Papers

In this paper, we present the first (to the best of our knowledge) demonstration of a low-power MCU-based edge device for Automatic License Plate Recognition (ALPR). The design leverages on a 9-core RISC-V processor, GAP8, coupled with a QVGA ultra-low-power greyscale imager. The proposed visual processing pipeline uses a multi-model inference approach based on SSDlite-MobilenetV2 for license plate detection and LPRNet for optical character recognition, reaching a 38.9% mAP score for the first task and a recognition rate of >99.13% for the latter on public datasets. On real-world data, the pipeline recognizes registration numbers when the size of LP crops is as small as 30x5 pixels. Thanks to the applied compression and optimization strategies, the multi-model inference (687 MMAC) achieves a throughput of 1.09 FPS at a power cost of 117 mW when running on GAP8. Our solution is the first MCU-class device embedding such a level of network complexity, resulting to be 73x more energy-efficient w.r.t. precedent mobile-class ALPR system featuring a Raspberry Pi3. The proposed design does not resort to any hardwired acceleration engines, thus retaining full flexibility for future algorithmic improvements.

The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech. It relies on content embeddings extracted from a frozen pretrained wav2vec2 encoder. These embeddings are decoded into an anonymized signal using vector quantization and a HiFi-GAN vocoder, both trained on LibriTTS without any waveform reconstruction loss or speaker embedding mapping. The training objective enforces that embeddings of the anonymized signal match those of the original one. While training, an auxiliary speaker classification branch with a gradient reversal layer is used to discard speakerspecific information. Results show that this straightforward embedding-based approach achieves very low WER (2.53) with an anonymization performance (EER 13.39) ranking within first level for VPC. Notably, emotions are partially preserved (UAR 43.91), even without a supporting training objective, while the anonymized voice is audible without reconstruction loss.

A cheap swarm of unreliable agents can be steered to a correct consensus by a few strong, expensive "oracle" correctors. We ask how much one must spend, and where to place the oracles. We model the swarm as a consensus on a graph in which each oracle pins one node toward the truth at a cost-coupled, concave strength, and measure quality by the coherence H(R)=tr M(R)^{-1}. Our first result is that H stays submodular (each added oracle helps less than the last) even when the oracles differ in strength, so a cost-benefit greedy comes within 1-1/e of the best placement at any budget. Inverting the budget gives the budget-correctness frontier B*(eps), the least spend that guarantees an eps-correct consensus: closed-form on the complete graph, and a minimal oracle count k* when oracles cost the same. Whether a budget then buys a few strong oracles or many medium onese curvature of the cost-quality law: diminishing returns favour spreadsharply increasion. Measured onthe Qwen3 ladder (0.6-32B), the law is concave for math verificatio convex foremergent code tracing, so the verdict is genuinely task-dependent.https://github.com/YehudaItkin/budgeted-oracle-placemen

Sepsis is a leading cause of mortality, yet optimal treatment policies remain contested. Existing reinforcement learning (RL) approaches learn fixed strategies for sepsis treatment, limiting adaptability to changing clinical objectives during inference. We propose EHRMPC, a framework that decouples learning patient dynamics from optimizing treatment by training a patient digital twin in the form of a generative electronic health record (EHR) model. The digital twin predicts clinical trajectories under interventions and enables model predictive control (MPC) to optimize treatments via inference-time planning over simulations. We evaluate EHR-MPC on a multicenter ICU sepsis cohort spanning 8 hospitals in the Mass General Brigham health system using both off-policy importance sampling and on-policy simulation-based evaluation. Relative to RL baselines, EHR-MPC achieves comparable off-policy performance and improved simulation performance. Unlike RL, this work frames sepsis treatment optimization as inference-time control over learned patient dynamics, establishing a general framework for decision making with generative clinical models.

