Papers

Recent progress in visual brain decoding from fMRI has been enabled by large-scale datasets such as the Natural Scenes Dataset (NSD) and powerful diffusion-based generative models. While current pipelines are primarily optimized for perception, their performance under mental-imagery remains less well understood. In this work, we study how a state-of-the-art (SOTA) perception decoder (DynaDiff) can be adapted to reconstruct imagined content from the NSD-Imagery benchmark. We propose a latent functional alignment (LFA) approach that maps imagery-evoked activity to the pretrained model's semantic content-enriched conditioning space, by adding a simple alignment module, while keeping the original remaining components frozen. To mitigate the limited amount of matched imagery-perception supervision, we further introduce a neural retrieval-based augmentation strategy that selects semantically related NSD perception trials from the same participants. Across four subjects, LFA consistently improves high-level semantic reconstruction metrics relative to the frozen pretrained baseline and a voxel-space ridge alignment baseline, and enables above-chance decoding from multiple cortical regions. These results suggest that semantic structure learned from perception can be leveraged to stabilize and improve visual imagery decoding under out-of-distribution conditions.

Angle-of-arrival (AoA) estimation is a crucial function in wireless communications used for localization, beam-forming, interference management, and other applications. Deep learning (DL) solutions have been proposed for AoA to mitigate limitations of traditional AoA estimation techniques such as sensitivity to noise and the inability to generalize across different array characteristics. A challenge, however, of DL-based approaches is their reliance on large data collection campaigns and model training. This paper proposes the application of Prototypical Networks (PN) to address this challenge and utilizes a real-world dataset collected on a software defined radio (SDR) testbed to validate the effectiveness of the proposed solution. Prototypical Networks excel in extracting representative embeddings from unstructured input data, establishing class prototypes during training that can be few-shot trained on unseen classes. We demonstrate the efficacy of PNs for AoA classification using complex IQ samples, focusing on its ability to correctly classify new, unseen angles that the model was not trained on previously. Our results show that training our proposed ProtoAoA on only 23% of the AoA dataset classes can attain a mean absolute error (MAE) of 3 degrees with only 4-shots of training on the unseen angles - and an MAE of 2 degrees with 32-shots of training data. These results demonstrate that the developed prototypical network architecture requires remarkably few data samples to achieve reliable AoA estimation - and highlights its potential for other wireless applications where data availability is limited.

Foundation models show strong potential for large-scale, high-dimensional biomedical applications, yet their ability to capture relevant neurobiological characteristics remains underexplored. We systematically evaluate embeddings from two neuroimaging foundation models, BrainLM and SwiFT, across multi-site fMRI datasets using a comprehensive evaluation framework. Our results show that foundation model embeddings encode substantial batch-related variability, often dominating diagnosis-related information across heterogeneous datasets. We further investigate how harmonization, applied to reduce batch effects, influences these embeddings. In addition, we find that BrainLM prefers to capture fine-grained regional activity, whereas SwiFT tends to represent interactions between regions, consistent with their respective model architectures. Our study highlights the importance of accounting for batch effects in foundation models and motivates future work on disentangling biologically meaningful signals from acquisition-related variability.

Scalable estimation of quantum states with readout errors is a central challenge in large multiqubit systems. Existing overlapping-tomography methods improve scalability by working with local subsystems, but they usually assume known or separately calibrated measurements. At the same time, readout-estimation methods model measurement errors without enforcing consistency among overlapping regional states. In this context, the present paper introduces a unified framework for joint regional quantum state tomography with readout errors. A multiqubit system is partitioned in overlapping regions, each region is assigned to a local density operator and a local confusion matrix, and neighboring regions are coupled through reduced-state consistency on shared subsystems. This leads to a structured bilinear optimization problem. To solve it, a distributed alternating method is developed in which the state-update step is handled by the alternating direction method of multipliers (ADMM), while the confusion-matrix updates are carried out locally in parallel. Analytical guarantees are also established, including a sufficient condition for local identifiability, local quadratic growth of the population misfit, and convergence of the inner state-update procedure. Simulations on Ring, Ladder, Torus, and Hub graph geometries show that joint estimation improves state recovery over fixed-readout reconstruction, recovers a substantial portion of oracle performance, and reveals a clear tradeoff between state estimation performance, communication, and computation.

