Papers

Channel foundation models assume access to fully observed channels, an assumption that fails in deployment. We introduce PilotWiMAE, a self-supervised framework whose encoder ingests noisy pilot observations directly and whose attention factorizes along the axis separating temporal from joint space-frequency processing, an inductive bias inspired by the physics of the problem. Pilot input shrinks the observation space by up to two orders of magnitude and also removes the unrealistic assumption of full-CSI availability while incurring lower latency. The factorized design generates robust representations by exploiting the separable channel structure and allows a pretraining mask ratio of $99\%$. We pair patch-normalized reconstruction, which captures small-scale fading structure, with an auxiliary scale loss that recovers the large-scale fading features, and use an AWGN curriculum to match pilot noise at pretraining and deployment. Pretrained solely on $3.5$\,GHz and evaluated at $28$\,GHz across in-distribution and out-of-distribution settings, PilotWiMAE's cross-frequency beam selection and channel characterization beat supervised baselines despite operating on a smaller observation space. To weaken the coupling between decoder capacity and representation quality, we further propose a decoder-centric pretraining stage following the encoder-decoder joint pretraining, which allows PilotWiMAE to demonstrate competitive channel estimation without sacrificing representation quality. To foster further work in this direction, we release the PilotWiMAE pretrained weights and training pipeline, together with CSIGen, our Sionna-based ray-tracing channel-generation tool, and the channel datasets used in this work.

Glaciers play a critical role as freshwater reserves and indicators of climate change, yet their automatic delineation, especially for debris-covered glaciers, remains challenging due to spectral similarity with surrounding terrain. This study introduces CryoNet, a deep learning framework that leverages a rich multi-modal dataset combining Sentinel-2 optical imagery, DEM-derived topographic variables, spectral indices, Principal Component Analysis (PCA), InSAR coherence and phase, tasseled-cap features, and GLCM texture to discriminate clean-ice glaciers, debris-covered glaciers, and glacial lakes. CryoNet is an encoder-decoder CNN with nested skip connections and spatial-channel Squeeze-and-Excitation (scSE) attention, built upon a ResNet101 encoder to capture hierarchical contextual and spatial features. The study is conducted in the Poiqu Basin in the central Himalaya, and transferability is evaluated by applying the trained model to the Mont Blanc Massif in the Alps. We additionally analyse the importance of each data layer in improving glacier mapping performance. The proposed model achieves an overall IoU of 90.52%, mean Recall of 98.08%, and mean Precision of 92.26%. For debris-covered glaciers specifically, CryoNet obtains an IoU of 90.46%, a recall of 95.79%, and a precision of 94.21%. Across both per-class and overall metrics, CryoNet surpasses DeepLabV3+, SegFormer, and U-Net, taken as state-of-the-art (SOTA) references, demonstrating its effectiveness for robust glacier mapping in complex high-mountain environments.

The Versatile Video Coding (VVC) standard, introduced in 2020, offers 40-50% bitrate savings for equivalent visual quality of reconstructed videos over its predecessor, High Efficiency Video Coding (HEVC), at the cost of significantly increased encoding complexity. This growth in encoding complexity is mainly due to the addition of the Quad Tree Multi Type Tree (QTMTT) partitioning structure, which increases the split combinatorial complexity. This paper presents a critical evaluation of state-of-the-art (SOTA) partitioning acceleration techniques designed to reduce the complexity of the partitioning search in VVC. Particular attention is given to how these methods have evolved alongside successive versions of the VVC Test Model (VTM), which serves as the reference software for benchmarking coding tools. These techniques are analyzed in the context of their adaptation to internal changes in VTM, such as updated heuristics for fast partitioning decisions. The study also highlights the challenges involved in improving the trade-off between encoding complexity and compression efficiency. This challenge becomes more pronounced when evaluating methods across diverse VTM configurations and multiple software versions.