Fluid reconfigurable intelligent surfaces (FRIS) have recently emerged as a promising technology for enhancing wireless link reliability through spatial decorrelation. However, their performance analysis remains challenging due to the sum-product structure of the cascaded channel. This letter develops a rigorous analytical framework for FRIS-assisted wireless systems over arbitrarily correlated Nakagami-$m$ fading channels. Specifically, we introduce a physically consistent correlation model for Nakagami-$m$ fading and derive tractable statistical characterizations for the cascaded channel. These results lead to rigorous lower bounds for the outage probability (OP), with a simplified expression also obtained for the independent and identically distributed case. To the best of our knowledge, these are the first strict OP lower bounds reported for an FRIS-aided wireless system under arbitrarily correlated Nakagami-$m$ fading. CLT- and Gamma-based approximations are included as benchmark methods. Notably, the numerical results show that the proposed OP bound not only provides rigorous performance guarantees but also yields a noticeably tighter OP characterization than the CLT approximation in the high-SNR regime.

This paper proposes a novel cyclic-prefixed single-carrier transmission scheme that amalgamate a reconfigurable intelligent surface (RIS) with spatial modulation in the frequency-selective fading channel. The discrete-input continuous-output memoryless channel's~(DCMC) capacities of the proposed schemes are formulated, while their gradients with respect to the RIS phase shifts are derived in the closed form. Then, the gradients are used for iteratively and efficiently optimizing the proposed RIS-aided schemes with the aid of the gradient-ascent algorithm. Our performance results demonstrate that the proposed iterative algorithm enhances the DCMC capacity of the schemes, while outperforming the conventional RIS benchmarks. Moreover, the convergence behavior and sensitivity in the proposed iterative algorithm are analyzed.

Purpose: To compare detuning performance and evaluate the power requirements of optical detuning methods, and to demonstrate the feasibility of an optically detuned four-channel receive array. Methods: Four optical detuning methods were compared in simulations, bench tests, and phantom measurements at 3T against conventional galvanic detuning. Passive detuning was also tested as an additional wireless detuning option. Optical power requirements for the detuning networks were investigated, and a flexible, optically detuned 4-channel shielded-loop resonator (SLR) array was constructed and tested in vivo. Results: A photodiode-PIN diode combination exhibited the highest unloaded Q (68.6) and Q ratio (1.9), with detuning performance and signal-to-noise ratio comparable to that of galvanic detuning at an optical power of 10 mW. Using this detuning strategy, in vivo images of the knee and brain were successfully acquired with a 4-channel flexible array. Conclusion: Optical detuning is a practical alternative to conventional galvanic detuning in flexible SLR arrays. With advances in optical signal and power transmission, optimizing optical detuning while meeting manageable power requirements is an important step toward fully optical receive-coil arrays. This study provides a baseline for the total optical power required for active detuning in such optical coil systems.

Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial markets, and wireless network optimization. In these settings, the target signals are realizations of unknown conditional distributions. However, prevailing approaches rely mostly on intricate, application-tailored designs that often regress to a conditional mean instead of sampling from the conditional law. This paper unifies such problems as conditional graph signal generative modeling and tackles them with a single denoising diffusion framework. We learn a reverse diffusion process, parametrized by graph neural networks (GNNs), that draws graph signals conditioned directly on the graph topology and on node-feature side information. The reverse process is realized by a novel architecture, the U-Graph Neural Network (U-GNN), which generalizes the image-convolutional U-Net to graph-structured signals. The U-GNN performs multi-resolution encoder–decoder processing in which pooling and unpooling reduce to a learned node selection, expressed by nested selection matrices, and a zero-padded lifting of coarse signals back to the full node set. The graph convolutions are carried out on the original graph, with a stride that sets their hop reach, so the U-GNN bypasses explicit graph coarsening at every resolution. We demonstrate our method on two generative tasks: stock price forecasting and optimal wireless resource allocation, with extensive numerical results in both domains.

