ensemble simulations demonstrate a distinct, non-linear phase transition as the population scales ($N \to \infty$). When the population metric outpaces memory capacity ($N \gg L$), the local re-encounter probability drops as $\mathcal{O}(L/N)$. This structural dilution neutralizes decentralized peer-to-peer accountability, causing global behavioral norms to decouple from moral baselines and drift toward a minimalist legal floor. Furthermore, cyclic scale experiments expose a prominent, path-dependent hysteresis loop, mathematically formalizing the non-Markovian inertia and irreversible nature of moral decay in self-organizing social systems.

This paper presents a deep learning-assisted methodology for the inverse synthesis of a compact, wideband inverted Doherty power amplifier (PA). Convolutional neural networks (CNNs) and genetic algorithms (GAs) are jointly employed to generate pixelated Doherty combiner networks that integrate load modulation, impedance matching, power combining, and phase compensation into a single structure. As a proof of concept, we design and fabricate a GaN HEMT Doherty PA with a pixelated output combiner. The prototype achieves a measured peak drain efficiency of 51%-63% and a 6-dB back-off efficiency of 48%-54% over 1.9-2.5 GHz. Within the same frequency range, the measured output power is 44+/-0.3 dBm. Furthermore, with digital predistortion (DPD) applied, the prototype circuit demonstrates an adjacent channel leakage ratio (ACLR) better than -53.2 dBc.

X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete. While learned reconstruction methods such as the Learned Primal-Dual algorithm achieve strong performance, they typically rely on supervised training with access to ground-truth data, which is often unavailable in practice. In this work, we propose a self-supervised reconstruction method by extending the Noise2Inverse framework to the Learned Primal-Dual algorithm. The resulting approach, called Noise2Inverse Learned Primal-Dual (N2I-LPD), enables training of a learned iterative reconstruction operator without ground-truth images by exploiting the statistical independence of noise in distinct measurements with respect to angular rotation of the CT-scan. We compare the proposed method with classical reconstruction methods, as well as neural network-based approaches such as a U-Net trained within the same N2I framework. The results demonstrate that N2I-LPD achieves improved reconstruction quality, highlighting the potential of combining learned reconstruction operators with self-supervised training strategies for practical CT imaging scenarios where ground-truth data is unavailable.

Empirical Bayes (EB) estimators can match the first-order asymptotic risk of maximum likelihood (ML) while behaving very differently at second order: recent excess mean squared error (XMSE) analysis shows that kernel-based EB estimation may be worse than ML when the kernel is poorly aligned with the true parameter. This paper turns that diagnostic into a design principle. We propose an XMSE-aware mixed estimator that interpolates between ML and EB shrinkage. Its fixed-weight XMSE is a scalar quadratic, yielding a closed-form oracle mixing weight that is no worse than both ML and the base EB estimator at the XMSE scale. A plug-in implementation based on finite-sample XMSE approximations is proved consistent, with a second-order oracle regret rate for an interior oracle weight. We further establish a transfer of the regret bound to the fixed-weight risk curve evaluated at the selected weight, a thresholded boundary rule, and extensions to compact kernel families and to finite and growing kernel dictionaries with high-probability oracle bounds. Finite impulse response simulations with SURE-tuned, hard-selection, and trace-corrected baselines, together with the public Silverbox and Cascaded Tanks benchmarks, show that the proposed estimator retains most of the benefit of regularization when it is helpful and retreats toward ML under kernel misspecification, with an identified finite-de analyzed on the benchmarks.

