Papers

Accurate distributed energy resources (DERs) forecasting is critical for downstream optimal operations. However, such forecast-based operation can be highly vulnerable to cyberattacks. While existing research mainly focuses on adversarial attacks, we pivot to a more controllable and persistent threat: backdoor attacks. In time series forecasting, a backdoored model generates an attacker-specified target pattern whenever a trigger is embedded in historical inputs. This paradigm naturally fits the entire DER forecast-optimization-operation chain. In this paper, we investigate whether and how backdoor attacks can compromise distribution network operations and propose GridTroj, a unified backdoor framework tailored for this scenario. Unlike standard time series backdoor approaches that train a poisoned model to match a predefined target only in terms of forecasting error, GridTroj explicitly incorporates the attacker's intention and optimizes the attack toward operational disruption. Specifically, GridTroj coordinates two key modules. The Intention Planner designs operation-damaging targets and poisoning strategies, while the Backdoor Realizer constructs the corresponding network architecture and training strategy to learn the trigger-target association. Experiments on three downstream optimization tasks demonstrate that GridTroj can effectively compromise grid operations and outperforms existing baselines. Our code is available at https://github.com/YuxuanCEE/GridTroj.

The rapid growth of large AI data centres introduces new operational challenges for power systems, including rapid ramping, oscillatory load behavior, voltage fluctuations, and supply-demand balancing impacts. For example, the Alberta Electric System Operator (AESO) has identified transmission-connected data centres (TCDCs) as large non-conforming loads that may need to limit their point-of-connection ramp rates. Existing mitigation approaches mainly rely on exogenous electrical resources, such as battery energy storage systems (BESS). This paper presents a proof-of-concept demonstration of a complementary software-defined mitigation layer: using flexible large language model (LLM) inference serving as endogenous TCDC flexibility to partially offset AI training power ramps. We consider a 150 MW TCDC with training, inference, and base-load components. A measured LLaMA-2-70B fine-tuning power profile is scaled to represent an aggregate training block, while measured LLaMA-3.1-70B inference power traces are used to model batch-size-dependent inference flexibility. Three strategies are compared: BESS-only mitigation, batch-size-only control, and coordinated batch-size plus BESS control. Simulation results show that the hybrid strategy reduces BESS discharge energy by 71% and peak discharge power by 51%, while maintaining near-complete compliance with a 10 MW/min ramp limit.

Brain-Computer Interfaces (BCIs) face a severe calibration bottleneck due to cross-subject spatial covariance shifts and physiological artifacts. To enable zero-calibration BCI, a deep learning pipeline was engineered combining Per-Session Independent Component Analysis, Riemannian Euclidean Alignment, and EEGNet stabilized by Stochastic Weight Averaging (SWA). Evaluated on the strict MOABB BNCI2014-001 benchmark, the proposed architecture successfully isolates true sensorimotor rhythms. For the primary case study (Subject 1), a clinically robust SWA stable accuracy of 90.97% (AUC: 0.976, Cohen's $\kappa$: 0.819) was achieved. Furthermore, expanded 9-fold Leave-One-Subject-Out (LOSO) cross-validation yielded a globally stable mean accuracy of 74.31%, proving hardware-agnostic zero-shot efficacy for binary motor imagery.

We present a case study on the Emerald Fibre Bridge Link, an operational subsea telecom cable connecting Dublin and North Wales, examining DAS vessel-related signatures jointly with concurrent AIS data. The observations show that vessel-related DAS responses depend on local cable sensitivity and background conditions, while their interpretation is complicated by imperfect AIS reporting. Examining vessel-crossing events jointly, we identify representative DAS-AIS association patterns, ranging from clear vessel matches to offset, ambiguous, AIS-incomplete, AIS-silent-candidate, and non-vessel confounders. These observations reveal the gap between physical measurements at the cable and cooperative vessel reporting, providing practical insights for designing future DAS-assisted cable-protection workflows.