Satellite state estimation plays a fundamental role in orbital navigation, tracking, and autonomous space operations. Accurate estimation remains challenging due to uncertainties in process and measurement noise, which may degrade the performance of conventional Kalman filtering techniques. This paper presents a Neural-enhanced micro-Kalman filter ($\mu$KF) for satellite tracking based on an information-form state estimation framework. Starting from a linearized state-space model of orbital dynamics, a lightweight neural scaling mechanism is introduced to adapt the process and measurement noise covariances online while preserving the underlying Bayesian filtering structure. The proposed estimator is formulated within the information-form $\mu$KF framework and evaluated through numerical simulations using a linear Gaussian satellite tracking model. Its performance is compared with the classical Kalman filter (KF), the extended Kalman filter (EKF), the unscented Kalman filter (UKF), and an adaptive Kalman filter under identical operating conditions. Simulation results demonstrate that the proposed Neural-$\mu$KF accurately tracks the satellite states with consistently low mean square estimation errors (MSEE). Furthermore, the proposed method achieves estimation performance comparable to, and for selected states slightly better than, the baseline Kalman filter while retaining the computational advantages of the information-form formulation. These results demonstrate that integrating lightweight neural covariance adaptation into the $\mu$KF provides an effective and flexible framework for satellite state estimation.

Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A common remedy is to compress the speech sequence at the adapter level to remove temporal redundancy before it enters the LLM; however, such early downsampling risks discarding fine-grained information that cannot be recovered. We propose SpeechKV, which applies a learned pooling to the KV cache of speech tokens inside the LLM. This design allows the LLM to fuse speech and text internally while directly accelerating decoding. Trained on 71K hours of speech data, SpeechKV compresses the speech to approximately text-level granularity yet maintains performance on par with or even slightly better than the uncompressed baseline, with relative gains of 6.6% on out-of-domain entity recognition and 2.3% on OpenASR, while delivering at least 1.49 times decoding speedup that scales with audio length.

The increasing penetration of inverter-based resources (IBRs) into bulk power systems has fundamentally altered short-term voltage dynamics following disturbances. Conventional short-circuit capacity (SCC) metrics provide a useful screening indicator of grid strength but are unable to fully capture post-disturbance voltage behavior at buses with dynamic loads, converter controls, or protection interactions. A bus with high SCC may still experience deep voltage dips, delayed recovery, or transient overvoltage that violates operating criteria. This paper proposes the Short-Term Voltage Performance Index (STVPI), an electromagnetic-transient (EMT)-based, criteria-aware metric that quantifies the quality of the post-disturbance voltage waveform relative to user-defined performance limits. STVPI processes voltage signals at the half-cycle level by computing a weighted log-amplitude ratio between the actual waveform and an ideal half-sine reference. Monotonic recovery envelopes on the overvoltage and undervoltage sides are compared against half-normal reference distributions using Kullback–Leibler (KL) divergence, normalized by the KL divergence of the critical voltage envelope, yielding two directional indices – $\mathrm{STVPI}^{+}$ and $\mathrm{STVPI}^{-}$ – whose combination produces a baseline-corrected scalar severity score. Bus-level and event-level aggregation derive BSTVPI and ESTVPI, enabling simultaneous identification of dynamically weak buses and critical fault contingencies. The framework is validated on the IEEE 9-bus and 39-bus test systems with IBR integration.

Open physiological corpora are heterogeneous: they use different sensors, labels, sampling rates, recording settings, and clinical endpoints. They can support detector design, but they do not directly specify which detector rules should be built for a new contactless monitoring platform. We report a controlled four-analyst large-language-model (LLM) workflow for converting 68 public physiological corpora, screened for commercial-use compatibility, into an auditable library of candidate rule shapes for prospective validation. Four independent commercial LLM families read the corpus documentation under a controlled prompt and produced 695 candidate rule markers (top-markers). Deduplication retained 649 rule records; a threshold-bounds audit then flagged 51 sanity violations for clamping or curator review. Cross-corpus consolidation produced 436 unique rule shapes. Gate-tagging against two hard invariants, native target-hardware channel availability and no multi-night per-patient personalization, identified 94 build-now detector components across four detector-family buckets. The pipeline does not produce a validated clinical detector. It produces an auditable engineering cascade in which analyst disagreement, threshold checks, curator review, and automated continuous-integration (CI) checks route literature-derived rules toward prospective hardware validation.