Steganalysis models excel on benchmark datasets but struggle in the wild when analyzed images are produced by a processing pipeline unseen during training. This problem known as Cover Source Mismatch (CSM) is particularly hard in realistic settings where practitioners (1) have access to only a small, unlabeled dataset, (2) are unsure of the processing techniques applied to these images, and (3) lack information on the proportion of covers and stegos in that set. To answer this challenge, we introduce TADA (Target Alignment through Data Adaptation), a framework learning to emulate the unknown processing pipeline from a small unlabeled target set. This architecture is trained with a loss combining residual covariance alignment, residual distribution matching, and a $\ell^2$ loss constraining the emulator to produce realistic images. Across toy and operational targets, TADA yields substantial gains in robustness to CSM and improves operational generalization compared to strong holistic and atomistic baselines. Additional resources are available at this link: https://github.com/RonyAbecidan/TADA

The reconfigurable coupler antenna (RCA), also called the flexible coupler antenna (FCA), is a new technique that aims to improve the performance of wireless communication networks by reconfiguring the positions and rotations of low-cost couplers around fixed-position active antennas to harness mutual coupling. Specifically, different couplers can independently adjust their positions and/or rotations at the transceiver to reshape the induced currents on the couplers for radiation, thereby collaboratively achieving mechanical beamforming for directional signal enhancement or nulling. The position and/or rotation reconfiguration of passive couplers provides a new and cost-effective means of enhancing wireless communication performance, while significantly reducing the antenna and radio-frequency (RF) chain costs of conventional active arrays. The compact and low form-factor structure of the RCA makes it particularly appealing for devices with stringent size, weight, and power (SWAP) constraints. In this article, we provide an overview of RCA to reveal its promising capabilities in wireless networks, including its system modeling, practical implementation, and competitive advantages over existing techniques. We present a variety of RCA-enabled performance enhancements in terms of mechanical beamforming gain, path-loss reduction, fading mitigation, spatial multiplexing gain, interference suppression, and geometric gain. Furthermore, we elaborate on the design challenges of RCA as well as promising solutions, and discuss the key applications of RCA in wireless networks. Finally, numerical results are presented to verify the substantial capacity gains enabled by RCA-aided transmission in wireless networks.

Flexible coupler antenna systems have recently received significant research interest due to their capability to intelligently reconfigure wireless channels by controlling coupler positions and/or rotations and dynamically exploiting mutual coupling. In this paper, we investigate a new type of flexible coupler antenna, termed rotatable coupler antenna (RCA), for enabling spectrum and energy efficient wireless communication cost-effectively. Specifically, an RCA consists of one fixed active antenna and multiple low-cost passive couplers, each of which can independently rotate in three-dimensional (3D) space, so as to collaboratively achieve mechanical beamforming without requiring additional radio-frequency (RF) chains for the couplers. We study an RCA-enhanced point-to-point communication system, where one RCA is deployed at the transmitter to serve a single user equipped with a fixed antenna. Based on multi-port circuit theory, we establish the channel model and characterize the mutual coupling coefficients as a function of coupler rotations. We formulate a new problem to maximize the received signal-to-noise ratio (SNR) at the user by optimizing the 3D rotations of all couplers, subject to practical coupler rotation constraints. To tackle this nonconvex problem, we develop a spherical-cap conditional-gradient-based algorithm with cross-entropy-method initialization. Simulation results demonstrate that the proposed RCA system can significantly improve communication performance in comparison with benchmark schemes, while requiring substantially fewer active antennas and RF chains.