Reliable geolocation of non-cooperative emitters in environments where Global Navigation Satellite Systems (GNSS) are unavailable or degraded is a key enabler for spectrum regulation, emergency response, autonomous mobility, and Integrated Sensing and Communication (ISAC) services in 5G/6G systems. Doppler-based techniques - from single-receiver Signal Doppler Frequency (SDF) fixes through multi-node Frequency Difference of Arrival (FDOA) and Direct Position Determination (DPD) to derivative-enhanced and learning-assisted hybrids - exploit radial-velocity-induced frequency shifts as a passive, high-resolution localization cue accessible with commodity software-defined radios, millimeter-wave access points, or acoustic sensors. This review consolidates over a decade of research across radio, acoustic, and satellite domains. It introduces a unifying taxonomy that divides the field into five technique families, outlining their evolution, measurement models, and estimator archetypes. It then compares algebraic, Bayesian, convex, and neural inference frameworks under realistic impairments such as oscillator drift, multipath, and asynchronous clocks, highlighting conditions where derivative Doppler metrics tighten the Cramer-Rao bound with minimal hardware cost. Environment-specific deployments are examined, from urban canyons and GNSS-denied tunnels to underwater, radar, UAV-swarm, and multi-orbit satellite scenarios, with prototype accuracies reaching meter scale using low-size, weight, and power payloads. Finally, the survey distils design recommendations for mobile and tactical operations and identifies open research challenges in frequency-reference integrity, multipath-aware modelling, edge-constrained computation, and trajectory-aware sensing.

We formulate a method to co-optimize power system capacity planning decisions and policy investments that shape electricity load patterns. To this end, we leverage a gradient-based solution technique that enables the efficient solution of operation-aware planning models. To compute gradients with respect to the conditions that define daily electricity demand profiles, we introduce and formalize the concept of differentiable scenario generation and show that generative machine learning models satisfy the mathematical requirements needed to compute consistent gradients. We demonstrate the feasibility of the proposed approach through numerical experiments using a diffusion model-based scenario generator and a stylized generation and capacity expansion planning model.

Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D spatial situations, and execute multi-phase tasks over extended horizons. We present SpaceMind, a modular and self-evolving vision-language model (VLM) agent framework that decomposes knowledge, tools, and reasoning into three independently extensible dimensions: skill modules with dynamic routing, Model Context Protocol (MCP) tools with configurable profiles, and injectable reasoning-mode skills. An MCP-Redis interface layer enables the same codebase to operate across simulation and physical hardware without modification, and a Skill Self-Evolution mechanism distills operational experience into persistent skill files without model fine-tuning. We validate SpaceMind through 192 closed-loop runs across five satellites, three task types, and two environments, a UE5 simulation and a physical laboratory, deliberately including degraded conditions to stress-test robustness. Under nominal conditions all modes achieve 90–100% navigation success; under degradation, the Prospective mode uniquely succeeds in search-and-approach tasks where other modes fail. A self-evolution study shows that the agent recovers from failure in four of six groups from a single failed episode, including complete failure to 100% success and inspection scores improving from 12 to 59 out of 100. Real-world validation confirms zero-code-modification transfer to a physical robot with 100% rendezvous success. Code: https://github.com/wuaodi/SpaceMind

