Papers

In real underwater environments, downstream image recognition tasks such as semantic segmentation and object detection often face challenges posed by problems like blurring and color inconsistencies. Underwater image enhancement (UIE) has emerged as a promising preprocessing approach, aiming to improve the recognizability of targets in underwater images. However, most existing UIE methods mainly focus on enhancing images for human visual perception, frequently failing to reconstruct high-frequency details that are critical for task-specific recognition. To address this issue, we propose a Downstream Task-Inspired Underwater Image Enhancement (DTI-UIE) framework, which leverages human visual perception model to enhance images effectively for underwater vision tasks. Specifically, we design an efficient two-branch network with task-aware attention module for feature mixing. The network benefits from a multi-stage training framework and a task-driven perceptual loss. Additionally, inspired by human perception, we automatically construct a Task-Inspired UIE Dataset (TI-UIED) using various task-specific networks. Experimental results demonstrate that DTI-UIE significantly improves task performance by generating preprocessed images that are beneficial for downstream tasks such as semantic segmentation, object detection, and instance segmentation. The codes are publicly available at https://github.com/oucailab/DTIUIE.

Continuum robots possess high flexibility and redundancy, making them well suited for safe interaction in complex environments, yet their continuous deformation and nonlinear dynamics pose fundamental challenges to perception, modeling, and control. Existing vision-based control approaches often rely on end-to-end learning, achieving shape regulation without explicit awareness of robot geometry or its interaction with the environment. Here, we introduce a shape-interpretable visual self-modeling framework for continuum robots that enables geometry-aware control. Robot shapes are encoded from multi-view planar images using a Bezier-curve representation, transforming visual observations into a compact and physically meaningful shape space that uniquely characterizes the robot's three-dimensional configuration. Based on this representation, neural ordinary differential equations are employed to self-model both shape and end-effector dynamics directly from data, enabling hybrid shape-position control without analytical models or dense body markers. The explicit geometric structure of the learned shape space allows the robot to reason about its body and surroundings, supporting environment-aware behaviors such as obstacle avoidance and self-motion while maintaining end-effector objectives. Experiments on a cable-driven continuum robot demonstrate accurate shape-position regulation and tracking, with shape errors within 1.56% of image resolution and end-effector errors within 2% of robot length, as well as robust performance in constrained environments. By elevating visual shape representations from two-dimensional observations to an interpretable three-dimensional self-model, this work establishes a principled alternative to vision-based end-to-end control and advances autonomous, geometry-aware manipulation for continuum robots.

Detecting weak signals buried in complex, non-Gaussian noise is a fundamental challenge in science and engineering, with applications ranging from radar systems and communications to industrial monitoring and gravitational wave detection. The Rao detector, a key concept in this domain, achieves asymptotically optimal performance as the number of measurements increases, but requires precise knowledge of the data's statistical properties, often relying on simplified noise models. We propose a hybrid framework that combines a lightweight neural network with the Rao detection framework to address this limitation. The neural network, trained on noise-only data, learns the optimal multivariate nonlinearity, transforming noisy data to enhance signal detectability. The newly introduced LRao detector then fully extracts the signal information, achieving asymptotically optimal performance even under challenging noise conditions. Validated on both simulated and real-world magnetic sensor data, our method significantly outperforms conventional approaches. By bridging data-driven techniques with model-based signal processing, it offers a robust and interpretable solution for signal detection across diverse applications.

The use of Intelligent Reflective Surfaces (IRS) to assist communication and sensing has proven cost-effective in challenging scenarios. For sensing, IRS is shown to sense non-line-of-sight (NLOS) and stealth targets, albeit with significant loss due to the four-hop path model. Amongst the available IRS-assisted configurations, we consider a three-hop model in which the IRS redirects the scattered target response towards the mono-static radar. With the IRS spatially displaced from the radar, this configuration mimics a bi-static radar. While target detection has been studied in this configuration, parameter estimation has not been investigated to date. To this end, we first develop the signal model for this configuration and derive the CRB for target parameters. The dependence of CRB on system parameters such as SNR, number of snapshots, number of IRS elements and their weights is brought forward through extensive simulations. This study can enable a designer to customize the system parameters to meet the requirements. It also serves as a benchmark for parameter estimation techniques developed for this configuration.