We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,977 subjects across 12 datasets. It spans ages 5-104 and five clinical domains: Alzheimer's, Parkinson's, tumors, white matter disease, and neurodevelopment. Unlike prior medical Visual Question Answering (VQA) efforts that operate on 2D slices or rely on narrow diagnostic labels, NeuroQA pairs every item with a full 3D volume. It evaluates 11 clinically grounded reasoning skills across Yes/No, multiple-choice, and open-ended formats. Of the 203 templates, 131 are image-grounded (answerable from a 3-plane viewer) and 72 are image-informed (ground truth from quantitative volumetry or clinical instruments). To remove text-only shortcuts, we apply answer-distribution refinement, reducing closed-format text-only accuracy from $>$80% to 44.6%; image necessity is assessed separately through an image-grounding protocol released with the benchmark. A 38-rule deterministic pipeline and two rounds of expert review verify every QA pair against FreeSurfer measurements, metadata, or radiology report fields, with zero same-subject contradictions across templates. We conduct a clinician evaluation in which two clinicians independently assess 100 frozen test items on a three-plane viewer. On closed-format (Yes/No + multiple-choice) test-public items, the best zero-shot vision-language model and a supervised 3D CNN baseline reach 47.5% and 43.7% accuracy respectively, both below the 49.4% text-only majority-template floor. NeuroQA adopts a two-tier release with public QA pairs for open-access datasets and reproducible generation scripts for datasets restricted by data use agreements (DUAs), plus subject-level splits, a held-out private test set, and an online leaderboard.

Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated prediction sets that provide deterministic long-run miscoverage guarantees. These guarantees, however, hinge on the assumption of perfect feedback about the coverage of past prediction sets. In practice, the observed miscoverage indicator may be corrupted by noise, communication failures, or adversarial manipulation, which can severely degrade OCP's calibration guarantees. In this paper, we study OCP under corrupted feedback. We first model feedback corruption as an arbitrary binary flip sequence, and analyze how feedback corruption affects and degrades the miscoverage performance of standard OCP. We then propose two robust schemes: robust OCP via filtering, which leverages the structural properties of the predicted threshold to filter corrupted feedback, and robust OCP via active compensation, which incorporates an active compensation mechanism to mitigate the effect of corrupted feedback. For both methods, we establish explicit miscoverage guarantees, which are further specialized for an independent stochastic flip model and for an arbitrary error model with memory bounds. Experiments on real-world datasets validate the proposed approach, showing markedly improved calibration and significantly smaller prediction sets compared with baseline OCP methods under corrupted feedback.

The paper describes a new method for estimating the poles of an ARMA model using higher-order crossings. The method involves transforming counts of crossing events into estimates of ARMA poles via the autocorrelation domain. An important advantage of the method is that the crossing counts are the only features that need to be stored from the original data. The poles of an ARMA model of a control loop correspond to the roots of the characteristic equation and are thus useful for evaluating control performance.

Quadratic constraints (QCs) are widely used to characterize nonlinearities and uncertainties, but generic analytical characterizations can be conservative on bounded domains. This paper develops a framework for constructing verified quadratic characterizations of scalar relations in the two-dimensional real plane. Candidate quadratic inequalities are locally generated by solving convex quadratic programs using samples from the relation and exterior sample points. They are then verified globally using sum-of-squares certificates over an exact semialgebraic description or, in the case of nonpolynomial relations, over relaxed polynomial descriptions. The resulting verified constraints define a sound overapproximation of the scalar relations over the considered domains. These constraints are directly compatible with existing analysis frameworks based on QCs and pointwise integral quadratic constraints (IQCs) for static nonlinearities and uncertainties, and they can also be embedded in QC-based semidefinite programs for reachability and safety analysis of feedforward neural networks. For smooth activations such as $\tanh$, the method yields domain-dependent quadratic characterizations that constitute an alternative to generic sector- or slope-based descriptions. For ReLU networks, we give methods to reduce conservatism in QC-based reachability analysis of feedforward networks by exploiting dependencies between neurons and tighter local bounds. Numerical examples demonstrate improved reachability results for smooth activations, reduced conservatism for ReLU networks, and applicability beyond neural networks through an example involving saturation.