Lane-change, a triggering of traffic disturbances to the upstream vehicles, is detrimental to traffic safety and efficiency. Coupled with car-following behavior, the joint maneuvers depict the general picture of how traffic disturbances generate and propagate through vehicle streams, especially under traffic congestion. This study proposes an integrated control framework for lane-changing and car-following for connected and automated vehicles (CAVs), where those two tasks are largely treated as independent driving tasks by prevailing methods. Utilizing the Parametrized Deep Q-Network (P-DQN) with a hybrid action space, the framework adeptly models multiple objectives in CAV control. The P-DQN's high-level control is employed for discrete lane-change decisions, while its low-level control manages continuous acceleration actions, i.e., lateral and longitudinal acceleration. These actions are interdependently determined, seamlessly integrating car-following and lane-changing control. By training to maximize cumulative rewards, the proposed control strategy ensures driving safety as well as the efficiency of car-following, lane-changing, and lane-keeping. Through numerical experiments, it is indicated that the P-DQN outperforms separated control methods, e.g., the combination of the Minimizing Overall Braking Decelerations Induced by Lane Changes (MOBIL) model and the Intelligent Driver Model (IDM), in terms of safety and comfort.

This paper provides the first near-optimal lower bounds for one-bit compressed sensing of approximately sparse signals lying in a scaled $\ell_1$ ball, which is a commonly adopted relaxation of the exactly $k$-sparse assumption. In prior works, the best known upper bounds on uniform Euclidean error are of order $\widetilde{O}((k/m)^{1/3})$, where $m$ is the number of measurements. Under sub-Gaussian matrices, we establish nearly matching lower bounds for both the canonical one-bit compressed sensing model and the uniformly dithered model. Our argument is to first embed a small Euclidean ball into the signal set, which is straightforward for the dithered model but relies on a lifting map for the canonical model, and then construct two signals in this small ball that are separated in Euclidean distance by at least $(k/m)^{1/3}$ (up to logarithmic factor) but are indistinguishable from the binary measurements. Moreover, our argument extends to approximately sparse signals that live in a properly scaled $\ell_q$ ball $(q\in [0,1])$, yielding a lower bound $\widetilde{\Omega}((k/m)^{\frac{2-q}{2+q}})$ that smoothly bridges the cases of exact sparsity ($q=0$) and $\ell_1$ sparsity ($q=1$). Finally, we discuss the extensions of our lower bounds to sub-Weibull matrices, adversarial bit flipping, matrix recovery, and characterize the transition to the non-sparse case.

This paper proposes Variational Inference-based Bayesian Estimation with Sobol screening (VIBES), a two-stage scalable framework for Bayesian uncertainty quantification (UQ). The proposed approach combines Sobol global sensitivity analysis (GSA) for screening and dimensionality reduction, followed by variational inference (VI) for UQ of kinetic, design/operational, and economic parameters. In the first stage, Sobol GSA is performed to identify dominant variables and parameters governing uncertainty in process outputs. In the second stage, Bayesian inference is performed only on the reduced dimensional space using VI, thus reducing computational burden and enhancing scalability. The framework is demonstrated on a process for bioadhesive production through base-catalyzed depolymerization of kraft lignin and subsequent crosslinking with isolated soy protein. A Python-Aspen interface is developed for automated simulation and parameter estimation, enabling Bayesian calibration through stochastic gradient-based optimization and automatic-differentiation. The methodology is generic and readily generalizable to other biomass conversion pathways. The results show that application of VIBES consistently reduces predictive uncertainty bounds across all model outputs by more than 80%, even when only the reduced-space input variables and parameters are optimized during Bayesian estimation. The framework can be potentially applied for scalable, uncertainty-aware decision-making in high-dimensional, complex chemical process systems.