Ray tracing has become a standard for accurate radio propagation modeling, but suffers from exponential computational complexity, as the number of candidate paths scales with the number of objects raised to the interaction order. This bottleneck limits its use in large-scale or real-time applications, forcing traditional tools to rely on heuristics that reduce path candidates at the cost of potentially reduced accuracy. To overcome this limitation, we propose a machine-learning-assisted framework that replaces exhaustive path searching with intelligent sampling via Generative Flow Networks. Applying these generative models to this domain presents challenges, particularly sparse rewards due to the rarity of valid paths, which can lead to convergence failures and trivial solutions when evaluating high-order interactions in complex environments. To ensure robust learning and efficient exploration, our framework incorporates three key components. First, an experience replay buffer captures and retains rare valid paths. Second, a uniform exploratory policy improves generalization and prevents overfitting to simple geometries. Third, a physics-based action masking strategy filters out physically impossible paths before the model considers them. Validated on idealized street-canyon scenarios, our model achieves substantial speedups over exhaustive search – up to $10\times$ faster on GPU and $100\times$ faster on CPU – while maintaining high coverage accuracy and successfully uncovering complex propagation paths. However, out-of-distribution evaluations on real-world Manhattan street geometries reveal that generalizing to substantially different urban morphologies requires further advancement in model capacity or alternative training strategies. Source code, tests, and a tutorial are available at https://github.com/jeertmans/sampling-paths.

In this paper, we investigate the coordination of vehicle maneuvers in mixed-traffic corridors where connected and automated vehicles, human-driven vehicles, and buses interact under dedicated bus lane operations. We develop a segment-based network coordination framework that jointly optimizes lane-change and routing decisions of connected and automated vehicles to improve dedicated lane utilization while preserving bus priority. The proposed framework incorporates a predictive bus-protection mechanism that restricts vehicle access to protected lane segments within a monitoring horizon, together with a utility-driven lane-change strategy that accounts for anticipated travel time gains, downstream routing feasibility, and lane-change stability. By explicitly coupling network-level routing decisions with lane-level interaction control, the method proactively mitigates conflicts on dedicated lanes before congestion effects materialize. The proposed approach is evaluated through microscopic traffic simulations in SUMO using a realistic urban corridor. Simulation results demonstrate that the framework enhances bus schedule adherence and reduces average travel times for both automated and human-driven vehicles, while maintaining stable lane-change behavior without increasing maneuver frequency.

We propose a block least mean square (LMS) algorithm to monitor the longitudinal power profile of a fiber-optic link through receiver-based digital data from a coherent detector. Compared to the benchmark least squares (LS) method, the proposed algorithm does not require large matrix inversions or batch processing, thus allowing the received data to be processed in blocks of minimum size by an overlap-save algorithm, reducing complexity and latency. We propose an efficient implementation of the method with a stochastic gradient update leveraging a key computation in the frequency domain, offering computational savings over state-of-the-art monitoring techniques. We test the proposal in different scenarios by means of numerical simulations.

The growing integration of electric vehicle (EV) fleets into transportation services and energy systems requires accurate modeling of battery discharge and state-of-charge (SoC) evolution to ensure reliable vehicle operation and grid coordination. Existing approaches face a trade-off between interpretable but simplified physics-based models and data-driven methods that demand large datasets and may lack physical consistency. In this paper, we propose a hybrid physics-based residual learning framework for EV battery discharge modeling. A vehicle dynamics model based on force-balance equations provides an interpretable baseline estimate of energy consumption and SoC evolution, capturing aerodynamic drag, rolling resistance, and regenerative braking. A neural network residual learner then corrects discrepancies caused by complex factors such as traffic conditions and driver behavior. Experimental results on $1,500$ trip scenarios demonstrate that the proposed approach reduces the mean absolute percentage error to approximately $0.8\%$, significantly outperforming physics-only models while preserving physical interpretability and computational efficiency.