Automatic Music Transcription (AMT) models have achieved a high level of success in polyphonic transcription of various instruments. Velocity, typically a measure of note intensity, is less commonly predicted in these models due to the absence of velocity labels in available datasets and lack of a proper definition for instruments other than piano. We present a methodology and model for velocity prediction in Automatic Guitar Transcription (AGT) which uses virtual instruments to generate synthetic training data with velocity labels. We first pretrain a model on this synthetic data. These weights are then transferred to a different model and trained on real guitar audio, allowing the model to retain the working velocity prediction while also achieving high performance and generalisability from the real training data. The velocity prediction is shown to outperform a baseline model which does not use the pretrained velocity weights, when evaluated on synthetic data. In addition, using the pretrained velocity weights offers a small improvement in note transcription, though the magnitude of this improvement is limited and not always significant depending on the testing data. Overall the model achieves results comparable to the state of the art in guitar transcription, while also successfully predicting velocity.

Voice control offers an intuitive alternative to manual drone piloting, yet most existing systems rely on rigid command vocabularies that fail to handle the spontaneous, disfluent speech of naive users. This paper addresses this gap by proposing an End-to-End Spoken Language Understanding architecture for real-time human-drone interaction in French. Our model combines a frozen Self-Supervised Learning acoustic encoder with a lightweight LSTM-based classification head, augmented by a cross-modal knowledge distillation objective that aligns acoustic representations with semantic embeddings from a text teacher, without requiring transcription at inference time. We evaluate our approach on VoiceStick, a novel French corpus of spontaneous speech collected during real teleoperation sessions with 29 nonexpert dyads. On simple voice commands, our best configuration achieves 93% accuracy at 7 ms inference latency, outperforming cascade baselines (79%, 202 ms) with a 29x speedup. On the full spontaneous speech test set, our architecture reaches 82% accuracy, with crossmodal distillation consistently improving robustness across all configurations. These results demonstrate that End-to-End architectures are not only feasible but preferable for spontaneous voice-guided UAV teleoperation, combining semantic robustness, low latency, and calibrated confidence.

In this work, we present SemanticVessel, a dataset for fine-grained brain vessel segmentation in computed tomography angiography scans. Based on the detailed contrast provided by dynamic 4D-CTA scans, we generate segmentation traces for arteries and veins. We then use intensity-guided region growing to obtain segmentations of the majority of vascular territories in the human brain, which are refined and annotated with 20 unique arterial classes by an expert radiologist. Unlike existing datasets, where minor arteries are discarded as background content, we merge these minor arteries into a generic arterial class. Due to the multiple-phase acquisition of dynamic 4D-CTA, labels for a single phase can be re-used for other phases in the same series, greatly increasing the size of our dataset with no additional annotation cost. The results show that models trained with the additional generic artery class produce better fine-grained segmentations across the board. We will make our code, annotation GUI, and model weights available to the scientific community. Code, weights, and data will be made available on https://github.com/alceballosa/robust-vessel-segmentation

Histopathologic cancer detection is challenging due to tissue variability, staining differences, and subtle visual distinctions between disease classes. We propose two quantum algorithms for this task: a configurable dual-gradient CSWAP circuit (DG-CSWAP) that computes multi-directional edge responses in a single execution via per-pixel local Ry encoding, and a hardware-efficient destructive swap circuit (DG-DST) natively matched to quantum processing unit (QPU) gate sets at substantially lower circuit complexity. We prove algebraic equivalence between DG-CSWAP and DG-DST, enabling a two-circuit QPU validation strategy. A three-stage NISQ mitigation pipeline, including readout error correction, bias subtraction, and slope regression, reduces single-pixel hardware MSE by ~8x. Validated on five quantum processors via Amazon Braket, the method achieves inter-platform Pearson r ~ 0.93-0.94 across all local-simulator pairs. Compared to a prior Quantum Fourier Transform (QFT) based amplitude-encoding baseline requiring 12-qubit global state preparation and a three-model ensemble (85.55% on PatchCamelyon), the proposed method uses shot-based measurements, executes on real quantum hardware, and achieves 79.80% accuracy with a single ResNet-50. A Lite configuration delivers a 17x preprocessing speedup at a 2.59% accuracy cost. To the best of our knowledge, this is the first quantum hardware implementation study with noise mitigation for histopathologic image classification.