Climate change has intensified extreme weather and wildfire conditions globally. Canada experienced record-breaking wildfires in 2023 and 2025, burning millions of hectares and severely impacting the Prairie provinces, with Manitoba facing its worst season in 30 years. These events highlight the urgent need to understand and mitigate escalating fire risks. While existing research largely focuses on wildfire management approaches, few studies have explored the relationship between user network traffic and wildfire activity, despite the potential of such correlations to provide valuable spatiotemporal insights into wildfire dynamics. This paper investigates the relationship between wildfire intensity and network performance during the 2025 Manitoba wildfire season, using Visible Infrared Imaging Radiometer Suite (VIIRS) satellite-derived Fire Radiative Power data and large-scale Speedtest measurements. We found statistically significant correlations between wildfire intensity and several network performance metrics in both the province-wide and region-wide case studies, as measured by Spearman's correlation coefficients ($\rho$) and corresponding p-values. Throughput-related metrics showed inverse correlations with wildfire intensity (e.g., download speed: $\rho = -0.214$, $p\_value = 0.004$), whereas latency-related metrics showed positive correlations (e.g., round-trip time latency: $\rho = 0.162$, $p\_value = 0.0308$). The findings suggest satellite fire indicators and network performance metrics together can reveal vulnerabilities during extreme environmental events and support diaster response and recovery efforts.

This paper presents a comparative AC Optimal Power Flow study on a real world city scale islanded microgrid with high solar PV penetration, implemented within a Digital Twin framework. Four objective function cases economic dispatch, voltage stress exposure via PV power factor variation, then optimal load delivery, and capacitor enhanced economic dispatch as recovery options are evaluated over a 47 hour time series horizon on the same network under a shared loading scenario. Optimization sensitivities OSQ and OSV extracted from all cases are combined into a composite placement score used to rank candidate buses for shunt capacitor upgrades. A post processing planning optimization balances capacitor upgrade cost against avoided value-of-lost-load, enabling direct economic comparison of infrastructure investment versus reliability penalties. Results demonstrate that sensitivity guided capacitor placement restores full load service across the horizon and provides targeted reactive support at a quantifiable cost trade off against corrective load shedding.

Resilience in cyber-physical systems (CPS) is the fundamental ability to maintain safety and critical functionality despite adverse "perturbations," which includes security attacks, environmental disruptions, and hardware or software failures. This survey provides a comprehensive review of CPS resilience, framing the field through five interconnected themes that are required in an integrated whole to achieve real-world resilience. The article first posits that resilience is a system-wide property emerging from interactions between hardware, software, and human users. Second, it addresses the challenges of learning-enabled CPS, which often operate in data-scarce environments characterized by imbalanced or noisy data, requiring innovative solutions like synthetic data generation and foundation model adaptation. Third, the survey examines proactive measures for resilience, which include distinctive aspects of verification, testing, and redundancy. Fourth, it explores recovery mechanisms, moving beyond traditional fault models to design "just good enough" recovery strategies that prioritize safety-critical functions during perturbations. Finally, it highlights the central role of the human, focusing on the different levels of human intervention, the necessity of trust calibration, and the requirement for explainable AI to support human-CPS teaming. These themes are illustrated through representative application domains, primarily Connected and Autonomous Transportation Systems (CATS) and Medical CPS (MCPS). By integrating the five interconnected themes, this survey provides a systematic roadmap for achieving the resilient CPS in increasingly complex and adversarial environments.

This study investigates whether speech-based depression detection models learn depression-related acoustic biomarkers or instead rely on speaker identity cues. Using the DAIC-WOZ dataset, we propose a data-splitting strategy that controls speaker overlap between training and test sets while keeping the training size constant, and evaluate three models of varying complexity. Results show that speaker overlap significantly boosts performance, whereas accuracy drops sharply on unseen speakers. Even with a Domain-Adversarial Neural Network, a substantial performance gap remains. These findings indicate that depression-related features extracted by current speech models are highly entangled with speaker identity. Conventional evaluation protocols may therefore overestimate generalization and clinical utility, highlighting the need for strictly speaker-independent evaluation.