Models of opinion dynamics aim to capture how individuals' opinions change when they interact with each other. One well-known model of opinion dynamics is the Deffuant–Weisbuch (DW) model, which is a type of bounded-confidence model (BCM). In the DW model, agents have pairwise interactions, and they are receptive to other agents' opinions when their opinions are sufficiently close to each other. In this paper, we extend the DW model by studying it on networks with heterogeneous and adaptive edge weights between pairs of agents. These edge weights govern the interaction probabilities between the agents and thereby encode the idea that people are more likely to communicate with individuals with whom they have previously compromised or had other positive interactions. We prove theoretical guarantees of our adaptive edge-weighted DW model's convergence properties, the long-time dynamics of its edge weights, and the model's associated “effective graph", which is a time-dependent subgraph that includes edges only between agents that are receptive to each other's opinions. We support our theoretical results with numerical simulations of our adaptive edge-weighted DW model on a variety of networks and find that including adaptive edge weights yields different qualitative dynamics for different types of networks. In particular, for small confidence bounds, we observe that incorporating adaptive edge weights decreases the convergence time for dense networks but increases the convergence time for sparse networks.

Long-form audio understanding poses significant challenges for large audio language models (LALMs) due to the extreme length of audio sequences and the need to reason over heterogeneous acoustic cues distributed over time, such as speech content, speaker identity, emotion, and sound events. To address these challenges, we propose PlanRAG-Audio, a planning-based retrieval-augmented generation framework for scalable long-form audio understanding. Rather than having audio LALMs process entire recordings directly, PlanRAG-Audio explicitly plans which modalities and temporal spans are required for a given query, and retrieves only query-relevant information from a structured text and audio database. This retrieval planning enables effective reasoning over complex, cross-domain audio queries while substantially reducing the input length passed to the large language models. Experiments across a wide range of speech/audio retrieval demonstrate that PlanRAG-Audio improves reasoning accuracy and stabilizes performance as audio duration increases by decoupling inference cost from raw audio length.

Stochastic hybrid systems combine continuous-time stochastic dynamics with discrete reset events, producing intrinsically non-Gaussian and often multimodal uncertainty. A consistent propagation law must also account for boundary-induced probability flux across guard sets, making direct density propagation through hybrid Fokker-Planck equations expensive. We develop a hybrid extension of the Max-Entropy Moment Kalman Filter (MEM-KF) that performs filtering from partial statistical information by propagating a finite collection of moments through stochastic hybrid dynamics and reconstructing beliefs using moment-constrained maximum-entropy distributions. The key step is a moment propagation rule derived from Dynkin's formula with a jump-sum, in which reset effects appear as a boundary-flux correction over the guard set. This yields tractable moment dynamics without solving the underlying hybrid PDE. In a stochastic bouncing-ball example, the proposed method captures reset-induced non-Gaussianity through corrected moment equations while retaining the MEM-KF's optimization-based maximum-entropy representation.

Class imbalance is a fundamental challenge in medical image segmentation, where frequent classes typically dominate training at the expense of rare classes. Loss-based approaches mitigate imbalance by reweighting the per-pixel loss within the batch, while sampling strategies control which images enter the batch. Yet neither explicitly controls which classes appear within the batch, leaving rare-class exposure only partially rebalanced. In this work, we adopt episodic sampling from few-shot learning to promote class-balanced batch construction in a fully supervised setting. We decouple episodic sampling from its conventional metric-learning context and evaluate it in body composition segmentation in CT. We compare episodic sampling against random and weighted sampling on nine muscle and adipose tissues, derived from 210 scans of the public SAROS dataset. Training is performed under full- and low-data regimes, with additional comparisons under matched training iteration budgets. Under full-data training, all three strategies performed comparably (mean Dice 0.882 for episodic, 0.878 for random and weighted). Under low-data training, episodic sampling outperformed random and weighted (0.787 vs. 0.758 and 0.762), driven by a 12-fold difference in training iterations. Under matched training budgets, random and weighted overfit earlier, while episodic improved for approximately three times more iterations before plateauing. Our findings identify the training iteration budget as under-recognized confound in sampling strategies, motivating iteration-aware evaluation protocols for small datasets. Furthermore, the residual advantage of episodic sampling is consistent with an implicit regularization effect of class-balanced batches, offering a low-cost, model-agnostic strategy for class-imbalanced medical image segmentation. Code is available at https://github.com/iasonsky/episodic-sampling.