In a recent paper by the second coauthor, directional pursuit-evasion for strictly forward-moving nonholonomic vehicles was solved "half-globally", namely under favorable initial line-of-sight conditions. In this paper, we develop feedback designs that achieve the directional pursuit and evasion objectives from arbitrary initial relative configurations. We achieve globality with completely different approaches to both the design and the analysis. Our designs are less aggressive in both the forward-speed and steering laws, allowing transient overshoot of the pursuer-evader range during global reorientation. The only price that we pay for globality is that our feedback laws require a priori knowledge of the opponent's maximal turning rate, whereas in the half-global work, no known bound of the opponent's turning rate was assumed. For the pursuit problem, the feedback law guarantees finite-time capture with prescribed directional alignment. For the evasion problem, the feedback law guarantees capture avoidance with a prescribed safety margin and achieves spinaway under a decay condition on the pursuer's turning rate. We illustrate the global capture and spinaway with simulations. The analysis is based on an integral input-to-state stability type mechanism induced by an endogenous time dilation, together with finite-time coextinction and safety-margin persistence lemmas for singularly coupled scalar inequalities.

In this study, we introduce the Elderly CodecFake Detection (ECFD) task and release the Elderly-CodecFake (ECF) dataset in English and Chinese. We show that state-of-the-art CF detectors trained on previous benchmark CF datasets generalize poorly to elderly speech, revealing a critical vulnerability. We further hypothesize and demonstrate that multimodal foundation models (FMs) such as LanguageBind (LB) and ImageBind (IB) are more effective for ECFD due to their exposure to elderly content during cross-modal pretraining. Motivated by prior evidence that fusion of FMs enhances downstream performance, we explore fusion of FMs for ECFD. To this end, we propose BONSAI, a novel framework that employs Jensen-Shannon Divergence as the fusion mechanism. BONSAI with the fusion of LB and IB achieves an average EER (%) of 1.66 and outperforms individual FMs as well as competitive SOTA baselines, establishing a new benchmark for the ECFD task.

In this paper, we introduce Synthetic Heart Sound Detection (SHAC), a task aimed at identifying phonocardiograms (PCGs) synthesized using neural audio codecs (NACs). To facilitate research in this direction, we release CARDIOFAKE, the first benchmark dataset for SHAC containing both real and codec-synthesized PCGs. We benchmark spectral representations (MFCC, LFCC) and self-supervised learning (SSL) representations (e.g., WavLM) for the task. Furthermore, we propose GROOT, a fusion framework that integrates spectral and SSL features for leveraging their complementary behavior. Experiments show that GROOT, combining MFCC and WavLM, achieves state-of-the-art performance, outperforming individual representations and competitive baselines.

A compact cross-structured dynamic antenna is presented for antenna-level physical-layer security using reconfigurable information-beam control rather than conventional radiation beam steering. The antenna uses four printed meander-line monopoles in a planar cross structure and a switching network that realizes two complementary excitation states for each dynamic mode. By switching between opposite or diagonal port groups, the aperture introduces apparent two-dimensional phase center displacement and supports four information-beam directions: $\varphi=0^\circ$, $45^\circ$, $90^\circ$, and $135^\circ$. An average–differential array factor formulation shows that the average component preserves broad omnidirectional coverage, while the odd-symmetric differential component creates angle-dependent magnitude and phase distortion that determines where the constellation remains recoverable. The recoverable information region is therefore reconfigured without phased-array beamforming, multiple RF chains, or mechanical motion. A 5.05-GHz prototype on Rogers RO4350B is fabricated with an electrical footprint of $0.57 \times 0.47\lambda_0^2$. Measured 16-QAM results show that low bit error rate is confined to the intended E-plane information-beam sectors, while off-beam angles exhibit large magnitude and phase errors, elevated BER, or unrecoverable constellations despite high received SNR. The measured H-plane cuts maintain low BER over nearly the full angular range, confirming omnidirectional information recovery in the orthogonal plane.