Formal robustness certificates for embedded neural-interface models can pass while task accuracy collapses: at perturbation budget e=0.25, EEGNet classification accuracy drops by 25.7% under projected-gradient attack while the Lipschitz-style certificate remains valid for all 9 tested subjects. We argue that this gap between mathematical certification and operational safety is one instance of a broader alignment failure in neural interfaces, where training objectives diverge from user welfare. We propose a unified empirical audit framework organized around three such failures: verification insufficiency, in which certificates pass while task behavior degrades; proxy-fidelity divergence, in which task-optimized representations damage neural signal structure (a time-domain auxiliary objective reduces reconstruction MSE by 0.1132 while worsening spectral log-MSE); and latent information exfiltration, in which public-task embeddings retain private attributes (subject identity recoverable at 48.1% versus 6.7% chance). We instantiate the framework on BCI Competition IV 2a and SEED-IV using multiple deep and classical EEG decoders, official session-level validation, null controls, and paired statistical tests. The verification gap persists across EEGNet, CSP+LDA, and FBCSP+LDA, and is therefore architecture-independent. Our results establish that operational safety auditing, not certificate verification alone, is necessary for responsible neural-interface deployment.

Process industries have accumulated validated specialist models, yet sensor drift, feedstock variation, and regime switching cause these models to degrade systematically in new scenarios. Collecting new labeled data and retraining is costly, while continuing with the original model incurs persistent bias. Existing adaptation methods require modifying model parameters with sufficient labeled data, making rapid response on deployed systems difficult. Using LLMs as direct predictors risks hallucinations and uncontrollable outputs. Such predictors also cannot incorporate unstructured scenario knowledge from the field. To address these limitations, this article proposes Reasoning-Driven Open Adaptation for Specialist Models (ROAM), a framework that uses LLM world knowledge and reasoning to adapt frozen specialist models to unseen scenarios without retraining. ROAM confines all corrections to a low-dimensional, semantically interpretable latent space. LLM-generated scenario judgments and online observations are fused under a unified probabilistic framework. A risk-constrained mechanism suppresses corrections under unreliable LLM evidence or abrupt scenario shifts and falls back to the original frozen model when evidence is insufficient. Experiments on a mineral thickening process and the public IndPenSim penicillin fermentation dataset show that ROAM reduces MAE by over 20% in major shift settings such as hidden shifts with only 839 additional parameters and under 0.02\,ms per-step overhead. These results indicate that LLM reasoning can be turned into a conservative adaptation signal for industrial models already in service.

Process industries rely on time-series forecasting and soft sensing to estimate quality variables that are hard to measure online. Labeled data are scarce, operating regimes change frequently, and retraining models or rebuilding alignment pipelines for each scenario is costly. Such settings often provide variable tables and process documents that record variable names, units, physical meanings, and process roles. However, standard time-series backbones usually treat inputs as anonymous numerical columns. Existing text-enhanced methods also rarely make the semantic-logical relations between input variables and the prediction target available to the model within each numerical window. To address this problem, this article proposes Task-Semantic Field Factorization (TSF), a large language model (LLM)-guided framework. TSF builds a task-semantic field from task protocols and variable documents before training and uses the LLM only for offline semantic construction. Online training and inference are handled by conventional time-series backbones. During training and inference, the current numerical window activates variable semantics, so semantic information participates in each prediction and supports adaptation to different prediction targets and operating shifts. Across multiple complex industrial forecasting and delayed soft-sensing tasks, TSF reduces MAE by 3.6% on average. Across all dataset–backbone pairs, the macro-average reduction is 2.9%, with a maximum reduction of 24.9%. It adds only about 0.7–4.3k parameters, with less than 8\,$\mu$s/sample of additional online inference overhead. These results show that TSF turns existing process documents into measurable forecasting gains across backbones and semantic generators while remaining lightweight for deployment.