We propose a MIMO radar angle estimation framework that uses the four-component weighted-type fractional Fourier transform (4-WFRFT) as a spatial-domain waveform diversity mechanism. Unlike conventional fractional Fourier (FrFT) MIMO radar where FrFT serves as a receiver-side time-frequency processing tool, our approach decomposes a data sequence into four WFRFT basis functions,original signal, its Fourier transform, time-reversal, and inverse Fourier transform, and transmits them simultaneously from a four-element uniform linear array. The spatial superposition of these basis functions at each far-field angle creates a unique angle-dependent waveform structure, enabling angle estimation through time-domain matched filtering with known waveforms. We demonstrate that this spatial-domain mixing achieves angular resolution surpassing the Rayleigh diffraction limit by a factor of 1.4$\times$ to 12.8$\times$, with the advantage most pronounced at low SNR where conventional beamforming fails completely. The Cramér-Rao bound is derived with a full 3-parameter Fisher information matrix, and the Fisher information is decomposed into geometry and waveform contributions, revealing that the WFRFT waveform structure contributes approximately 3$\times$ more information than array geometry alone. Extension to $M$-element arrays with $M$-component WFRFT demonstrates resolution gain scaling with array size. Simulations with linear chirp base sequences achieve 0\,dB PAPR and validate sub-Rayleigh resolution with a four-element array.

We analyze the uplink spectral efficiency achievable in a distributed multiple-input multiple-output (D-MIMO) architecture employing a 1-bit radio-over-fiber fronthaul. This architecture eliminates the need for local oscillators at the access points, hence enabling coherent-phase transmission without costly over-the-air synchronization. With this fronthaul architecture, the uplink signal at the central processing unit is a dithered, oversampled, and 1-bit quantized version of the passband signal received at the access points. This makes some of the conventional spectral-efficiency expressions used in the D-MIMO literature not directly applicable for two key reasons: the nonlinearity of the input-output relation and the practical unavailability of minimum mean square error (MMSE) channel estimates. To address this issue, we propose novel achievable-rate expressions that do not require MMSE channel estimates and rely on the Bussgang decomposition to linearize the input-output relation. We use these expressions to determine the optimal signal-to-dither ratio (SDR) that maximizes the achievable rates in both single- and multiuser scenarios and to assess the impact of oversampling. We then use one of the proposed achievable-rate expressions to investigate the max-min fairness problem when the access points cannot maintain the optimal SDR because of limitations in their dynamic range.

Hot-weather electric-vehicle thermal management is no longer a separate cabin and battery problem. A single climate system must cool the traction battery, maintain passenger comfort, and admit outdoor air for cabin air quality, while high ambient temperature and solar load derate the compressor serving all three demands. We identify fresh-air ventilation as a hidden battery-safety load: on a derated shared cooling loop, the compliant fresh-air floor consumes finite cabin-side cooling capacity and removes residual cooling reserve from the battery. In a 40 $^\circ$C, 800 W m$^{-2}$, 150 kW event, raising the fresh-air floor from 0.30 to 0.43 lowers peak cabin CO$_2$ from 1219 to 978 ppm, but raises peak battery temperature from 39.96 to 40.02 $^\circ$C and reduces the battery cooling bus from 575 to 529 W. We develop a reserve-aware predictive controller combining a physics-guided scientific-machine-learning surrogate, grid-connected departure thermal reserve, air-quality-priced ventilation allocation, and dual control-barrier-function projections for battery temperature and operative comfort. The controller holds the pack at 39.73 $^\circ$C, caps peak CO$_2$ at 895 ppm, keeps operative-temperature RMSE at 0.82 $^\circ$C, and uses 20.0% less drive cooling energy than fixed maximum-compressor operation; ablations show that removing either barrier, under-ventilating, or removing departure reserve breaks joint feasibility. Evidence comes from NASA POWER records, KU Leuven BEV BMS data merged with NASA POWER weather, 45 $^\circ$C GOTION aging data, 40 $^\circ$C high-power NMC thermal identification, EnergyPlus cabin cross-checks, and OpenModelica/FMI replay. Treating fresh air as a battery thermal-reserve variable creates an actionable path toward EV thermal management that protects battery life, occupant health, comfort, and efficiency in one shared loop.