Inertial sensors can track object kinematics, however, unbounded drift from integrating noisy signals makes them impractical for MRI motion correction at millimeter resolution and minute-long scans. We introduce MR-Compass, which exploits the MRI system's static magnetic and gravitational fields to estimate 3-DOF orientation at 2 kHz directly, without integration, eliminating random-walk. The remaining 3-DOF translation is recovered via phase correlation from the MRI data. We experimentally validate the efficacy of the method retrospectively using a 3D radial koosh-ball sequence and prospectively using 2D EPI fMRI during large volunteer motions. MR-Compass followed by phase-correlation achieved a mean accuracy of 0.6$^o$ and 0.4 pixels across all experiments. Image quality improved when motion correction was applied in all volunteer scans for both retrospective and prospective correction cases. MR-Compass was effective in measuring head motion in the MRI scanner with high accuracy at unprecedented sample rates, and enabled both retrospective and prospective reconstruction to improve image quality by aligning the k-space data appropriately and by reducing the motion related artifacts.

Text-to-audio (T2A) generation has advanced considerably in recent years, yet existing methods continue to face challenges in accurately rendering complex text prompts, particularly those involving intricate audio effects, and achieving precise text-audio alignment. While prior approaches have explored data augmentation, explicit timing conditioning, and reinforcement learning, overall synthesis quality remains constrained. In this work, we experiment with reinforcement learning to further enhance T2A generation quality, building on diffusion transformer (DiT)-based architectures. Our method first employs a large language model (LLM) to generate high-fidelity, richly detailed audio captions, substantially improving text-audio semantic alignment, especially for ambiguous or underspecified prompts. We then apply Group Relative Policy Optimization (GRPO), a recently introduced reinforcement learning algorithm, to fine-tune the T2A model. Through systematic experimentation with diverse reward functions (including CLAP, KL, FAD, and their combinations), we identify the key drivers of effective RL in audio synthesis and analyze how reward design impacts final audio quality. Experimental results demonstrate that GRPO-based fine-tuning yield substantial gains in synthesis fidelity and prompt adherence.

End-to-end speech large language models (LLMs) often answer the same question less accurately from speech than from text, even when the spoken content matches the text prompt. Existing analyses study this modality gap through the geometry of representations and measure how closely speech representations align with text. Geometric alignment gives the gap a measurable form, but it does not show whether the model uses aligned representations in the same way. This work connects representation geometry with answer formation and asks whether geometric alignment implies functional equivalence. We compare cross-layer Centered Kernel Alignment (CKA) with layer-wise answer margins for four open-weight speech LLMs on SpeechMMLU and VoiceBench BBH. In Qwen2.5-Omni and MiniCPM-o, speech and text representations align in middle layers while their late-layer answer margins still differ, so mid-layer alignment does not imply functional equivalence. Qwen2-Audio instead shows weak alignment, which indicates a different failure mode. An attention intervention at fixed input and token count identifies a causal effect of late attention allocation on answer-code separation, a quantity distinct from answer correctness. Compressing the speech signal or its token sequence repairs a subset of the errors that occur only with speech.

Graph signal processing extends spectral analysis to data supported on irregular domains. Existing fractional transforms for two-dimensional graph signals, including the two-dimensional graph fractional Fourier transform (GFRFT), typically impose a shared fractional order across dimensions, which limits adaptivity to heterogeneous spatiotemporal spectra. To address this limitation, we propose the two-dimensional graph bi-fractional Fourier transform, which assigns independent fractional orders to the factor graphs of a Cartesian product, enabling decoupled spectral control while preserving separability, unitarity, and invertibility. To further resolve the basis ambiguity in temporal fractional analysis, we develop a geodesic-coupled GFRFT by constructing a coupling path along the principal geodesic on the unitary manifold, thereby unifying graph-induced and discrete temporal bases with guaranteed unitarity and a closed-form inverse. Building on these transforms, we derive a differentiable Wiener-type filtering framework with a hybrid optimization strategy: the fractional orders are learned end-to-end from data, while the coupling parameter is fixed as a structural regularizer. Experiments on real-world time-varying graph datasets and dynamic image restoration tasks demonstrate consistent gains over state-of-the-art fractional transforms and competitive learning-based baselines.

Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained outside these efforts. In this work, we introduce Spoof-SUPERB, a benchmark for audio deepfake detection that systematically evaluates 20 SSL models spanning generative, discriminative, and spectrogram-based architectures. We evaluated these models on multiple in-domain and out-of-domain datasets. Our results reveal that large-scale discriminative models such as XLS-R, UniSpeech-SAT, and WavLM Large consistently outperform other models, benefiting from multilingual pretraining, speaker-aware objectives, and model scale. We further analyze the robustness of these models under acoustic degradations, showing that generative approaches degrade sharply, while discriminative models remain resilient. This benchmark establishes a reproducible baseline and provides practical insights into which SSL representations are most reliable for securing speech systems against audio deepfakes.

Neural audio codec (NAC) is essential for reconstructing high-quality speech signals and generating discrete representations for downstream speech language models. However, ensuring accurate semantic modeling while maintaining high-fidelity reconstruction under ultra-low bitrate constraints remains challenging. We propose an entropy-guided group residual vector quantization (EG-GRVQ) for an ultra-low bitrate neural speech codec, which retains a semantic branch for linguistic information and incorporates an entropy-guided grouping strategy in the acoustic branch. Assuming that channel activations follow approximately Gaussian statistics, the variance of each channel can serve as a principled proxy for its information content. Based on this assumption, we partition the encoder output such that each group carries an equal share of the total information. This balanced allocation improves codebook efficiency and reduces redundancy. Trained on LibriTTS and VCTK, our model shows improvements in perceptual quality and intelligibility metrics under ultra-low bitrate conditions, with a focus on codec-level fidelity for communication-oriented scenarios.

Evaluation of conversational naturalness is essential for developing human-like speech agents. However, existing speech naturalness predictors are often designed to assess utterances from a single speaker, failing to capture conversation-level naturalness qualities. In this paper, we present a framework for an automatic naturalness predictor for two-speaker, multi-turn conversations. We first show that existing naturalness estimators have low, or sometimes even negative, correlations with conversational naturalness, based on conversational recordings annotated with human ratings. We then propose a dual-channel naturalness estimator, in which we investigate multiple pre-trained encoders with data augmentation. Our proposed model achieves substantially higher correlation with human judgments compared to existing naturalness predictors for both in-domain and out-of-domain conditions.

Global token mixing, implemented via self-attention or state-space sequence models, has become a popular model design choice for MRI restoration. However, MRI restoration tasks differ substantially in how their degradations vary over image and k-space domains, and in the degree to which global coupling is already imposed by physics-driven data consistency terms. In this work, we ask the question whether global token mixing is actually beneficial in each individual task across three representative settings: accelerated MRI reconstruction with explicit data consistency, MRI super-resolution with k-space center cropping, and denoising of clinical carotid MRI data with spatially heteroscedastic noise. To reduce confounding factors, we establish a controlled testbed comparing a minimal local gated CNN and its large-field variant, benchmarking them directly against state-of-the-art global models under aligned training and evaluation protocols. For accelerated MRI reconstruction, the minimal unrolled gated-CNN baseline is already highly competitive compared to recent token-mixing approaches in public reconstruction benchmarks, suggesting limited additional benefits when the forward model and data-consistency steps provide strong global constraints. For super-resolution, where low-frequency k-space data are largely preserved by the controlled low-pass degradation, local gated models remain competitive, and a lightweight large-field variant yields only modest improvements. In contrast, for denoising with pronounced spatially heteroscedastic noise, token-mixing models achieve the strongest overall performance, consistent with the need to estimate spatially varying reliability. In conclusion, our results demonstrate that the utility of global token mixing in MRI restoration is task-dependent, and it should be tailored to the underlying imaging physics and degradation structure.