To address high data traffic demands of sixth-generation (6G) networks, this paper proposes a novel architecture that integrates autonomous aerial vehicles (AAVs) and multi-functional reconfigurable intelligent surfaces (MF-RISs) as AM-RIS in fluid antenna (FA)-assisted full-duplex (FD) networks. The AM-RIS provides hybrid functionalities, including signal reflection, amplification, and energy harvesting (EH), potentially improving both signal coverage and sustainability. Meanwhile, FA facilitates fine-grained spatial adaptability at FD-enabled base station (BS), which complements residual self-interference (SI) suppression. We aim at maximizing the overall energy efficiency (EE) by jointly optimizing transmit DL beamforming at BS, UL user power, configuration of AM-RIS, and positions of the FA and AM-RIS. Owing to the hybrid continuous-discrete parameters and high dimensionality of the intractable problem, we have conceived a self-optimized multi-agent hybrid deep reinforcement learning (DRL) framework (SOHRL), which integrates multi-agent deep Q-networks (DQN) and multi-agent proximal policy optimization (PPO), respectively handling discrete and continuous actions. To enhance self-adaptability, an attention-driven state representation and meta-level hyperparameter optimization are incorporated, enabling multi-agents to autonomously adjust learning hyperparameters. Simulation results validate the effectiveness of the proposed AM-RIS-enabled FA-aided FD networks empowered by SOHRL algorithm. The results reveal that SOHRL outperforms benchmarks of the case without attention mechanism and conventional hybrid/multi-agent/standalone DRL. Moreover, AM-RIS in FD achieves the highest EE compared to half-duplex, conventional rigid antenna arrays, partial EH, and conventional RIS without amplification, highlighting its potential as a compelling solution for EE-aware wireless networks.

The combination of control barrier functions (CBFs) and adaptive control – a framework referred to as adaptive safety – has proven to be a powerful paradigm for safety-critical control of nonlinear systems with parametric uncertainties. Yet the theoretical conditions for forward invariance within this framework are often quite conservative, and may require using large adaptation gains to achieve acceptable performance, an approach that is traditionally discouraged in adaptive control. This paper mitigates these issues via high-order tuners, a recent class of higher-order adaptation laws that leverages different adaptation gains at different orders of differentiation. We illustrate that these high-order tuners decouple adaptation gain conditions from those placed on the initial conditions of the system required for set invariance. We extend these results to robotic systems whose linear-in-the-parameters structure proves particularly useful for adaptive control. The efficacy of our results are illustrated via simulations.

Functional magnetic resonance imaging (fMRI) is widely used for studying and diagnosing brain disorders, with functional connectivity (FC) matrices providing powerful representations of large-scale neural interactions. However, existing diagnostic models are trained either on a single site or under full multi-site access, making them unsuitable for real-world scenarios where clinical data arrive sequentially from different institutions. This results in limited generalization and severe catastrophic forgetting. This paper presents the first continual learning framework specifically designed for fMRI-based diagnosis across heterogeneous clinical sites. Our framework introduces a structure-aware variational autoencoder that synthesizes realistic FC matrices for both patient and control groups. Built on this generative backbone, we develop a multi-level knowledge distillation strategy that aligns predictions and graph representations between new-site data and replayed samples. To further enhance efficiency, we incorporate a hierarchical contextual bandit scheme for adaptive replay sampling. Experiments on multi-site datasets for major depressive disorder (MDD), schizophrenia (SZ), and autism spectrum disorder (ASD) show that the proposed generative model enhances data augmentation quality, and the overall continual learning framework substantially outperforms existing methods in mitigating catastrophic forgetting. Our code is available at https://github.com/4me808/FORGE.

In this paper, we propose a novel framework for the joint identification of system dynamics and noise covariance in linear systems, under general noise distributions beyond Gaussian. Specifically, we would like to simultaneously estimate the dynamical matrix $A$ and the noise covariance matrix $\varSigma$ using state transition data. The formulation builds upon a novel parameterization of the state-transition distribution, which enables more effective use of distributional "shape" information for improved identification accuracy. We introduce two practical estimators, namely the maximum likelihood estimator (MLE) and the score-matching estimator (SME), to solve the joint dynamics-covariance identification problem, and provide rigorous analysis of their statistical properties and sample complexity. Simulation results show that the proposed estimators outperform the ordinary least squares (OLS) baseline.