Cold-climate transit agencies are electrifying fixed-timetable fleets, but winter exposes a block-level failure mode hidden by seasonal energy margins: cabin heating can deplete batteries faster than layovers recharge them, causing later trips to start undercharged and making one cold day cascade into timetable infeasibility. We present WeatherRobustBus, an open-data framework that converts this risk into block-level failure probability by injecting real hourly weather into real transit duties and propagating cold-weather energy uncertainty. The framework couples a transparent traction and cabin-thermal backbone with a bounded monotone residual ensemble, and validates cabin heating against an independent EnergyPlus bus-cabin simulation driven by the same Toronto weather record. Against this first-principles reference, it achieves the lowest all-year error (0.213 kWh RMSE over 8760 hours) and remains reliable in the out-of-support cold tail ($T \le -12^\circ$C), where pure machine-learning baselines degrade by 1.5–4x and the best competitor reaches only 1.055 kWh. Embedded in a Monte Carlo block-feasibility simulator over 60 real Toronto TTC vehicle blocks, the model reveals a sharp weather-induced failure envelope. A forecast-triggered robust policy combining opportunity charging, a fuel-fired cabin-heating bridge, and modest buffering reduces mean cold-wave failure probability from 0.759 to 0.112 across eight cold-wave days; a deconfounded ablation shows opportunity charging is the dominant lever and the heater is a low-cost complement. WeatherRobustBus provides a reproducible pathway from weather data to winter-resilience decisions for electric-bus fleets.

We introduce DNSMOS-C, a compact end-to-end speech quality assessment model that extends the DNSMOS Pro framework by integrating a MOS-guided triplet-based contrastive loss. Applied directly to the intermediate embeddings, this contrastive supervision encourages the latent space to be better organized with respect to perceptual quality while preserving the simplicity and efficiency of DNSMOS Pro. Unlike prior methods that depend on large pre-trained self-supervised learning (SSL) encoders and multi-stage training, DNSMOS-C jointly learns speech representations and MOS regression within a single, unified framework. Experiments on multiple datasets show that DNSMOS-C consistently improves correlation metrics over DNSMOS Pro and achieves better generalization on challenging out-of-domain test sets. Furthermore, latent space analyses indicate that our approach learns representations that exhibit an emergent low-dimensional quality ordering, which enhances interpretability and improves training stability. These findings demonstrate that MOS-guided contrastive learning enables more robust and accurate quality predictions without incurring additional computational overhead.

M-ary Aggregate Spread Pulse Modulation (M-ASPM) is a physical layer (PHY) modulation technique that offers several advantages for low-power wide-area networks (LPWANs). For instance, in conventional LPWAN modulations increasing receiver sensitivity by extending symbol duration - thereby proportionally increasing the time-on-air (ToA) - exacerbates collision exposure. In contrast, M-ASPM payload processing gain can vary over a wide range without impacting the effective packet collision rate. In particular, in this work we demonstrate how short front portions of M-ASPM packets can serve as a separate collision-resistant detection channel that, in addition to performing asynchronous packet detection and synchronization, obtains the carrier frequency offset (CFO) for each packet within a desired range and with the required precision. Then, while raising processing gain, the subsequent payload information can be extracted without expanding the sample window per symbol. Consequently, the receiver sensitivity can be significantly increased without exacerbating packet collisions and thus without reducing network throughput under collision-limited operation. We further establish a multi-channel configuration in which numerous quasi-orthogonal payload channels share a single detection channel that additionally performs payload channel identification and selection. Such sharing is especially useful for scaling and economizing LPWAN deployments under diverse technical requirements and constraints. The presented analysis is validated via extensive simulations under high packet collision rates in wide ranges of payload sizes and processing gains, and for varying noise and interference power levels. The results signify that M-ASPM provides a structurally distinct scaling behavior compared to conventional LPWAN modulations, decoupling range extension from collision-induced throughput degradation.

