Papers

The ResNet-18 image classification model is employed to determine the physical parameters of a plate reverb from a recording of the impulse response. The model is adapted to derive parameters using normalized and downsampled multi-resolution spectrograms computed from the provided impulse responses (IRs). To refine the prediction of the output location, the spectral phase response is also included as an additional input channel to the network since multiple output locations can give the same magnitude response for high-order resonant modes. On a 5000 IR validation set, our model achieves an average normalized mean squared error (NMSE) of 0.02920 across all parameters, with the lowest average NMSE occurring for parameters yo (0.00228), Ly (0.00347), and xo (0.00574).

State tracking from sequential observations can require both retaining information and updating it by composing observed operations. We extend Mamba-3's diagonal transition with an input-dependent low-rank reflection term to support noncommutative state tracking, in which the order of operations matters. The rank-one update couples state coordinates along an input-dependent direction, enabling non-diagonal state transitions within a single Mamba-3 block. The extension preserves Mamba-3's exponential-trapezoidal discretization, rotary embeddings (RoPE), and readout. For training, we adapt chunkwise computation to parallelize the proposed recurrence within each chunk. Experiments cover group word problems with discrete inputs and a shell game with continuous observations, in which a policy is trained by behavioral cloning. Among the models selected for their strong performance under fixed timing, the proposed model maintains higher tracking success on longer swap sequences in the shell game with continuous observations and timing jitter. These experiments show that the proposed method achieves high accuracy on the evaluated non-commutative tracking tasks, improving on standard Mamba-3. The extension thus offers a Mamba-3-based approach to non-commutative state tracking.

This paper proposes adaptive tensor tracking for angular trajectories (ATTRACT), a structure-aware alternating least squares algorithm for low-latency target tracking in reconfigurable intelligent surface (RIS)-assisted sensing. The received echo is represented as a dynamic third-order PARAFAC tensor that separates angular, delay, and Doppler information. Unlike batch tensor estimators, ATTRACT processes one data slice at a time and carries forward the preceding factor estimates, avoiding the need to collect an entire sensing window before updating the target state. Its distinguishing feature is the integration of delay and Doppler structure into each iterative update through the known transmitter-RIS channel, pilot signals, and RIS configurations. Numerical results show that, for a large enough RIS, ATTRACT achieves accuracy comparable to the offline tensor baseline at high signal-to-noise ratios while reducing computational overhead and providing slot-wise estimates.

This paper presents the design and experimental evaluation of a fully solderless realization of a 400 V, 2.5 kW GaN-based variable speed drive (VSD), using screw-clamped resin molds and rubber compression pads instead of soldered interconnections. The power stage uses 650 V GaN power transistors and is operated at a switching frequency of 200 kHz. The solderless demonstrator is compared to a soldered reference realization using an identical printed circuit board (PCB). Over 120 thermal cycles with heatsink temperatures up to 90 {\deg}C, the solderless contacts show no degradation in effective on-state resistances (including contact resistances). Separately, open-loop vibration sweeps from 5 Hz to 2 kHz with acceleration amplitudes above 10 g were performed on the solderless assembly and left the continuously powered demonstrator electrically intact; subsequent resistance and nominal-power checks likewise indicate no contact degradation. An initial life-cycle assessment (LCA) indicated a higher embodied carbon footprint for the solderless realization due to 3D-printed resin molds, whereas a prospectively evaluated injection-molding scenario reduces the carbon footprint to near that of the soldered reference. The solderless assembly furthermore enables non-destructive component replacement, as demonstrated after a power transistor failure, as well as component re-use. These results support the feasibility of repair-oriented, industrially relevant kilowatt-class solderless power converters.