A mode sorter separates a set of M orthogonal spatial modes in a shared input channel into M different output channels. Here we present an analytic derivation and experimental validation of a single plane device for sorting spatial modes from a diverse variety of mode families, including Hermite-Gaussian (HG), Laguerre-Gaussian (LG), Bessel-Gaussian (BG), with almost no cross-talk. This sorting capability is required for a wide range of applications that employ classical or quantum light. We also show that applying this design in order to sort a set of Orbital Angular Momentum (OAM) modes with zero radial index reproduces the well-known Fork grating configuration. Furthermore, by taking the limit of M -> inf, we present an analytical expression for sorting all the modes of a given family. By operating this device in reverse, it can be used to generate arbitrary modes, by illuminating it with a Gaussian beam. The power transmission coefficient for this sorter goes as 1/M and we provide a mathematical proof that this is optimal for any typical arrangement of the detector positions. We further study the sorter sensitivity to wavelength and random phase noise.

Designing robust architectures that can mitigate sophisticated attacks is now a key priority for modern wireless systems. This paper investigates a single-cell bistatic integrated sensing and communication (ISAC) network facing simultaneous coordinated active jamming and malicious detection. These threats aim to disrupt the downlink communication and detect the presence of the ISAC target, respectively. To counter these attacks, we propose the SAFE-ISAC framework, which utilizes a simultaneous transmit and reflect reconfigurable intelligent surface (STAR-RIS) to jointly suppress jamming power and reduce the malicious detector's Signal-to-Interference-plus-Noise Ratio (SINR). We formulate a joint minimization problem for jamming gain and detection probability by optimizing the STAR-RIS reflection and transmission responses. This non-convex problem is decoupled into two subproblems: i) malicious detection mitigation in the transmission subspace, solved using the Dinkelbach method and Semidefinite Programming (SDP) relaxation, and ii) jamming suppression in the reflection subspace, addressed via Polak-Reibére Riemannian conjugate gradient algorithm. Numerical results validate that the proposed scheme effectively achieves jamming mitigation and target concealment while meeting all communication and sensing Quality-of-Service (QoS) requirements, compared to existing benchmarks.

We promote in this paper the processing of radar data in the frequency domain to achieve higher robustness against noise and structural errors, especially in comparison to feature-based methods. This holds also for high dynamics in the scene, i.e., ego-motion of the vehicle with the sensor plus the presence of an unknown number of other moving objects. In addition to the high robustness, the processing in the frequency domain has the so far neglected advantage that the underlying correlation based methods used for, e.g., registration, provide information about all moving structures in the scene. A typical automotive application case is overtaking maneuvers, which in the context of autonomous racing are used here as a motivating example. Initial experiments and results with Fourier SOFT in 2D (FS2D) are presented that use the Boreas dataset to demonstrate radar-only-odometry, i.e., radar-odometry without sensor-fusion, to support our arguments.

Oil spills represent a severe threat, making early-stage thickness estimation crucial for guiding remediation efforts. Unmanned Aerial Vehicles (UAVs) are an attractive platform for environmental monitoring. However, due to their limited computation and power budgets, real-time onboard processing requires optimized algorithms or lightweight machine learning models. While the standard U-Net architecture is often too large for constrained UAV hardware, the compressed Tiny U-Net variant fits on FPGA platforms and achieves competitive estimation performance (0.79 in the metric Intersection over Union, or IoU). Despite this success, Tiny U-Net processes every radar image through the complete inference pipeline, resulting in unnecessary computation for simple cases. To address this inefficiency, we integrate an early exit feature into the Tiny U-Net architecture. We introduce an early exit branch that returns an early prediction when a compact confidence score exceeds a tunable threshold, bypassing deeper layers for high-confidence evaluations. Our experiments demonstrate that this design achieves comparable IoU to the full baseline model. Crucially, the technique is shown to reduce the average number of multiplications by up to 42% for an aggressive threshold, reducing the dynamic power consumption. Choosing a threshold that ensures extreme confidence reduces the complexity-reduction gains for an improved IoU. This early exit approach substantially improves computational efficiency in Tiny U-Net, enabling more practical deployment in UAV-based environmental monitoring systems.