This work establishes a rigorous connection between stability properties of discrete-time algorithms (DTAs) and corresponding continuous-time dynamical systems derived through $ O(s^r) $-resolution ordinary differential equations (ODEs). We show that for discrete- and continuous-time dynamical systems satisfying a mild error assumption, exponential stability of a common equilibrium with respect to the continuous time dynamics implies exponential stability of the corresponding equilibrium for the discrete-time dynamics, provided that the step size is chosen sufficiently small. We extend this result to common compact invariant sets. We prove that if an equilibrium is exponentially stable for the $ O(s^r) $-resolution ODE, then it is also exponentially stable for the associated DTA. We apply this framework to analyse the limit point properties of several prominent optimisation algorithms, including Two-Timescale Gradient Descent–Ascent (TT-GDA), Generalised Extragradient (GEG), Two-Timescale Proximal Point (TT-PPM), Damped Newton (DN), Regularised Damped Newton (RDN), and the Jacobian method (JM), by studying their $ O(1) $- and $ O(s) $-resolution ODEs. We show that under a proper choice of hyperparameters, the set of saddle points of the objective function is a subset of the set of exponentially stable equilibria of GEG, TT-PPM, DN, and RDN. We relax the common Hessian invariance assumption through direct analysis of the resolution ODEs, broadening the applicability of our results. Numerical examples illustrate the theoretical findings.

This report details our submission to the CHiME-9 MCoRec Challenge on recognizing and clustering multiple concurrent natural conversations within indoor social settings. Unlike conventional meetings centered on a single shared topic, this scenario contains multiple parallel dialogues–up to eight speakers across up to four simultaneous conversations–with a speech overlap rate exceeding 90%. To tackle this, we propose a multimodal cascaded system that leverages per-speaker visual streams extracted from synchronized 360 degree video together with single-channel audio. Our system improves three components of the pipeline by leveraging enhanced audio-visual pretrained models: Active Speaker Detection (ASD), Audio-Visual Target Speech Extraction (AVTSE), and Audio-Visual Speech Recognition (AVSR). The AVSR module further incorporates Whisper and LLM techniques to boost transcription accuracy. Our best single cascaded system achieves a Speaker Word Error Rate (WER) of 32.44% on the development set. By further applying ROVER to fuse outputs from diverse front-end and back-end variants, we reduce Speaker WER to 31.40%. Notably, our LLM-based zero-shot conversational clustering achieves a speaker clustering F1 score of 1.0, yielding a final Joint ASR-Clustering Error Rate (JACER) of 15.70%.

Koopman operator provides a general linear description of nonlinear systems, whose estimation from data (via extended dynamic mode decomposition) has been extensively studied. However, the elusiveness between the Koopman spectrum and the stability of equilibrium point poses a challenge to utilizing the Koopman operator for stability analysis, which further hinders the construction of a universal theory of Koopman-based control. In our prior work, we defined the Koopman operator on a reproducing kernel Hilbert space (RKHS) using a linear–radial product kernel, and proved that the Koopman spectrum is confined in the unit disk of the complex plane when the origin is an asymptotically stable equilibrium point. Building on this fundamental spectrum–stability relation, here we consider the problem of Koopman operator-based Lyapunov function estimation with a given decay rate function. The decay rate function and the Lyapunov function are both specified by positive operators on the RKHS and are related by an operator algebraic Lyapunov equation (ALE), whose solution exists uniquely. The error bound of such a Lyapunov function estimate, obtained via kernel extended dynamic mode decomposition (kEDMD), are established based on statistical learning theory and verified by a numerical study.