In sound field control applications, it is commonly assumed that one has access to an accurate representation of the sound field in the region of interest. This is a problematic assumption since the reconstruction of a sound field from available microphone measurements is especially challenging in real-time applications where only causal measurements are available. Notably, causal time-windowed observations introduce correlation between frequency components, making sound field reconstruction methods that process each frequency band independently sub-optimal. In this work, we formulate a causal finite-window spatio-temporal linear minimum mean-square error estimator for sound field reconstruction. The sound field is modeled as the solution to the wave equation driven by a stationary stochastic spatio-temporal source distribution, which induces a physically interpretable covariance function. It is shown that this covariance function is closely related to the classical diffuse-field coherence model. Since the computational complexity grows rapidly with the number of spatio-temporal observations, we formulate a budget-constrained spatio-temporal sample selection approach to minimize the posterior reconstruction variance. The proposed estimator and sampling strategy are evaluated using both simulated and measured sound fields, demonstrating improved short-window reconstruction compared to frequency domain finite-window baselines.

Global Navigation Satellite Systems (GNSS) underpin positioning, navigation, and timing (PNT), yet their low-power signals are easily blocked or disrupted, leaving gaps in PNT availability in contested environments (e.g. maritime settings) where interference, spoofing, or denial can occur. A key practical need is an independent, ubiquitous aiding signal that can be tracked passively and fused with inertial sensing to sustain full navigation-state estimation without dedicated or cooperative infrastructure. This paper presents an end-to-end LEO-aided hybrid framework that fuses GPS, Starlink downlink beacons, and an inertial measurement unit (IMU) in a 9D (3D position, 3D velocity, and 3D attitude) PNT system using an extended Kalman filter (EKF). We (i) extract Doppler-rate from Starlink downlink beacon tones by associating measurements with satellite IDs, (ii) benchmark beacon Doppler-rate against OFDM-derived range observables under a common processing/estimation pipeline, and (iii) integrate the resulting observable into inertial navigation. We evaluate GPS/IMU, Starlink/IMU, and GPS-Starlink-IMU using Fisher-information predictions, Monte Carlo simulations, and hardware measurements. Results show that Starlink Doppler-rate provides meaningful complementary PNT information, and can aid 9D estimation when GNSS is degraded or intermittently unavailable.

This paper presents an innovative solution designed to facilitate safe and flexible operation of nuclear power plants. The purpose of this new device, named OAPS system, is to provide optimal strategies (e.g., axial offset control, xenon oscillations mitigation, effluent minimization) and real-time recommendations (e.g., dilution and boration flowrates, turbine power setpoints and variation rates) to help NPP operators perform power variations confidently and efficiently. In fact, just as a GPS navigator optimizes and modifies its planned route according to the current position of the user, the OAPS system regularly updates its recommendations based on the latest plant measurements. To achieve this, the OAPS system relies on a well-established -yet cutting-edge in the nuclear industry -advanced control technique known as model predictive control. The conventional axial offset control strategy of the OAPS system was previously validated on both Framatome's full-scope PWR simulator and EDF's full-scope N4 simulator. In this paper, three new advanced strategies are showcased on an intermediate-complexity PWR simulator developed by Framatome: 1) determination of the fastest feasible power variation rates, 2) accelerated cancellation of axial power oscillations and 3) minimization of water and boron effluents.

This letter introduces attack-resilient Control Lyapunov Functions (AR-CLFs) and attack-resilient Control Barrier Functions (AR-CBFs) for nonlinear control-affine systems subject to control-input false data injection attacks (FDIA) satisfying an at-most-exponentially growing envelope. The proposed framework embeds a unified adaptive compensation term into both the CLF decrease and CBF safety constraints. In contrast to input-to-state stability/safety (ISS/ISSf)-based methods that certify disturbance-dependent enlarged safe sets, the proposed approach enables finite-time recovery to the nominal safe set without requiring a prior magnitude bound on the FDIA, relying instead on a growth-rate characterization used for analysis and an online gain tuning law that regulates the compensation term. A unified quadratic program (QP) is developed to enforce the AR-CLF and AR-CBF conditions simultaneously, guaranteeing uniformly ultimately bounded (UUB) stability and uniform ultimate safety (UUS) under unbounded FDIA. Numerical results demonstrate improved resilience compared to existing ISS-CLF, ISSf-CBF, and robust CLF-CBF-QP approaches.