The rise of Artificial Intelligence (AI)-driven services, machine-type communications, and massive Internet of Things (IoT) deployments is reshaping wireless traffic toward dense, uplink-oriented, bursty, and latency-critical patterns. In these regimes, Multi-User Multiple-Input Multiple-Output (MU-MIMO) is essential to support massive concurrent connectivity through spatial multiplexing. However, the need for frequent, low-latency scheduling decisions exposes fundamental scalability barriers in existing user selection approaches. The inherently combinatorial nature of MU-MIMO user selection leads computational complexity to grow rapidly with both the number of candidate users and spatial layers, rendering existing near-optimal heuristic methods impractical in dense and highly dynamic scenarios. This paper introduces the Space Splitting-based User Selection (SS-US) algorithm, a complexity barrier-breaking, massively parallelizable method that departs from subset-based selection by constructing orthonormal spatial bases and independently matching users to spatial directions. Simulation results across diverse MIMO configurations, channel conditions, and user densities show that SS-US reduces computational complexity by over three orders of magnitude while achieving spectral efficiency comparable to state-of-the-art practical baselines.

Crack segmentation on edge devices can support continuous infrastructure monitoring and maintenance and thereby help to preserve public safety. Furthermore, autonomous infrastructure monitoring by using Unmanned Aerial Vehicles (UAVs) can reduce inspection risks, as human operators no longer need to enter hazardous areas. Edge processing reduces the cost of inspection by eliminating the need for high resolution image storage for offline processing and mitigates the security risks and bandwidth requirements of streaming to cloud servers. Edge inference is difficult due to the limited memory and computational capabilities of edge devices, which can affect both accuracy and latency. Furthermore, battery-powered devices are subject to strict power and energy constraints. Together, these limitations impose restrictions on the model size and computational complexity that can be deployed close to the sensor. In recent years, Transformers have achieved state-of-the-art accuracy in a variety of applications, including semantic segmentation. However, Transformer-based models are typically large and computationally intensive, making efficient edge deployment difficult. To address this, we first apply knowledge distillation to enhance the performance of the base models. We then use PTQ to compress the models further. Additionally, we consider the deployment of these models across multiple edge platforms. To maximize energy efficiency, we design and implement a custom hardware architecture for the models on an FPGA. Our results show that Knowledge Distillation (KD) improves all tested U-Net variants. Among the evaluated platforms, the selected FPGA implementation achieves 398 FPS at 204.99 Frames/J while maintaining a mean IoU of 69.42%. In addition, our best model reaches 71.92% mean IoU, which is 8.82 percentage points (pps) higher than the previously reported result on the CrackVision12K dataset.

The increasing penetration of Distributed Energy Resources (DERs), particularly electric vehicles, heat pumps, and photovoltaic systems, is fundamentally changing power flows in Low-Voltage (LV) distribution networks. Despite this transition, Distribution System Operators (DSOs) often lack reliable and up-to-date knowledge of the DER capacity connected downstream of LV substations. Limited observability, incomplete topology information, and restricted access to customer-level data make it difficult to maintain accurate DER registries, creating uncertainty in both operational and planning processes. This paper presents aggregated DER installed capacity, estimated at LV aggregation points, as a practical and scalable approach to improving DER awareness without requiring customer-level monitoring. We define the problem of estimating DER installed capacities from commonly available substation and feeder measurements. By linking these estimates to operational and planning needs, we discuss how knowledge of aggregated DER installed capacity enhances DER-aware forecasting, congestion management, flexibility quantification, hosting capacity assessment, and monitoring of DER adoption.

Future mobile networks must achieve substantial improvements in energy efficiency to offset the anticipated traffic growth. Despite this requirement, many discussions regarding physical layer design remain primarily focused on peak data rates and spectral efficiency, even though typical network operation is dominated by low-data-rate regimes. To address this mismatch, the Gearbox-PHY was proposed as an energy-efficient physical layer architecture that dynamically switches between modulation schemes and their associated analog front ends in order to adapt to varying operating requirements. This paper quantifies the achievable energy savings by jointly modeling front end power consumption and hardware-aware spectral efficiency to formulate an energy-per-bit minimization problem. To move beyond idealized assumptions, non-ideal hardware effects, including oscillator phase noise and limited quantizer resolution, are incorporated. These impairments simultaneously affect power consumption and achievable spectral efficiency, thereby introducing trade-offs between front end complexity, hardware non-linearities, spectral efficiency, and energy efficiency. Numerical results demonstrate that the Gearbox-PHY enables significant energy savings, particularly at low data rates. Evaluations with spatially distributed users confirm that gains of up to two orders of magnitude persist in a cellular deployment scenario.