This paper investigates an extremely large-scale reconfigurable intelligent surface (XL-RIS) assisted near-field integrated sensing and communication (ISAC) system, where a multi-antenna base station (BS) simultaneously sends unicast data to multiple single-antenna communication users (CUs) and senses multiple targets (TGTs). The BS, CUs and TGTs are all assumed to be located in the near-field region of the XL-RIS. We aim to maximize the weighted sum rate (WSR) of all CUs, subject to the sensing beampattern gain constraint for each TGT, the transmit power constraint for the BS, and the unit modulus constraints on the XL-RIS phase shift. First, we develop a fractional programming (FP) based block coordinate descent (BCD) algorithm to obtain a locally optimal solution for such a non-convex joint design problem. Secondly, to address the high-dimensional spatial correlations and scalability of the XL-RIS near-field channels, we propose a customized graph neural network (GNN) scheme to generate the BS transmit beamforming variables and the XL-RIS reflecting coefficient vector for ISAC, where the near-field ISAC system is modeled as a heterogeneous graph comprising XL-RIS/CU/TGT nodes. The proposed GNN scheme can effectively learn the near-field channel state information (CSI) features, in which the message passing mechanism is employed to exchange CSI among these directly connected nodes in the graph. Furthermore, each XL-RIS/CU/TGT node maintains a feature vector for mapping to the BS transmit beamforming variables or the XL-RIS reflecting coefficient vector. Numerical results show that the proposed GNN-based beamforming design scheme achieves a better performance than the existing baselines, in terms of computational efficiency, feasibility, robustness, and the ability of generalization.

Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge: policy lag, which is the mismatch between the behavior policy generating data and the learning policy being updated. Policy lag can hinder the scaling of on-policy learning algorithms to larger problems. In this paper, we identify the sources of policy lag caused by distributed learning and high update frequency. We use the findings to propose total Variation-based Advantage aligned Constrained policy Optimization (\methodacronym) as a practical approach to mitigate policy lag. We empirically validate our method and show that it offers better robustness to policy lag in classic RL tasks and a modern RL for LLM math reasoning task.

Over the last decades, progress in modal analysis has enabled increasingly routine use of modal parameters for applications such as structural health monitoring and finite element model updating. For output-only identification, or Operational Modal Analysis (OMA), widely adopted approaches include Stochastic Subspace Identification (SSI) methods and the Natural Excitation Technique combined with the Eigensystem Realization Algorithm (NExT-ERA). Nevertheless, SSI-based techniques may become cumbersome on large systems, while NExT-ERA fitting can struggle when measurements are contaminated by noise. To alleviate these, this work investigates an OMA frequency-domain formulation for aeronautical structures by coupling the Loewner Framework (LF) with NExT, yielding the proposed NExT-LF method. The method exploits the computational efficiency of LF, due to the effectiveness of tangential interpolation, together with the impulse response function retrieval enabled by NExT. NExT-LF is assessed on two experimental benchmarks: the eXperimental BeaRDS 2 high-aspect-ratio wing main spar and an Airbus Helicopters H135 bearingless main rotor blade. The identified modal parameters are compared against available experimental references and results obtained via SSI with Canonical Variate Analysis and NExT-ERA. The results show that the modes identified by NExT-LF correlate well with benchmark data, particularly for high-amplitude tests and in the low-frequency range.

This paper investigates the use of relative cues for text-based target speech extraction (TSE). We first provide a theoretical justification for relative cues from the perspectives of human perception and label quantization, showing that relative cues preserve fine-grained distinctions that are often lost in absolute categorical representations for continuous-valued attributes. Building on this analysis, we propose a two-stage TSE framework in which a speech separation model first generates candidate sources, followed by a text-guided classifier that selects the target speaker based on embedding similarity. Within this framework, we train two separate classification models to evaluate the advantages of relative cues over independent cues in case of continuous-valued attributes, considering both classification accuracy and TSE performance. Experimental results show that (i) relative cues achieve higher overall classification accuracy and improved TSE performance compared with independent cues; (ii) the proposed two-stage framework substantially outperforms single-stage text-conditioned extraction methods on both signal-level and objective perceptual metrics; and (iii) in controlled target-selection comparisons, the all cues, random cues, and temporal order settings outperform the strong enrollment-audio selection based on ECAPA-TDNN speaker embeddings, while language and distance cues remain competitive. In the WHAM!-noise evaluation, textual cues also show strong noise robustness, while all cues, random cues, and gender are especially robust. These results demonstrate the practical value of textual cues when enrollment speech is unavailable or cannot be used due to privacy concerns. Further analysis reveals notable differences in discriminative power across cue types, providing insights into the effectiveness of different relative cues for TSE.