The scientific utility of large single-dish radio telescopes depends critically on the stability and fidelity of their beam patterns, which govern angular resolution, sensitivity, and polarimetric accuracy. For the 32-m Ghana Radio Astronomy Observatory (GRAO) antenna, electromagnetic simulations reveal residual sidelobes, structural diffraction, and cross-polar leakage that limit performance in high-dynamic-range and polarisation-sensitive observations. To address these limitations, we develop a finite-impulse-response (FIR) spatial filtering framework that reformulates beam optimisation as a digital signal processing problem. By exploiting the equivalence between angular displacement and spatial frequency, classical FIR design methods, window-based and Parks-McClellan algorithms are adapted to operate directly on simulated Jones fields. This approach enables controlled suppression of high spatial frequency artefacts responsible for sidelobes and polarisation mixing, while preserving the telescope's diffraction-limited resolution. Applied to the GRAO 5 GHz beam model, the method achieves substantial reductions in near-in sidelobe ripple, improves beam smoothness, and lowers cross-polar leakage below -30 dB at boresight. These improvements translate into enhanced calibration stability and polarimetric precision, strengthening the telescope's capacity for Very Long Baseline Interferometry, spectral-line surveys, and pulsar timing. Beyond GRAO, the method provides a generalisable, non-invasive, and computationally efficient pathway for beam control applicable to other single-dish and phased-array instruments. The results establish digital spatial filtering as a practical complement to conventional optical or mechanical optimisation, advancing the integration of electromagnetic modelling and signal processing in next-generation radio astronomical instrumentation.

Unmanned aerial vehicles (UAVs) enable numerous commercial and public-safety applications, yet they also create security risks near critical infrastructure, transportation hubs, and restricted airspace. While integrated sensing and communications (ISAC) can leverage existing wireless networks for UAV surveillance, practical deployment must address competition between sensing and communication demands, as well as the challenges associated with tracking highly maneuverable UAVs with low radar cross section (RCS). This paper investigates adaptive multistatic ISAC for load-aware UAV detection and tracking in 5G wireless networks. A shared-resource framework is developed to quantify how sensing waveform length, sensing transmission rate, and beam allocation affect communication throughput in a 5G new radio (NR) system. Detection performance is analyzed using Zadoff-Chu (ZC) sensing waveforms, while tracking continuity is evaluated through an M-of-N detection model. To improve robustness under congestion, software-defined sensor (SDS) nodes exploit external signals of opportunity (SoO) to provide supplemental passive sensing opportunities when network resources become limited. Results show that adaptive sensing policies outperform fixed sensing reservations by preserving throughput under dynamic load while maintaining useful sensing capability. Under heavy congestion, SDS assistance substantially reduces tracking outage in the simulated scenarios. Cramer-Rao lower bound (CRLB) analysis demonstrates that multistatic sensing geometries improve localization accuracy and provide more uniform spatial coverage than monostatic sensing alone. These results highlight coordinated adaptive sensing and distributed multistatic support as a practical path toward resilient UAV surveillance in future wireless networks.

Implicit Neural Representations (INRs) have recently emerged as a promising paradigm for image compression, offering a fundamentally different approach from traditional and learned codecs. Nevertheless, INR-based methods for image compression suffer from long encoding times and a consistent performance gap in classic quality metrics such as PSNR. In this work, we explore the potential of purely INR-based compression methods and we propose PaaF (Picture as a Function), a novel INR-based image codec that introduces improved architectural design, adaptive quantization, and an efficient entropy coding scheme. These components are designed to enhance rate-distortion performance while preserving the simplicity and parallelizability of INR-based decoding. Experimental results demonstrate consistent improvements over existing INR-based methods in both quantitative metrics and perceptual quality. These findings highlight the potential of INR-based approaches and contribute to narrowing the gap between functional representations and more established compression paradigms.