A rigid motion in $\mathbb{R}^d$ consists of a proper rotation and a translation, and it can be represented as a matrix in $\mathbb{R}^{(d+1)\times (d+1)}$. The problem of rigid motion synchronization aims to estimate a collection of rigid motions $G^*_1, \dots, G^*_n$ from noisy observations of their comparisons ${G^*_i}^{-1} G^*_j$. Such problems naturally arise in diverse applications across signal processing, robotics, and computer vision, and have thus attracted intense research attention in recent years. Motivated by geometric considerations, this paper develops a novel spectral approach for rigid motion synchronization, called the anchored spectral estimator (ASE). Theoretically, we establish uniform estimation error bounds for the estimators produced by ASE. Empirically, we show that ASE outperforms the widely used two-stage approach, which first estimates the rotations and then the translations. Further numerical experiments on the multiple point-set registration problem are presented to demonstrate the superiority of ASE over state-of-the-art methods.

Automated driving at unsignalized intersections is challenging due to complex multi-vehicle interactions and the need to balance safety and efficiency. Model Predictive Control (MPC) offers structured constraint handling through optimization but relies on hand-crafted rules that often produce overly conservative behavior. Deep Reinforcement Learning (RL) learns adaptive behaviors from experience but often struggles with safety assurance and generalization to unseen environments. In this study, we present an integrated MPC-RL framework to improve navigation performance in multi-agent scenarios. Experiments show that MPC-RL outperforms standalone MPC and end-to-end RL across three traffic-density levels. Collectively, MPC-RL reduces the collision rate by 21% and improves the success rate by 6.5% compared to pure MPC. We further evaluate zero-shot transfer to a highway merging scenario without retraining. Both MPC-based methods transfer substantially better than end-to-end PPO, which highlights the role of the MPC backbone in cross-scenario robustness. The framework also shows faster loss stabilization than end-to-end RL during training, which indicates a reduced learning burden. These results suggest that the integrated approach can improve the balance between safety performance and efficiency in multi-agent intersection scenarios, while the MPC component provides a strong foundation for generalization across driving environments. The implementation code is available open-source.

Synchronized radio telescope-based experiments conducted since 2017, together with subsequent interferometer experiments, provide evidence of an anomalous source of 3.7 Hz bandwidth pulses, sourced from near the direction of the star Rigel. The current experiment, reported here, uses a two-element phase-measuring interferometer to monitor the hypothetical pulse source across azimuths within the beam-widths of the elements of a south-facing interferometer. 123 days of phase measurements of 3.7 Hz bandwidth pulse pairs, adds to the prior evidence that the pulsing signal source has celestial origin. Associated measurements of noise power in 954 Hz and 50 MHz bandwidths, made simultaneous with the 0.27 second duration pulse pair measurements, are presented. Measurement results are presented to aid in the development of independent experimental replication, and alternate and auxiliary explanatory hypotheses.

The growing proliferation of unmanned aerial vehicles (UAVs) poses major challenges for reliable airspace surveillance, as drones are typically small, have low radar cross-sections, and often move slowly in cluttered environments. These characteristics make the joint tasks of detecting, localizing, and tracking multiple objects difficult for conventional detect-then-track (DTT) approaches, which rely on pre-processed measurements and may discard informative low-signal-to-noise ratio (SNR) signal components. To overcome these limitations, we propose a variational message passing (VMP)-based direct multiobject tracking (MOT) method that operates directly on raw radar signals and explicitly accounts for an unknown and time-varying number of objects. The proposed method is formulated for MIMO multi-radar systems and performs data fusion by jointly processing the signals of all radar sensors using a probabilistic model. A superimposed signal model is employed to capture correlations in the raw sensor data caused by closely spaced objects, and a hierarchical Bernoulli-Gamma model is introduced to jointly model object existence, reflectivities, and the reliability of individual radar-object links. Using a mean-field approximation, we derive message updates, yielding a computationally efficient VMP algorithm that simultaneously performs object detection, track formation, state estimation, and nuisance parameter learning directly from the radar signal. Simulation results in synthetic scenarios with weak and closely-spaced objects show that the proposed direct-MOT method outperforms a conventional pipeline based on super-resolution estimation followed by belief propagation (BP)-based tracking, particularly in low-SNR and clutter-rich conditions, demonstrating the advantages of direct signal-level inference and coherent multi-radar fusion.