Reward rate is a key performance criterion in cyber-physical and robotic systems where time, workload, and coordination costs are limiting resources. We introduce reward-rate congestion games, where agents seek to maximize reward per unit execution time. The direct reward-rate game is generally not an exact potential game. We develop a Dinkelbach-based framework in which, for every fixed Dinkelbach parameter, the transformed game is an exact potential game. This yields a potential-level Dinkelbach iteration that terminates finitely at the optimal potential reward rate when the inner potential maximization problem is solved globally. We also provide a sufficient condition under which an equilibrium of the transformed game is an equilibrium of the original reward-rate game. To optimize aggregate performance, we introduce marginal externality corrections that make the corrected potential coincide with the Dinkelbach-transformed social reward-rate objective, thereby enabling optimization of the social reward rate. Finally, we develop a continuous-time replicator–Dinkelbach dynamics for reward-rate population games coupling fast replicator dynamics with a slow reward-rate update. We establish convergence of the fixed-parameter replicator dynamics, global asymptotic and local exponential stability of the reduced Dinkelbach dynamics, and local exponential stability of the coupled system for sufficiently slow Dinkelbach updates. The framework is illustrated on a continuous task-allocation problem.

This paper investigates the threat to ballot secrecy in the Brazilian electronic voting machine (UEB) posed by electromagnetic side-channel attacks, also known as TEMPEST attacks. In these attacks, screen content can be reconstructed remotely by intercepting electromagnetic emanations associated with the target device's video signal. This work is motivated by a recent ruling by a Brazilian electoral court concerning an attempt to violate ballot secrecy using electronic equipment. Based on publicly available information about the electoral system, attack scenarios against polling stations are proposed. Experiments using software-defined radio show that the effectiveness of TEMPEST attacks strongly depends on the lack of oversight resulting from public unawareness of the threat. Finally, awareness guidelines are proposed for voters, poll workers, and party representatives to mitigate attack risks within a polling station.

Text-to-audio (TTA) generation aims to synthesize realistic audio that faithfully reflects natural-language descriptions. Most TTA systems adopt a two-stage latent paradigm: an audio tokenizer is optimized for reconstruction and then frozen, after which a generative model is trained in the resulting latent space. However, reconstruction-oriented representations may be suboptimal for generation, motivating joint representation and generative learning. To this end, we introduce Unite-Audio, to our knowledge, is the first to jointly learn continuous audio representations and latent flow matching for TTA. By coupling reconstruction with self-supervised generative prediction, Unite-Audio allows the generative objective to directly shape the latent space rather than treating it as a fixed intermediate representation. We further employ Flow-GRPO post-training to improve text-conditioned generation. Experiments show competitive TTA performance with a compact latent flow model, while ablation studies confirm the benefit of jointly learning the audio representation and generative model. Audio samples are available at https://runwushi.github.io/Unite-Audio.

Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, protecting them requires mapping that is accurate for individual forest parcels yet deployable continent-wide. Geospatial foundation model (GFM) embeddings enable label-scarce land classification, but their value for old-growth detection remains unknown. Here, we map old-growth forests across 211,893 ha of Romania's Southern Carpathians, a beech-spruce landscape typical of the Alpine Biogeographic Region. We construct high-confidence, expert-informed reference labels for old-growth and non-old-growth parcels. We add AlphaEarth, TESSERA v2 and Sentinel-1/2 features to a common baseline of topographic and human-access predictors, then compare them under spatially blocked validation with and without 10 km train-test buffers to limit residual autocorrelation. With buffering, GFM and Sentinel-1/2 predictors increase precision-recall AUC by 0.21-0.25 [95% CIs: 0.15-0.34] relative to baseline, indicating spectral data contain a spatially robust old-growth signal. With a PR-AUC of 0.84 [0.79-0.88], TESSERA outperforms Sentinel-1/2 (+0.08 [+0.05 to +0.11]) and AlphaEarth (+0.08 [+0.04 to +0.12]) under unbuffered spatial validation. At a 10 km buffer, however, this advantage narrows to +0.04 [-0.01 to +0.11] and +0.03 [-0.04 to +0.10], intervals consistent with no difference. At 10 m resolution, convolutional neural networks add no benefit over pixel-based XGBoost. Comparisons with four national- and continental-scale products show the importance of non-old-growth labels, and reveal 81% agreement between our predictions and a field-calibrated map. We conclude that buffered spatial validation is vital when transferring old-growth detection models to unseen landscapes, and provide our labels and predictions for future work.