Utilities increasingly rely on planning and operational tools to cope with the increased penetrations of distributed energy resources, yet the lack of realistic, openly available datasets remains a major barrier for benchmarking and comparison. Traditional test feeders, and recently proposed large-scale synthetic networks alleviate this issue but are typically based on heuristic rules and do not learn directly from data. This paper proposes a generative framework based on Generative Adversarial Networks (GANs) to create power distribution network layouts using image-based representations. The model is trained on rasterised views of distribution systems and can operate in two modes: an unconditional configuration that learns layout patterns from the training dataset, and conditional configurations that incorporate geographical context such as street maps and the spatial distribution of consumers. The methodology includes dataset preparation from Geographic Information System (GIS) sources, GAN architecture design, and the analysis of training stability and image resolution. Results from three representative cases show that the proposed approach can reproduce the topologies of low (LV), medium (MV) and high voltage (HV) feeders and align generated layouts with underlying geographical structures. At the same time, the study reveals limitations related to training stability, resolution-dependent artefacts and limits, and the absence of explicit electrical constraints. The proposed framework constitutes a data-driven complement to existing synthetic network generation methods, and could be applied to propose distribution network layouts for the electrification of new areas. This would require future extensions towards power flow, electrically validated models.

Image forgery detection is a critical task in digital forensics, yet many deep-learning localization approaches are typically GPU-accelerated and computationally heavier than handcrafted screening methods. We propose a lightweight, interpretable feature engineering pipeline for image-level forgery screening using only CPU computation and gradient boosted trees. Our method introduces multi-scale Error Level Analysis (ELA) computed at seven JPEG quality levels, combined with novel cross-quality ELA ratio features that capture double-compression artifacts characteristic of spliced regions, augmented by spatial entropy, FFT energy bands, edge density, SRM residuals, and DCT blockiness, yielding a 405-dimensional feature vector. CASIA v2.0 contains a format confound (60% of tampered images are TIFF while authentic images are JPEG/BMP and contain no TIFF samples), enabling a trivial is\_tiff classifier to reach 0.80 AUC. We address this through rigorous format-controlled evaluation: on the JPEG-only subset (9,501 images, eliminating the TIFF/JPEG container confound), our method achieves AUC~=~0.990 [95% CI: 0.988–0.991] and F1~=~0.905 using 5-fold stratified cross-validation. Under a conservative source-aware group split (preventing related images from appearing in both train and test), AUC remains 0.976. An ablation study reveals that multi-scale ELA provides the dominant gain (+0.180 AUC over single-quality on the format-controlled subset), while cross-quality ratios provide complementary double-compression detection. These results support that the method detects compression-history inconsistencies rather than file-format shortcuts – while offering feature-level interpretability, CPU-only deployment, and sub-second inference.

A learning-enabled disturbance-rejection framework based on a Neural Extended State Observer (Neural-ESO) is presented in this letter. Unlike existing learning-based control methods that largely rely on the learned model once deployed, Neural-ESO adopts a dual-pathway architecture: a predictive pathway uses a neural network to provide a feedforward disturbance estimate that accelerates convergence, while a corrective pathway employs a conventional ESO to compensate prediction errors and prevent over-reliance on the neural component. Using Lyapunov theory and a small-gain analysis, we show that enforcing a Lipschitz bound on the learning component guarantees uniform ultimate boundedness of the closed-loop error dynamics. The proposed framework is validated on a quadrotor landing task subject to strong ground-effect disturbances across normal and out-of-distribution scenarios, demonstrating accuracy-robustness trade-off and greater operational reliability during training, deployment, and transfer compared with state-of-the-art baselines.