Low Earth Orbit (LEO) communication satellites have emerged as a promising source of signals of opportunity for resilient positioning, navigation, and timing (PNT) in GNSS-challenged environments. Unlike GNSS constellations, however, commercial LEO systems are not globally synchronized, and independent satellite clock biases and drifts severely degrade kinematic estimation and induce statistical inconsistency when not explicitly managed. This paper proposes a base-station-aided differential navigation architecture that explicitly mitigates independent LEO satellite clock biases and drifts without inflating the state vector of the mobile rover. A fixed base station continuously tracks time-varying per-satellite clock states and transmits them as measurement-domain corrections, along with their rigorously propagated uncertainties, to a compact, 8-state rover Extended Kalman Filter (EKF). To support this architecture, we introduce a robust visibility management scheme to seamlessly handle the frequent entry and exit of LEO satellites. Furthermore, we derive the Recursive Bayesian Cramer-Rao Bound (RBCRB) directly linked to the channel-domain signal model to establish fundamental theoretical performance limits. The proposed methodology is validated using real-world urban vehicular data combined with high-fidelity LEO constellation simulations. Results demonstrate that the differential framework completely eliminates the statistical inconsistency endemic to single-receiver baselines. Crucially, the rover's posterior estimation uncertainty perfectly tracks the theoretical RBCRB limits across all kinematic and clock states, ensuring highly reliable PNT even during periods of severe geometric degradation.

Deep unrolled networks (DUNs) integrate physical forward models with learned regularization in cascaded network architectures, achieving exceptional performance in inverse problems while maintaining interpretability. While most DUNs operate in the object domain (e.g., image space), recent variants explored representation spaces for improved information flow. However, these methods rely on heuristic methods for data consistency (DC), sacrificing fidelity with measurements. In this work, we introduce DUNE (Deep Unrolled Networks in rEpresentation space), a framework that maintains exact adherence to physical measurements while operating in learned representation spaces. By deriving the DC gradient via the chain rule and implementing it through the Vector-Jacobian Product (VJP), we enable exact backpropagation of measurement residuals into the representation space. This formulation supports diverse architectural backbones, including pre-trained encoders to guide the iterative process. We assess DUNE against state-of-the-art baselines on accelerated MRI reconstruction tasks, demonstrating that exact VJP-based gradients yield superior reconstruction quality and structural fidelity across both single-channel portable low-field and multi-channel clinical high-field MRI acquisitions. The code will be available upon publication at https://github.com/EfeIlicak/DUNE.

Functional magnetic resonance imaging (fMRI) utilizes echo-planar imaging (EPI) to capture blood-oxygen-level-dependent (BOLD) signals with high temporal resolution. However, EPI is inherently sensitive to magnetic field inhomogeneities, resulting in susceptibility-induced geometric distortions along the phase-encoding (PE) direction. To correct these distortions, conventional approaches rely on additional calibration scans, such as field maps or reverse PE acquisitions, which are not always available in practice. To overcome this limitation, we propose SACRED, a calibration scan-free susceptibility distortion correction framework that corrects geometric distortions via image translation-based registration using only a routinely acquired anatomical T1-weighted (T1w) image and a unidirectional PE BOLD image. SACRED employs an invertible neural network as the image translation backbone to bridge the contrast gap between BOLD and T1w images while enforcing structural consistency through a modality independent neighborhood descriptor. This design enables the use of a mono-contrast similarity objective to train the registration network in an unsupervised manner without requiring distortion-corrected BOLD images. In addition, we incorporate test-time adaptation (TTA) to further enhance performance on out-of-distribution (OOD) data at inference time. SACRED was evaluated on one in-distribution (ID) dataset and two OOD datasets, and was compared with representative fMRI distortion correction methods. The results demonstrate that SACRED significantly outperforms competing methods on both ID and OOD datasets, exhibiting robustness to scanner and population shifts, partly enabled by TTA. The code will be made publicly available upon acceptance.