We present a semidefinite programming framework for constructing time-varying Lyapunov densities for nonautonomous dynamical systems on a hypertorus. The formulation leverages Gram matrix representations of hybrid (real-trigonometric) polynomials. In addition, we introduce a novel block decomposition of these Gram representations to confine the blow-up of the resulting density to a prescribed set. The results are then applied to establish the almost global synchronization of a time-varying Kuramoto model and the robust almost-global stability of a parameter-varying nonautonomous system. These examples demonstrate the applicability of the proposed method and validate the theoretical results. All computational results are obtained using an open-source MATLAB implementation, as referenced in the text, thereby facilitating reproducibility of the reported examples.

Labeling speaker diarization data is costly, yet annotation tools rarely measure that cost. We present voxmap-studio, an open-source, React-based diarization annotation tool integrated with the pyannote-based diarization ecosystem. Its canvas is initialized by a fast stride-accelerated diarization engine so that the annotator corrects a hypothesis rather than drawing every speaker turn by hand, and the tool records annotation cost - typed edit-operation counts and time - as a first-class output, enabling quantitative comparison of how much different forms of assistance actually help. Export is gated on per-segment human confirmation and guarded by injected "phantom" attention checks, which prevent unverified automatic output from being released as ground truth. In a preliminary study on nine AMI audio files, unassisted manual annotation was the costliest and least accurate, and automatic initialization shifted the work from creating turns to correcting them; highlighting uncertain segments gave the lowest cost in our small sample. The tool and its instrumentation are open source.

Learning discrete speech representations that preserve similarity across variable-length utterances is central to query-by-example spoken term detection (QbE-STD). While wav2tok introduced CTC-based sequence alignment to enforce token consistency, its tightly coupled clustering and alignment training recipe limits scalability. We propose wav2tok 2.0, a scalable alignment-aware speech tokenizer built on the BEST-STD backbone. wav2tok 2.0 employs staged training, first learning discriminative, speaker-invariant representations via contrastive learning and vector quantization, and then enforcing pairwise token consistency using a CTC alignment loss and a novel DTW-aligned framewise prediction objective with adaptive weighting. Experiments show that wav2tok 2.0 consistently outperforms BEST-STD and general-purpose tokenizers on QbE-STD while remaining efficient and scalable.

Spin plays a crucial role in many ball sports due to its effect on the trajectory of the ball. Vision-based estimation of the ball's spin during a game with conventional cameras is challenging due to the ball's small size, high speed, and fast rotation. To address these challenges, we propose an event-based active vision system that can track unmodified balls and measure their spin in real time. The system consists of an event camera for its high temporal resolution and minimal motion blur, high-speed pan/tilt galvanometer mirrors to keep the ball in the field of view, and a low-latency focus-tunable telephoto lens to increase the spatial resolution on the ball and keep it in focus. To track the ball, we use a hybrid approach that combines 2D event-based detection for centering and 3D positions from a ball localization system for re-initialization. For high-accuracy spin estimation, we propose an offline method that performs contrast maximization on the sphere (s-CMax). This method achieves state-of-the-art accuracy on static balls across multiple sports (table tennis, baseball, tennis, and golf), with mean magnitude and axis errors of 1.2% and 1.5 degrees, respectively. We then develop a low-latency online method for table tennis as a case study in real-time applications. This method uses an uncertainty-aware convolutional neural network trained on pseudo-ground-truth spin labels from the offline approach, combined with a GPU-accelerated batch implementation of contrast maximization for refinement. We demonstrate reliable tracking and spin estimation with a three-view setup during professional table tennis matches, with high accuracy (8.8% magnitude and 6.4 degrees axis mismatch w.r.t. the offline method), 3 ms latency, and 750 Hz throughput.

High penetration of distributed energy resources increasingly creates congestion in low-voltage distribution networks, while local energy markets (LEMs) optimise community welfare without explicitly internalising network constraints. This paper investigates whether a profit-seeking aggregator embedded within a welfare-oriented LEM can partially internalise distribution-level congestion through market participation. We develop a post-clearing, price-protected intervention in which the aggregator injects additional supply and triggers re-clearing, with network feasibility validated using nonlinear AC power flow subject to a non-deterioration constraint on maximum line loading. The mechanism is benchmarked against Distribution System Operator (DSO)-only corrective control and a hybrid regime with residual DSO action following aggregator intervention. Results on a UK LV feeder show that aggregator participation reduces thermal loading and preserves community welfare relative to DSO-only control, though it does not fully restore compliance under severe stress. The hybrid regime achieves the strongest technical performance while maintaining lower welfare loss. Overall, aggregator intervention remains privately profitable, indicating partial incentive alignment.

Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition, yet many studies emphasize classification accuracy without identifying which respiratory properties separate different states. Using the chest respiratory channel of the WESAD dataset, we analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal one-dimensional convolutional neural networks (1D-CNNs) and physically grouped handcrafted respiratory signatures. The primary task is stress versus non-stress detection, while baseline, stress, amusement, and meditation are additionally analyzed in a one-vs-rest setting to reveal state-specific respiratory markers. The feature space is organized into respiratory timing, breath-to-breath variability, waveform statistics, spectral/time-frequency descriptors, and autocorrelation/nonlinear predictability descriptors, with the raw 60 s signal treated as a sixth representation for the CNN branch. We introduce autocorrelation transition lags (Zpm/Zmp) as interpretable markers of respiratory correlation scale and separately evaluate exploratory forecast-error-growth/Lyapunov-like descriptors. In the final CNN refit setting, the raw-signal model achieved the strongest stress-vs-rest performance (accuracy 96.72%, macro-F1 95.30%, MCC 90.61%). In contrast, compact feature models were stronger for baseline (MCC 65.34%), amusement (MCC 35.69%), and especially meditation (MCC 88.65%). Strict nested reanalysis of the auxiliary Top-20 stress search yielded mean MCC=82.29% versus 85.45% originally, indicating modest selection optimism. These results show that CNNs are most useful for the practical stress detector, whereas interpretable respiratory signatures provide stronger and more physiologically transparent state-specific markers for several non-stress conditions.

Arbitrary slice super-resolution reconstructs isotropic volumes from anisotropic clinical acquisitions by synthesizing intermediate slices at arbitrary scales. However, treating this ill-posed inverse problem as unconstrained residual-based regression risks hallucinating anatomically implausible structures or altering the originally observed data. To address both concerns, this paper presents the Dual-Prior Null-space Learning (DP-NSL) framework, which reformulates the task as a constrained recovery process guided by two complementary priors. A Measurement-Consistent Projection (MCP) enforces a Deterministic Observation Prior: the reconstruction undergoes an exact orthogonal projection that reproduces every acquired slice with zero error, confining all learned details to the unobservable null space. Within this null space, a Mixture-of-Splines (MoS) module imposes a Geometric Continuity Prior by dynamically mixing B-spline experts of different analytic orders, allowing each anatomical region to be modeled with a content-aware level of continuity. To promote spatial coherence, a Local Spatial Consistency Decoder (LSCD) further injects local inductive bias. Experiments on three CT and one MRI benchmark show that DP-NSL outperforms existing approaches while strictly preserving measurement consistency. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.

Skin lesion segmentation is a key task in computer-aided dermatological diagnosis, where accuracy directly impacts downstream analysis and disease classification. However, dermoscopic images are challenging due to blurred boundaries, low contrast, large shape variations, and artifacts such as hair and shadows. Recently, diffusion models have shown strong performance in medical image segmentation thanks to their progressive denoising and distribution modeling capabilities. Nevertheless, existing diffusion-based methods still suffer from limited cross-level feature interaction and insufficient boundary detail recovery. To address these issues, we propose MLFFM-SegDiff, a multi-level feature fusion diffusion model for skin lesion segmentation. Built on a diffusion framework, the method introduces a dual-path U-Net encoder, a Multi-Level Feature Fusion Module (MLFFM), and a boundary-sensitive loss function. The dual-path encoder enhances interaction between noisy mask features and dermoscopic image features. MLFFM improves skip connections via attention, scale alignment, and adaptive cross-level fusion. These designs enable the decoder to jointly leverage shallow boundary cues and deep semantic representations, improving mask reconstruction quality. Experiments on ISIC2018, PH2, and HAM10000 demonstrate that MLFFM-SegDiff outperforms representative methods including DermoSegDiff, U-Net, and SwinUNETR across Accuracy, F1-score, Jaccard index, Recall, and Dice. In particular, it achieves an average Jaccard index of 0.8546 and Dice coefficient of 0.9207. These results validate the effectiveness of the proposed multi-level feature fusion strategy for improving lesion segmentation performance. The code will be released at https://github.com/Qacket/MLFFM-SegDiff.git after publication.