The 2026 Formula 1 technical regulations introduce a fundamental change to energy strategy: under a 50/50 internal combustion engine / battery power split with unlimited regeneration and a driver-controlled Override Mode, the optimal energy deployment policy depends not only on a driver's own state but on the hidden state of rival cars. This creates a Partially Observable Stochastic Game that cannot be solved by single-agent optimisation methods. We present a tractable two-layer inference and decision framework. The first layer is a 40-state Hidden Markov Model (HMM) that infers a probability distribution over each rival's ERS charge level (four modes: H, M, L_harvest, L_derate), Override Mode status, and tyre degradation state from six publicly observable telemetry signals. The second layer is a Deep Q-Network (DQN) policy that takes the HMM belief state as input and selects between energy deployment strategies. We formally characterise the counter-harvest trap, a deceptive strategy in which a car deliberately suppresses observable deployment signals to induce a rival into a failed attack, and show that detecting it requires belief-state inference over both ERS level and the harvest/derate sub-mode. On synthetic races, the HMM achieves 96.8% ERS-level accuracy (random baseline 25%), classifies L_harvest vs. L_derate with 89.4% accuracy, and detects counter-harvest trap conditions with 96.3% recall. Pre-season analysis indicates circuit-dependent recharge availability (1.0x to 2.2x per lap) as the primary confound; Melbourne is the hardest-case validation environment. Baum-Welch calibration on 2026 race telemetry begins with the Australian Grand Prix (8 March 2026).

Speech processing systems face a fundamental challenge: the human voice changes with age, yet few datasets support rigorous longitudinal evaluation. We introduce VoxKnesset, an open-access dataset of ~2,300 hours of Hebrew parliamentary speech spanning 2009-2025, comprising 393 speakers with recording spans of up to 15 years. Each segment includes aligned transcripts and verified demographic metadata from official parliamentary records. We benchmark modern speech embeddings (WavLM-Large, ECAPA-TDNN, Wav2Vec2-XLSR-1B) on age prediction and speaker verification under longitudinal conditions. Speaker verification EER rises from 2.15% to 4.58% over 15 years for the strongest model, and cross-sectionally trained age regressors fail to capture within-speaker aging, while longitudinally trained models recover a meaningful temporal signal. We publicly release the dataset and pipeline to support aging-robust speech systems and Hebrew speech processing.

AC optimal transmission switching (AC-OTS) is a computationally challenging problem due to the nonconvexity and nonlinearity of AC power-flow (PF) equations coupled with a large number of binary variables. A computationally efficient alternative is the DC-OTS model, which uses the DC PF equations, but it can yield infeasible or suboptimal switching decisions when evaluated under the full AC optimal power flow (AC-OPF). To tackle this issue, we propose an AC-Informed DC Optimal Transmission Switching (AIDC-OTS) scheme that enhances the DC-OTS model by leveraging first- and second-order admittance sensitivities-based constraints and repair/penalty costs that guide the DC OTS towards AC-feasible topologies. The resulting model initially is a Mixed-Integer Quadratically Constrained Quadratic Program (MIQCQP), which we further reformulate into solver-friendly representations, such as a Mixed-Integer Second-Order Cone Program (MISOCP) and a Mixed-Integer Linear Program (MILP). This proposed scheme yields switching topologies that are AC-feasible, while maintaining computational tractability. We validate the proposed scheme using extensive simulations across a large set of PGlib test cases, demonstrating its effectiveness, with performance benchmarks against original DC-OTS and other OTS formulations such as LPAC-OTS and QC-OTS.

The increasing penetration of photovoltaic (PV) generation in low-voltage distribution networks presents operational challenges, with overvoltages being among the most critical. This study introduces a tool based on Unbalanced Optimal Power Flow (UBOPF) to assess cost-effective local inverter control strategies specifically aimed at mitigating overvoltage issues. Two approaches are examined: dynamic active power curtailment and combined active and reactive power control. These strategies are tested on a residential low-voltage network with high PV penetration, where the UBOPF model with voltage-magnitude constraints was implemented in Julia using the JuMP optimization package. The results demonstrate that both methods are effective in maintaining voltage levels within regulatory limits, with the latter leading to lower PV curtailment. The analysis highlights the need to consider these control actions as ancillary services to the grid, which should be properly compensated given their effect on generator revenues.