Data center power systems are increasingly exposed to weak-grid conditions due to the evolution of modern power systems and the integration of large and dynamic loads. In centralized uninterruptible power supply (UPS) architectures, the front-end rectifier plays a critical role in maintaining stable operation and ensuring reliable power delivery to information technology (IT) equipment. However, conventional phase-locked loop (PLL)-based proportional-integral (PI) control strategies may exhibit degraded performance or instability under low short-circuit ratio (SCR) conditions. This paper investigates the behavior of centralized UPS systems under weak-grid conditions and demonstrates, through electromagnetic transient simulations, that PI-controlled rectifiers can become unstable at SCR=2. To address this issue, a power-based control approach is applied to the three-phase rectifier, enabling direct regulation of active and reactive power without relying on PLL synchronization. Simulation results show that the proposed control strategy improves system damping and restores stable operation under weak-grid conditions. The findings highlight the importance of control design for maintaining reliable operation of data center power systems in emerging low-strength grid environments.

Engine order enhancement is central in automotive sound design, where selective harmonics are synthesized to shape perceptual qualities such as sportiness, refinedness, or power. This paper investigates a neural network-based approach to combustion engine sound modeling that extends conventional engine order analysis and enhancement by deriving synthesis parameters from audio data with machine learning and incorporating stochastic components into the synthesis framework. The system parameterizes engine sounds as a compact representation capturing per-order and broadband timbral variation across the full RPM-torque operating range, while remaining manually tunable and compatible with established automotive audio frameworks. The approach leverages gradient-based optimization and analysis-by-synthesis through an end-to-end differentiable implementation. The resulting synthesis parameter set is directly transferable to conventional DSP implementations for deployment on embedded targets. Spectral metrics and listening tests confirm high reconstruction fidelity, and integration into an established automotive audio development platform (EVx Suite) demonstrates technical feasibility on deployment-ready embedded systems.

Respiratory rate is a vital indicator of pulmonary and cardiovascular health, yet conventional methods for estimating respiratory rate are often intrusive due to their contact-based nature. Remote photoplethysmography offers a promising non-contact alternative and has been widely used for heart rate estimation; however, its potential for respiratory rate estimation remains underexplored. Existing methods typically adapt green and chrominance-based projections originally designed for heart rate estimation, which only partially capture respiratory dynamics. Most prior work focuses on the Eulerian representation with fixed or empirically selected RGB projections. To address these gaps, we propose a skin-tone-aware dynamic RGB signal projection that captures respiratory information. To mitigate the sensitivity of the Lagrangian representation to non-respiratory motion, we introduce a denoising network for motion-based remote photoplethysmography signals. We further design a phase-independent contrastive loss that enables Eulerian and Lagrangian representations to collaboratively learn respiratory rate information. We also introduce RR-rPPG, a respiratory-rate facial video dataset with Indian demographic representation. We evaluate the method on RR-rPPG and the publicly available COHFACE dataset, where it consistently outperforms comparison methods and achieves up to a 42.1% reduction in mean absolute error across the evaluated settings. The proposed framework demonstrates the effectiveness of jointly leveraging skin-tone-aware Eulerian and denoised Lagrangian representations for contactless respiratory rate estimation from facial videos. In addition, RR-rPPG contributes a diverse benchmark resource for future research in remote respiratory monitoring. The code and dataset will be made publicly available upon paper acceptance.

Inpainting-based image compression usually stores an optimised subset of all pixel locations and their colour values. In the decoding phase, the missing data are approximated via inpainting. Since the reconstruction quality depends critically on the selection of the stored data, we introduce a novel feature type: We store the vertex locations of a Delaunay triangulation together with the average colour values inside all triangles. We show that combining this feature type with homogeneous diffusion inpainting creates an elegant mathematical formulation with a positive definite linear system of equations. Even a simple solver such as the conjugate gradient method allows the handling of large images. To make our Delaunay averages maximally adaptive to the image, we develop an efficient data optimisation strategy specifically tailored to them. It incorporates ideas successfully used in the stippling literature. Experiments show that our approach outperforms the popular inpainting with optimised colour values by a large margin. Last but not least, we discover a favourable scaling behaviour: Doubling the image resolution allows us to halve the percentage of stored data while maintaining the quality level. This is attractive for compressing modern high-resolution images, where even data densities below 1 % yield appealing reconstructions.