This paper studies the constrained-capacity for precoded faster-than-Nyquist (FTN) signaling with finite-alphabet inputs. Despite the promise of accelerated transmission, the fundamental rate limit of precoded FTN signaling under practical finite-alphabet constraints remains unclear. By introducing cyclic prefix (CP) and cyclic suffix (CS), the FTN channel is decomposed into a set of parallel eigenchannels by the discrete Fourier transform (DFT) matrix, based on which the constrained capacity is derived. The results demonstrate that time acceleration can improve spectral efficiency over Nyquist signaling even when a fixed modulation order is employed. Moreover, in the low and moderate signal-to-noise ratio (SNR) regimes, a smaller constellation combined with stronger time acceleration can outperform a larger constellation with weaker acceleration. Next, the asymptotic behavior of the constrained capacity is analyzed as the acceleration factor tends to zero under both fixed transmit-SNR and fixed receive-SNR definitions. It is shown that the constrained capacity for DFT-precoded FTN is fundamentally limited by the constellation size. In addition, the constrained capacity under channel mismatch is studied and a mismatched achievable information rate (AIR) formulation is developed to show the effects of practical constraints on the performance degradation. Finally, adaptive bit loading across eigenchannels is investigated to exploit the higher-quality eigenchannels.

While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and strict temporal alignment, such as audiobook narration and video dubbing, the inability to explicitly manipulate word-level acoustic attributes remains a critical bottleneck. This limitation is primarily amplified by the severe scarcity of fine-grained annotated datasets and the architectural challenge of integrating multi-dimensional control signals into discrete autoregressive generation. To address this, we propose a unified framework for highly precise word-level control. First, we construct WordVoice-5A, a massive 4.7k-hour bilingual dataset featuring five-dimensional word-level annotations (duration, boundary, energy, pitch and tone) developed through a rigorous linguistically-guided pipeline. Second, we introduce WordVoice to transform the implicit generation process into an explicit, highly controllable paradigm. Specifically, we introduce a bound-token mechanism within the LLM to formulate an explicit “acoustic planning” process, enabling adaptive multi-task prosodic planning and flexible manual intervention. Furthermore, we augment the token-to-waveform stage with a fine-grained acoustic modulation module, bridging the resolution gap to strictly align word-level attributes between highly compressed discrete tokens and continuous waveforms. Extensive experiments demonstrate that WordVoice achieves superior, decoupled control over multiple acoustic dimensions while maintaining competitive zero-shot synthesis stability. The code and audio samples are publicly available at https://xxh333.github.io/wordvoice-demo/.

This paper studies input-to-state stability (ISS) certification for data-driven Koopman learning control of unknown discrete-time nonlinear repetitive systems over finite trial horizons. Rather than proposing a new learning law, we certify when a fixed Koopman-assisted constrained update yields practical stability of the selected tracking error along the trial axis. Prediction accuracy alone is insufficient for this purpose: the selected finite-horizon input-output channel must have a positive margin, and the unreachable component of the requested output increment must be accounted for through a projection residual. Thus, a Koopman predictor with small held-out prediction residuals may still fail the learning-stability certificate if its selected channel is weak. We formulate the selected stacked tracking error as the state of a discrete-time learning-axis system and treat Koopman residuals, reset mismatch, channel uncertainty, projection residuals, deployment shifts, and numerical tolerances as ISS inputs. The deterministic result gives a practical ISS estimate from the initial learning error to an explicit ultimate band. A finite-sample implementation constructs an episode-level residual bound under a fixed controller and combines it with reported channel, projection, shift, and numerical margins. Numerical checks on nonlinear repetitive systems support the predicted residual-to-band scaling, weak-channel rejection, projection closure, and ultimate-band coverage.

Energy-efficient neuromorphic computing at the edge requires simulation tools that can capture the non-ideal behavior of mixed-signal spiking neural network (SNN) hardware while supporting system-level design exploration. This work presents an open-source hardware-aware simulation framework for mixed-signal SNNs that enables comparative analysis across neuron, synapse and architecture choices. The framework supports multiple neuron models, including Leaky Integrate-and-Fire (LIF), Hodgkin-Huxley (HH) and Axon-Hillock (AH), together with non-volatile analog synapses based on floating-gate transistors and ReRAM devices. By incorporating device-level nonlinearities directly into PyTorch-based training and inference, the tool enables optimization of physical synaptic parameters rather than idealized abstract weights. The framework is evaluated on standard neuromorphic benchmarks, including N-MNIST, DVS Gesture and Spiking Heidelberg Digits (SHD). For each model dataset configuration, it reports classification accuracy together with hardware-oriented metrics such as silicon area, power consumption and quantization sensitivity. These capabilities enable cross-layer design space exploration and help identify neuron-synapse configurations that best satisfy application-specific constraints on accuracy, energy efficiency, area and hardware fidelity.