This article presents a Hamilton–Jacobi (HJ) reachability framework for a two–satellite collision avoidance problem operating in the same circular orbit, where relative motion is modeled in the radial–tangential–normal (RTN) frame using planar Hill–Clohessy–Wiltshire (HCW) dynamics. We define the target state space as unsafe relative configurations in the orbit plane corresponding to minimum separation requirements consistent with Federal Communications Commission (FCC) orbital standards. The interaction between spacecraft is formulated as a zero–sum differential game, where Player 1 is the controlled satellite and Player 2 is modeled as a bounded adversarial disturbance with unknown intent. We present the HJ formulation and compute backward reachable sets that characterize relative states from which collision cannot be avoided under worst-case disturbances, while states outside this set admit provably collision-free trajectories. These reachable sets are integrated with supervisory hybrid control logic to determine when evasive maneuvers must be initiated, enabling mathematically grounded safety guarantees for scalability.

Advanced Traffic Signal Control (TSC) algorithms require real-time phase control, yet existing Hardware-in-the-Loop Simulation (HILS) testbeds only support pre-programmed timing plans. In this paper, we present the first HILS testbed for real-time phase control. We develop a novel middleware architecture that translates dynamic phase actions (selection, switch, and duration) into commands for NTCIP-compliant commercial hardware controllers. This middleware manages phase transitions, synchronizes signal states, and handles errors without interrupting the hardware's internal operations. Experimental validation demonstrates that the system executes real-time phase commands, handles system conflicts, and achieves a low system internal latency at sub-millisecond on average.

Distributed acoustic sensing (DAS) systems generate continuous, ultra-high-channel-count data streams at rates that exceed the capabilities of conventional batch-oriented analysis frameworks. As a result, essential tasks such as interactive exploration of long-duration recordings, scalable event annotation, and real-time algorithm-in-the-loop monitoring remain inadequately supported by workflows built around manually selected data segments and offline processing. This paper presents FiLark (Fiber Lark), a Python framework that applies a streaming-first principle uniformly across data access, signal processing, visualization and monitoring for DAS. Instead of operating on manually selected data segments, FiLark presents any DAS sources-including continuous multi-file recordings-as a unified stream and builds all system components around that abstraction. An OpenGL-based ring-buffer renderer enables interactive browsing and visualization of arbitrarily long recordings with constant memory usage. An integrated annotation interface supports event labeling directly within continuous data streams, facilitating the creation of reproducible machine-learning-ready labeled datasets without offline preprocessing. The signal processing library includes temporal, spatial, spectral, and decomposition-based operators, with both CPU implementations and GPU-accelerated variants via PyTorch, alongside stateful chunked execution that preserves processing continuity and application semantics across segment boundaries. A standardized monitor interface further integrates streaming detectors and learning-based models into the visualization workflow. By sharing a common streaming abstraction across all layers, FiLark allows processing configurations and workflows developed interactively to transfer directly to scalable production pipelines without modification.

While conventional (k=1) discrete-time barrier certificate conditions impose strict safety constraints by requiring the function to be non-increasing at every step, k-inductive barrier certificates relax this by allowing a temporary increase – up to k-1 times, each within a threshold $\epsilon$ – while maintaining overall safety, and improving flexibility. This paper leverages neural networks and constructs k-inductive neural barrier certificates (k-NBCs) for (partially) unknown nonlinear systems. While neural networks offer scalability in the design process, they lack formal guarantees, requiring additional approaches such as counterexample-guided inductive synthesis (CEGIS) with satisfiability modulo theories (SMT) for verification. However, the CEGIS-SMT framework requires knowledge of system dynamics, which is unavailable in practical settings. To address this, we leverage the generalization of the Willems et al.'s fundamental lemma, using a single state trajectory, to construct a data-driven representation of (partially) unknown models for SMT verification without sacrificing accuracy. Additionally, CEGIS-SMT further removes the constraint of restricting barrier certificates to specific function classes, such as sum-of-squares, enabling greater flexibility in their design. We validate our approach on three nonlinear case studies with (partially) unknown dynamics.

Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generative manifold geometry, breaking probability conservation and driving samples off the learned manifold under strong guidance. We analyse guidance through the continuity equation and show its effect decomposes into a divergence term and a score-parallel term defined invariantly across parameterisations. We prove the divergence term blows up structurally as sampling approaches the data manifold, motivating a time-dependent schedule alongside score-parallel attenuation. The resulting plug-and-play rule, Adaptive Manifold Guidance (AdaMaG), bounds both terms at no additional inference cost. Finally, we show that most empirical heuristics for reducing saturation or improving generation quality correspond directly to the two terms in our decomposition. Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and induces controlled desaturation in high-guidance regimes.

This paper presents a new stochastic relay-based extremum-seeking controller (ESC) for multi-input-single-output (MISO) systems. The goal of this work was to create an algorithm that is much simpler to configure than alternative approaches making deployment to real-world problems easier. A solution is developed first for a static map and then adapted for a general class of dynamic systems. The number of configurable parameters is one per input channel for the static case and only one additional parameter is needed for the dynamic version. The problem of gradient identification is solved via the use of stochastic relay gains and a simple stability proof for the static case is presented. Simulation tests demonstrate the performance of the strategy for optimizing both static and dynamic systems.

Short-form video poses new challenges to the quality assessment of user-generated content (UGC) due to its complex generation pipeline, rapid content variation, and mixed distortions. To address this challenge, we propose an end-to-end video quality assessment (VQA) framework that employs a dense visual encoder based on CLIP, and incorporates compression priors derived from the frequency domain to generate artifact- and structure-aware weight maps for feature aggregation. By explicitly decomposing artifact, structure, and original visual feature branches and adaptively fusing them over time through a learned gating module, the proposed method achieves accurate and efficient quality prediction. Experimental results show that our method achieves strong performance on short-form video datasets in terms of average rank and linear correlation (SRCC: 0.736, PLCC: 0.787), while maintaining efficient inference runtime. The code and additional results are available at: https://github.com/xinyiW915/FGSVQA.

This paper proposes CAT-MoEformer, a context-aware transformer with scene-conditioned mixture-of-experts (MoE) feed-forward networks, for proactive mmWave beam prediction from compressed uplink pilot observations. The spatial encoder comprises a three-layer asymmetric convolutional network followed by a squeeze-and-excitation recalibration block, which extracts frequency-beam correlation features from pilot tensors without explicit channel reconstruction. A truncated pretrained GPT-2 backbone models the temporal evolution of beam sequences, with the feed-forward networks in the upper three transformer layers replaced by scene-conditioned MoE-FFN modules. A lightweight gating network maps the scenario label and normalized user equipment speed to expert mixing weights, conditioning the routing decision on physical propagation descriptors rather than on latent hidden states. This design yields interpretable expert assignments and eliminates the load imbalance associated with token-level routing. To prevent expert collapse under soft routing, a three-stage training strategy is introduced: hard expert assignment in the first stage establishes scene-specific specialization, isolated gating network training in the second stage aligns the soft routing distribution with the hard partition, and top-1 hard inference in the third stage fine-tunes the model under deterministic single-expert activation to maximize scene-specific precision. Simulation results on 3GPP TR 38.901 Urban Macro channel simulations with $64{,}000$ user samples demonstrate that CAT-MoEformer achieves a Top-1 beam prediction accuracy of $94.88\%$ and a beam switching instant accuracy of $80.62\%$, representing gains of $2.33\%$ and $9.55\%$ respectively over a CNN+GPT-2 baseline, with an inference latency of $0.52$~ms.