Event cameras asynchronously report brightness changes with microsecond-level temporal resolution, but real event data remain difficult to collect at scale because specialized sensors, careful synchronization, and task-specific annotations are required. Event-camera simulation is therefore important to event-based vision tasks. Most practical simulators build on contrast-threshold event generation, some with additional filtering, stochastic noise, or calibrated sensor parameters. While effective, such formulations can simplify the temporal structure produced by a pixel's recent response history. We introduce FracEvent, a physics-inspired sensor-side simulator with compact fractional-relaxation voltage dynamics. Given a log-intensity trajectory, FracEvent combines fast and slow response modes, emits ON/OFF events by localizing threshold crossings on the continuous voltage trajectory, and updates the event reference while retaining the mode states. This retained state links residual response to later event timing. We evaluate FracEvent through direct event-stream comparison and downstream transfer on image reconstruction and optical flow estimation. Across multiple datasets, FracEvent achieves leading results on multiple metrics in both evaluations, showing its practical value for event-camera simulation. Project page: https://bonaparte233.github.io/FracEvent/

While traditional image restoration focuses on perceptual quality, Task-Driven Image Restoration (TDIR) aims to maximize the performance of downstream high-level vision tasks. Recent approaches leveraging generative priors have shown promise for TDIR; however, they typically suffer from computational inefficiency and potential semantic alteration by indiscriminately updating all latent tokens. In this paper, we posit that not all visual information is equally important for machine perception. Through an analysis of the latent token space, we observe that task-relevant cues are unevenly distributed across the token sequence, exhibiting index-wise specialization. This suggests that selectively refining a subset of tokens can be sufficient for task-driven objectives. Leveraging this insight, we propose TaskTok, a novel framework that selectively restores only task-relevant tokens via a learnable token switch and a lightweight token refinement module. Extensive experiments across image classification, semantic segmentation, and object detection demonstrate that TaskTok significantly enhances task performance with high computational efficiency. The source code is available at https://github.com/jimmy9704/TaskTok

Synthetic electrocardiogram (ECG) generation can support algorithm development and robustness evaluation, but simulated signals must preserve interpretable activation, recovery, and morphology properties. We present a graph-based ECG synthesis framework that combines activation-consistency certification with diagnostics-aware morphology curation. A unified heart graph supports an eikonal-template backend (ET) and a pseudo-diffusion reaction–eikonal backend (RE). We formulate graph Eikonal activation as a Bellman fixed-point problem and use the Bellman residual as a computable certificate for activation-time consistency. Each simulated ECG is evaluated by a two-stage diagnostics pipeline that separates metric computation from experiment-specific acceptance policies. On the cardiac graph, RE-derived activation times showed near-millisecond agreement with the Eikonal backbone and achieved $R^2=0.99876$ after causal predecessor filtering. Recovery experiments showed that endo-epicardial APD gradients determined the main T-wave morphology window, whereas the diffusion strength $\kappa$ provided secondary repolarization smoothing. In final balanced multi-lead curation, RE accepted 658/2000 samples versus 578/2000 for ET and increased per-model morphology coverage from 0.09248 to 0.09888. The framework provides a conservative basis for controllable and curated synthetic ECG generation.