Odrzywolek (2026) recently introduced the Exp-Minus-Log (EML) operator eml (x, y) = exp(x) - ln(y) and proved constructively that, paired with the constant 1, it generates the entire scientific-calculator basis of elementary functions; in this sense EML is to continuous mathematics what NAND is to Boolean logic. We investigate whether such a uniform single-operator representation can accelerate either the forward simulation or the parameter identification of a six-branch RC equivalent-circuit model (6rc ECM) of a lithium-ion battery cell. We give the analytical EML rewrite of the discretized state-space recursion, derive an exact operation count, and quantify the depth penalty of the master-formula construction used for gradient-based symbolic regression. Our analysis shows that direct EML simulation is slower than the classical exponential-Euler scheme (a ~ 25x instruction overhead per RC branch), but EML-based parametrization offers a structurally complete, gradient-differentiable basis that competes favourably with non-parametric DRT deconvolution and metaheuristic optimisation when the cardinality of RC branches is unknown a priori. We conclude with a concrete recommendation: use EML only on the parametrization side of the 6rc workflow, keeping the classical recursion at runtime.

Deep neural networks (DNNs) deliver state-of-the-art accuracy on regression and classification tasks, yet two structural deficits persistently obstruct their deployment in safety-critical, resource-constrained settings: (i) opacity of the learned function, which precludes formal verification, and (ii) reliance on heterogeneous, library-bound activation functions that inflate latency and silicon area on edge hardware. The recently introduced Exp-Minus-Log (EML) Sheffer operator, eml(x, y) = exp(x) - ln(y), was shown by Odrzywolek (2026) to be sufficient - together with the constant 1 - to express every standard elementary function as a binary tree of identical nodes. We propose to embed EML primitives inside conventional DNN architectures, yielding a hybrid DNN-EML model in which the trunk learns distributed representations and the head is a depth-bounded, weight-sparse EML tree whose snapped weights collapse to closed-form symbolic sub-expressions. We derive the forward equations, prove computational-cost bounds, analyse inference and training acceleration relative to multilayer perceptrons (MLPs) and physics-informed neural networks (PINNs), and quantify the trade-offs for FPGA/analog deployment. We argue that the DNN-EML pairing closes a literature gap: prior neuro-symbolic and equation-learner approaches (EQL, KAN, AI-Feynman) work with heterogeneous primitive sets and do not exploit a single hardware-realisable Sheffer element. A balanced assessment shows that EML is unlikely to accelerate training, and on commodity CPU/GPU it is also unlikely to accelerate inference; however, on a custom EML cell (FPGA logic block or analog circuit) the asymptotic latency advantage can reach an order of magnitude with simultaneous gain in interpretability and formal-verification tractability.

We propose a matrix zonotope perturbation framework that leverages matrix perturbation theory to characterize how noise-induced distortions alter the dynamics within sets of models. The framework derives interpretable Cai-Zhang bounds for matrix zonotopes (MZs) and extends them to constrained matrix zonotopes (CMZs). Motivated by this analysis and the computational burden of CMZ-based reachable-set propagation, we introduce a coefficient-space approximation in which the constrained coefficient space of the CMZ is over-approximated by an unconstrained zonotope. Replacing CMZ-constrained-zonotope (CZ) products with unconstrained MZ-zonotope multiplication yields a simpler and more scalable reachable-set update. Experimental results demonstrate that the proposed method is substantially faster than the standard CMZ approach while producing reachable sets that are less conservative than those obtained with existing MZ-based methods, advancing practical, accurate, and real-time data-driven reachability analysis.