Spectral initialization is a critical yet challenging step in sparse phase retrieval. Existing spectral design theory is largely tailored to dense phase retrieval, where the objective is eigenvector estimation. In contrast, sparse initialization first requires a statistically distinct support screening step whose design remains much less understood. This paper develops a stage-specific design theory for diagonal support screening. We formulate each coordinate score as a scalar statistic for distinguishing support from non-support coordinates and adopt the deflection criterion as a tractable measure of screening quality. Within a Hilbert-space formulation, we characterize the optimal spectral preprocessors that maximize this criterion. In the Gaussian model, the unique optimum is the centered linear preprocessor. To obtain a bounded implementation, we introduce a spherical normalization and characterize its exact optimal preprocessor. Since the exact spherical optimum exhibits a boundary singularity, we construct a bounded surrogate preprocessor and establish its unique optimality under a surrogate deflection criterion. The surrogate optimum is shown to be the direction-only projection of the Gaussian rule, removing the unbounded radial factor while preserving the same first-order screening structure. We further establish a general finite-sample diagonal bridge that connects the exact and surrogate deflection quotients to the initialization sample complexity, and that replacing the unknown signal energy by its empirical estimate introduces only a lower-order perturbation. Numerical experiments are consistent with the ordering predicted by the design quotients and show that the Gaussian centered rule and its spherical counterpart behave nearly identically at both the screening and initialization levels.

Autonomous vehicles must generate long-horizon and dynamically feasible trajectories in real time-even when operating at the limits of vehicle handling-to ensure safe operation in adverse conditions. However, existing work rarely quantifies the computational demands of generating such trajectories without prior references, warm starts and often defaults to low-fidelity models, compromising accuracy and control authority. We investigate the modeling and solver design choices that enable real-time solution of long-horizon, reference-free optimal control problems (OCPs) using full vehicle dynamics. To this end, we analyze vehicle stiffness properties to justify the OCP's integration scheme and show that lower-order A-stable methods consistently outperform alternatives, with solve time differences reaching two orders of magnitude. We show that robust nonlinear solver performance hinges on understanding barrier parameter update strategies and safeguarding techniques for Hessian indefiniteness, inherent in some interior point methods. Lastly, we propose a computationally efficient method for generating initial guesses using dynamic equilibrium, unlocking real-time performance and reducing initial infeasibility by up to four orders of magnitude. Extensive benchmarking and high-fidelity BeamNG simulation demonstrate compute times as low as 55 ms over a 260 m horizon, including high-speed obstacle avoidance scenarios where drifting emerges as a necessary component of feasible trajectory generation.

Reset control provides a nonlinear approach for improving closed-loop performance beyond the limitations of linear time-invariant controllers. However, the reset action inevitably introduces higher-order harmonics, which may degrade tracking performance, distort the reset signal, and reduce the reliability of frequency-domain predictions obtained via describing-function analysis. This paper revisits the generalized first-order reset element with shaping filters and develops a systematic framework for suppressing undesired reset-induced nonlinearities. Analytical conditions are derived for shaping filter coefficients to increase the low-frequency attenuation slope of the magnitude of the higher-order sinusoidal input describing functions (HOSIDFs). By modifying the asymptotic attenuation behavior of these higher-order harmonics, the proposed design provides stronger harmonic suppression in frequency regions where reset action is undesired, while preserving the beneficial first-order harmonic phase advantage near the desired cross-over frequency. The reduction in nonlinear behavior is verified through HOSIDF analysis and a superposition-law test, demonstrating that higher-order shaping filters make the reset element behave more closely to a linear system at a certain range of frequencies. Experimental validation on an industrial motion stage demonstrates improved tracking performance, reduced higher-order harmonic content, and selective activation of the reset action in the intended frequency region.