Adaptive control learns the plant online; neural-operator control learns the control gains offline. We bring the two together for a class of nonlinear hyperbolic PDEs whose dynamics are governed by an unknown Volterra series of arbitrarily many kernels. An observer-based passive identifier learns a truncation of this series online. The infinite-dimensional map that synthesizes the backstepping kernels from the parameter estimates – a cascade of PDEs on simplex domains of increasing dimension, prohibitive to solve in real time – is approximated once, offline, by a neural operator. The closed loop then carries two learning processes in series: online learning of the plant feeds an offline-learned PDE solver, whose output is the online control gains. We prove closed-loop stability and asymptotic regulation of the plant state, observer state, and input, on a basin that recovers the exact-kernel basin as the neural-operator accuracy improves. With a single Lyapunov function we absorb at once the perturbations – all vanishing – of truncating an infinite Volterra series, of identifying the plant online, and of approximating the gains.

This paper systematically analyzes the relationships among the $dq$-domain, $\alpha\beta$-domain, and sequence-domain representations used in small-signal impedance modeling of voltage-source converters (VSCs). It is shown that the AC impedance matrix expressed with $dq$-complex and $\alpha\beta$-complex variables leads to different formulations in the sequence domain. The study demonstrates that asymmetric systems exhibit different physical phenomena in the rotating and stationary reference frames; therefore, the transformations between these frames are not physically consistent in such cases. It is also demonstrated that the so-called modified sequence-domain impedance is equivalent to the universal impedance model in the frequency domain. The analysis clarifies several notational inconsistencies found in the literature. Finally, a physical interpretation is presented highlighting the implications of using stationary and rotating reference frames for stability analysis of power converters.

Accurate quantification of lung disease severity from chest imaging is critical for clinical decision-making and resource allocation. We propose a tri-modal deep learning framework, TMF-RSE (Tri-Modal Fusion with Regional Semantics and Evidential Uncertainty), that combines appearance features from two-dimensional chest inputs, structural features from lung segmentation masks, and semantic features from vision-language models (VLMs) for severity quantification. Our approach employs complementary fusion mechanisms that integrate semantic guidance, structural priors, and hierarchical interactions across modalities. The model employs evidential regression to provide both severity predictions and uncertainty estimates. Experiments on the Per-COVID-19 CT and RALO datasets show that TMF-RSE outperforms recent transformer-based baselines, achieving MAE of 4.02 and Pearson correlation of 0.9629 on Per-COVID-19 validation, and 0.339 MAE / 0.973 PC on RALO geographic extent.

In non-convex markets, a competitive equilibrium may fail to exist. This turns out to be an important issue in real-world non-convex auction markets, such as electricity markets, as it complicates pricing and requires the auctioneer to resort to out-of-market discriminatory side payments to sustain an equilibrium. We investigate whether the introduction of convex financial trading induces a smoothing effect, mitigating the issues arising from non-convexities. We develop a two-stage non-convex market model (a forward market followed by a spot market) in which convex financial traders participate in the forward market. Our model predicts that financial trading reduces the magnitude of side payments required to support the cleared allocation. To test the prediction of our model, we examine the introduction of a transaction fee on financial traders in 2020 by PJM, the US's largest electricity market. We show that the substantial decline in financial trading volume caused by this policy coincided with a significant increase in side payments, in line with our theoretical predictions.

We evaluate joint probabilistic and geometric constellation shaping via reinforcement learning for complexity-constrained joint equalization and demodulation of direct detection optical signals. We demonstrate the proposed technique in a simulated 56 GBd, 2.2 km C-band direct-detection system, demonstrating its effectiveness for complexity-constrained receivers.