This paper investigates robust synchronization for multi-agent systems (MASs) governed by parabolic partial differential equations in the presence of both observable and unobservable disturbances. Using only boundary output measurements, a disturbance observer is designed to estimate observable Dirichlet boundary disturbances while ensuring robustness of the observer error system with unobservable disturbances occurring in the domain. Using only the reference signal and local output information, distributed synchronization controllers are then constructed to enable all agents to track the reference trajectory. In particular, exponential tracking is achieved in the absence of unobservable disturbances, while robustness is preserved when additional unobservable disturbances occur during controller implementation. We further analyze the impact of unobservable Dirichlet-Robin boundary disturbances on synchronization performance by proving the boundedness of solutions to the synchronization error system. Moreover, to characterize the influence of all disturbances, input-to-state stability (ISS) is established for the closed-loop system. For the involved systems, the generalized Lyapunov method and the recursion technique are extensively employed in the stability analysis, and the lifting technique and semigroup theory are used to prove the well-posedness. Simulation results validate the proposed control scheme, demonstrating effective disturbance estimation and rejection, robust synchronization, and the ISS properties under various scenarios.

This paper implements deep reinforcement learning (DRL) with a safety filter for spacecraft reorientation control with a single pointing keep-out zone. A new state space representation is designed which includes a compact representation of the attitude constraint zone. A reward function is formulated to achieve the control objective while enforcing the attitude constraint. The soft actor-critic (SAC) algorithm is adopted to handle continuous state and action space. A curriculum learning approach is implemented for agent training. To guarantee the compliance of the attitude constraint, a control barrier function (CBF)-based safety filter is implemented for agent deployment. Simulation results demonstrate the effectiveness of the proposed state space presentation and the designed reward function. Monte Carlo simulations underscore that reward shaping alone cannot guarantee the safety during reorientation maneuver. In contrast, with the CBF-based safety filter, the constraint can be guaranteed during maneuvers.

Blind source separation (BSS) is a natural framework for studying how latent causes may be recovered from sensory mixtures, but deriving online and biologically plausible algorithms for structured (i.e., constrained to known domains) and potentially correlated sources remains challenging. Recent work has derived neural networks for BSS from maximization of an entropy measure, yet its online implementations involve complex and nonlocal recurrent dynamics. Motivated by this perspective, we propose Predictive Entropy Maximization, which achieves competitive performance in BSS, using only local weight updates. The method employs a close approximation of an entropy measure, yielding an objective function with easily interpretable components. Minimizing this objective leads to a predictive neural architecture in which feedforward synapses follow an error-driven rule (that can be realized through dendritic mechanisms), lateral inhibitory connections are learned with local Hebbian plasticity, and source-domain constraints are enforced through simple output nonlinearities. We derive explicit spectral bounds on the surrogate error, characterizing when the approximation is accurate. Empirically, Predictive Entropy Maximization remains robust under increasing source correlation and observation noise, outperforms biologically plausible algorithms that rely on stronger independence or decorrelation assumptions, and remains competitive with exact determinant- and correlative-information-based baselines. These results show how local plasticity and adaptive lateral inhibition can emerge from maximizing a regularized second-order entropy over structured source domains. Our implementation code is available at https://github.com/BariscanBozkurt/Predictive-Entropy-Maximization.

This paper addresses the problem of tracking in-plane waves from image sequences using periodic surface patterns. Wave-induced deformation is modeled as a spatial phase modulation of a periodic carrier. We propose ADOPT (Analytical Demodulation of Periodic Texture), a method based on an oriented two-dimensional analytic signal to estimate displacement phase and orientation. The approach relies on a physical model describing longitudinal and transverse in-plane waves. Orientation-selective filtering isolates relevant spectral components, and phase extraction provides a stable reconstruction of the displacement field. A theoretical analysis using the Cramer–Rao bound evaluates performance limits of ADOPT. Simulations show that the proposed method outperforms state-of-the-art Digital Image Correlation (DIC) at high signal-to-noise ratios, especially for small displacements where DIC becomes limited. Moreover, ADOPT is more computationally efficient. Experiments on silicone membranes with periodic patterns confirm accurate estimation of wave fields and dispersion curves under impulsive excitation. Overall, the proposed framework provides a robust and efficient solution for wave-induced displacement estimation.