Equalization-enhanced phase noise (EEPN) emerges as a key performance limitation in high symbol-rate coherent transmission systems. In this paper, we highlight recent advances in modeling EEPN and show that the temporal Gaussian noise model reproduces the characteristic burst-like SNR degradation, enabling efficient system simulation.

Mandarin stuttered speech remains under-resourced, limiting the development of robust speech processing systems. We present a Mandarin stuttering speech synthesis and data augmentation framework that adapts both autoregressive and non-autoregressive TTS models using naturally stuttered speech. Specifically, we adapt CosyVoice2 and MaskGCT to support controllable generation of specific stuttering events while also modeling broader utterance-level characteristics of stuttered speech. Using the adapted models, we construct synthetic data resources for downstream augmentation. Evaluations show that the generated speech closely approaches real stuttered speech. Extensive ASR experiments demonstrate consistent augmentation gains and further observe a domain-gap–diversity trade-off between synthetic and real data. These results demonstrate the value of learning synthetic stuttering data directly from real dysfluency for robust Mandarin speech processing.

Task-oriented voice agents need to map spoken user requests to structured outputs such as semantic frames, executable actions, and function calls. A common approach is to cascade ASR with a text-based LLM, but transcription errors can propagate to downstream structured output generation, especially under noisy conditions. Spoken language models (SLMs) offer a direct speech-based alternative, yet adapting them to new tasks typically requires paired speech-target annotations. Motivated by this gap, we present CORTIS, a text-only adaptation framework for task-oriented voice agents. CORTIS fine-tunes SLMs using text-form task supervision, enabling speech-based structured output generation at inference time without task-specific speech-target annotations during adaptation. We evaluate CORTIS on two Qwen2.5-Omni backbones and three task-oriented speech datasets, including an in-house product dataset, and compare it with matched ASR-LLM cascades trained with the same text-form task supervision. Results show that CORTIS performs competitively with matched cascades and offers clearer advantages under acoustic degradation, particularly in preserving high-level task semantics. These findings suggest that text-only fine-tuning of SLMs can serve as a practical adaptation strategy for voice agents when paired speech-target data are costly to collect.

As large language models scale, memory bandwidth for key-value caches and retrieval-augmented generation systems becomes a critical bottleneck. While 1-bit quantization addresses this constraint, recent TurboQuant relies on dense random rotation matrices to condition the vector distribution before quantization. This projection demands millions of floating-point multiplications per embedding, making it difficult to deploy on constrained edge silicon. We introduce Fast-TurboQuant, a multiplier-free projection architecture that replaces the dense matrix with a structured fast Johnson-Lindenstrauss transform. By applying a Rademacher phase inversion followed by a fast Walsh-Hadamard transform (FWHT), the method leverages sub-Gaussian concentration to satisfy the prerequisites of scalar Lloyd-Max quantization without Gaussian projections. This substitution reduces the arithmetic complexity to only additions, eliminating hardware multipliers. Evaluation on DBpedia OpenAI-3 Large embeddings demonstrates a 19.7 times algorithmic speedup under sequential execution. Furthermore, the dimension expansion due to the FWHT zero-padding reduces the mean squared error and improves Recall@10.

This paper develops a frequency-domain reliability assessment framework for reset control systems. The closed-loop higher-order sinusoidal-input describing function formulation is extended to explicitly include the reset-triggering signal generated through a shaping filter. Based on this signal, two metrics are introduced: \(\sigma_t\), which quantifies reset-time deviation, and \(\sigma_d\), which evaluates the tendency toward additional zero crossings. These metrics provide design-oriented indicators for identifying potentially unreliable reset behavior. To improve reset-triggering reliability, a first-order shaping filter is proposed for a generalized first-order reset element, increasing the low-frequency attenuation slope of the nonzero higher-order harmonics. The proposed analysis is evaluated on an industrial motion stage. The results show that the proposed metrics capture reliability issues that are not evident from the first-order closed-loop response alone and can therefore support the design of reset controllers with more reliable reset-triggering behavior.