The rapid growth of digital devices and IoT has intensified the demand for collaborative learning. Since these devices generate sensitive and high-dimensional data, centralized transmission is often impractical, while local learning suffers from slow convergence. Collaborative approaches can alleviate these issues by allowing agents to use information from one another to improve estimation. Each agent faces a personalized learning problem, and collaboration is beneficial among agents whose data are generated from the same distributions. This paper studies the problem of personalized online mean estimation in heterogeneous environments, where each agent observes data from its own sigma-sub-Gaussian distribution. Collaborative algorithms enable agents to identify similarity classes in real time and exploit information from agents belonging to the the same class to improve convergence and accuracy. The work builds on existing approaches: the collaborative mean estimation (colME) and its graph-based extensions (C-colME and B-colME), which improve scalability and robustness. Since the variance estimation plays a crucial role in the above mentioned algorithms, a method for accurate, local and real-time estimation of variance is proposed. Estimation of sample kurtosis is also incorporated. We derive the CI estimators for the sample standard deviation and sample kurtosis. These results are combined with sample colME methods to design a unified procedure for constructing multifold CI based jointly on the sample mean, sample variance, and sample kurtosis. This framework enables colME in challenging scenarios, such as when classes share similar means but differ in variances, or when both means and variances are alike while the underlying distributions diverge in higher-order characteristics.

Data center cooling systems consume significant auxiliary energy, yet optimization studies rarely quantify the gap between theoretically optimal and operationally deployable control strategies. This paper develops a digital twin of the liquid cooling infrastructure at the Frontier exascale supercomputer, in which a hot-temperature water system comprises three parallel subloops, each serving dedicated coolant distribution unit clusters through plate heat exchangers and variable-speed pumps. The surrogate model is built based on Modelica and validated through one full calendar year of 10-minute operational data following ASHRAE Guideline 14. The model achieves a subloop coefficient of variation of the root mean square error below 2.7% and a normalized mean bias error within 2.5%. Using this validated surrogate model, a layered optimization framework evaluates three progressively constrained strategies: an analytical flow-only optimization achieves 20.4% total energy saving, unconstrained joint optimization of flow rate and supply temperature demonstrates 30.1% total energy saving, and ramp-constrained optimization of flow rate and supply temperature, enforcing actuator rate limits, can reach total energy saving of 27.8%. The analysis reveals that the baseline system operates at 2.9 times the minimum thermally safe flow rate, and the co-optimizing supply temperature with flow rate nearly doubles the savings achievable by flow reduction alone.

An Adaptive Cruise Control (ACC) system automatically adjusts the host vehicle's speed to maintain a safe following distance from a lead vehicle. In typical implementations, a feedback controller (e.g., a Proportional-Integral-Derivative (PID) controller) computes the host vehicle's acceleration using a target speed and a spacing error, defined as the difference between the measured inter-vehicle distance and a desired safe distance. ACC is often assumed to be resilient to fault-injection attacks because a Kalman filter (KF) can smooth noisy speed measurements. However, we show–through analytical proofs and simulation results–that a KF can tolerate injected speed values only up to a bounded threshold. When injected values exceed this threshold, the filter can be driven off track, causing the ACC controller to make unsafe acceleration decisions and potentially leading to collisions. Our main contribution is to augment the PID-based controller with Intrusion Detection System (IDS) outputs, yielding Intrusion Detection Systems-Based Adaptive Cruise Control (ACC-IDS). The ACC-IDS controller is simple and implementable: a binary intrusion flag switches the control law to emergency braking. We prove that augmenting ACC with an IDS, under assumed detection-performance and latency constraints, can mitigate these attacks and help preserve ACC's collision-avoidance guarantees.