In sea-air communication networks composed of an uncrewed aerial vehicle (UAV) and an uncrewed surface vehicle (USV), the extended target characteristics and three degree of freedom motion of the USV under sea induced disturbances cause beam misalignment in the UAV's tracking of the USV. To address these issues, this paper proposes a predictive beam tracking scheme based on integrated sensing and communication (ISAC) for sea-air networks. We develop a wide and narrow beam switching scheme based on sub-array selection, where a time allocation factor is optimized to balance robust state sensing in the wide beam mode and high-rate communication in the narrow beam mode. Specifically, a wide beam mode provides full USV coverage and state sensing, while a narrow beam mode exploits the estimated state for high-gain communication with the communication receiver (CR) mounted on the USV. To characterize the CR motion, a sea-air state evolution model is derived by jointly considering the surge, sway, yaw, and sea induced disturbances of the USV. For the extended target USV, the measurement equation is constructed from multiple scatterer observations, with the measurement noise caused by sea clutter modeled, and an extended Kalman filter (EKF) based CR state prediction and estimation method is developed. In addition, the effect of sea clutter on sensing accuracy is incorporated into the time allocation optimization problem to adjust the time of the wide beam mode. Simulation results demonstrate that the proposed scheme achieves higher tracking accuracy than the state-of-the-art benchmark schemes.

High-frequency massive multiple-input multiple-output (MIMO) systems promise ultra-high data rates. However, efficient beam management remains challenging due to the prohibitive beam training overhead and intricate coordination required in multi-user MIMO (MU-MIMO) scenarios. To address these bottlenecks, environment-aware communications have emerged as a promising paradigm, leveraging site-specific knowledge to circumvent exhaustive pilot-based beam training and streamline multi-user communications. In this paper, we propose an interpretable and geometry-driven framework that utilizes multi-modal environmental data, specifically regional 3D light detection and ranging (LiDAR) point clouds and location information, to construct an offline virtual base station (VBS) database. By modeling dominant reflection paths via mirror symmetry across building facades reconstructed from the point clouds, the VBS database provides a compact and sparse description of the wireless propagation environment. To bridge the semantic gap between geometric information and wireless channels, we develop a coarse channel reconstruction mechanism that estimates channel parameters directly from VBS-derived geometric relationships. Based on the resulting coarse beamspace representation, we design a VBS-assisted orthogonal-pilot (VOP)-based partial beam training scheme to refine the coarse estimates with minimal online training overhead. Finally, to tackle the combinatorial beam selection problem and manage inter-user interference, we propose a hierarchical deep reinforcement learning framework, namely a dual-agent dueling double deep Q-network, for coordinated beam selection (DD3QN-CBS). Simulation results demonstrate consistent gains in both beam training efficiency and beam selection performance over heuristic and learning-based baselines.

While pre-trained models excel in specialized tasks, learning universal representations across diverse acoustic domains remains challenging. To address this, we propose WQ-Fusion, a robust dual-encoder framework for cross-domain audio representation learning. Overcoming the limitations of static concatenation, WQ-Fusion integrates whisper and qwen via an Adaptive Feature Modulation module and a novel element-wise gated attention mechanism. This design enables dynamic feature selection, allowing the model to selectively emphasize relevant acoustic and semantic dimensions. Extensive experiments on the Interspeech 2026 Audio Encoder Capability Challenge (Track A) benchmark demonstrate that by effectively routing heterogeneous information, WQ-Fusion achieves a superior overall score of 0.836, significantly outperforming the strongest single-encoder baseline.

Many multimodal systems estimate the reliability of each modality and weight their contributions to the final prediction. However, it remains unclear whether these scores influence model decisions or merely correlate with performance. We propose a simple diagnostic to test whether reliability information is used during inference. After training, the model and inputs are fixed while reliability scores are permuted across test examples. If predictions depend on these scores, performance should degrade. Experiments on StressID for stress recognition and CMU-MOSEI for sentiment analysis show that permuting reliability scores leaves performance unchanged despite substantial potential gains from selecting the best modality per example. In positive controls where reliability signals identify the correct modality, the same frozen fusion rules yield significant improvements, indicating that reliability signals influence fused decisions only when they reliably predict unimodal correctness.