Electrocardiography (ECG) contains subject-specific morphology that supports biometric recognition, yet image-based performance depends on how the waveform is rendered. We introduce representative-morphology heatmaps, a deterministic ECG-to-image representation adapted from ECGXtractor. Within each block of ten aligned beats, the five beats closest to the block mean are averaged into a 400 by L matrix and rendered either as a conventional trace or as a dense cardiac-time-by-lead heatmap. Since both representations contain identical physiological samples, their comparison isolates the effect of rendering. We evaluate verification and closed-set identification on PTB, ECG-ID, and MIMIC-IV-ECG-DEMO. Five compact models, including ZACH-ViT, are trained from scratch, while six ImageNet-pretrained CNN and transformer backbones assess model scale and visual transfer. Heatmaps improve both FNMR operating points and both identification ranks in all 15 compact model-dataset comparisons, while EER improves in 14. Across the matched experiments, EER decreases by 9.59 percentage points and Rank-1 increases by 24.69 points on average. ConvNeXt-Tiny reaches 2.43% EER on PTB and 5.79% on ECG-ID, whereas DeiT-Base reaches 14.92% on MIMIC-DEMO. ImageNet initialization clearly benefits the two multilead datasets but has a mixed effect on ECG-ID, and performance does not increase monotonically with model size. The best heatmap systems approach the strongest signal-domain EER on PTB and ECG-ID, while DeiT-Base provides the strongest evaluated performance on MIMIC-DEMO. Lead-channel ablation further shows that useful channel combinations depend on the cohort and biometric task. Overall, representative-morphology heatmaps provide an effective image representation for ECG verification and identification.

Coordinating large population of flexible grid-edge devices can alleviate the need for time-consuming and capital-intensive network upgrades, and AI-based control methods such as multi-agent reinforcement learning or imitation learning are promising in their real-time decision scalability. However, system operators still need an independent and rigorous way to decide whether a given AI system is safe enough for deployment. This paper develops a finite-sample probabilistic safety certification framework for black-box AI decision models in closed-loop grid operation. The central idea is to reduce the complete input–AI–grid evaluator workflow to a binary unsafe outcome under an operator-defined safety specification, and then use exact binomial inference to certify the corresponding unsafe operation probability. Given a set of held-out calibration scenarios, the framework returns the tightest one-sided upper certificate and an accept/reject deployment criterion that controls the probability of false safety certification. Because the certification is for the calibration distribution that may deviate from the future operation, we further combine the nominal certificate with physically interpretable sample-space adversarial attacks, a concept widely used in AI to investigate the fragility of AI models. Case studies on grid-edge flexibility coordination with 1{,}000-agent AI models (independent parameters) verify the finite-sample safety guarantee and the value of integrating adversarial attacks into a rolling-window training-certification-deployment flow.

Downlink channel state information (CSI) feedback is essential for frequency-division duplex massive MIMO, yet the feedback overhead grows rapidly with the numbers of antennas and subcarriers. To reduce this overhead, most deep learning approaches compress CSI by treating it as a generic image, leaving its low-rank multipath structure unexploited. In contrast, model-driven alternatives explicitly embed this structure in iterative recovery, but at the cost of high computational complexity and latency. To overcome these limitations, we propose a low-rank prior-guided (LRP) framework that performs learnable rank-one sensing at the user equipment to compress CSI into low-dimensional codewords, and reconstructs CSI by direct rank-one synthesis at the base station. Both compression and reconstruction are jointly optimized, and fully exploit the low-rank structure of CSI. We further develop DCRNetV2, which preserves LRP as its backbone and uses gated dilated-convolutional residual paths to compensate for finite-rank errors. Experimental results show that LRP outperforms iterative model-based methods with lower complexity, and DCRNetV2 achieves a better accuracy-complexity tradeoff than existing learning-based methods.

Global building and settlement products increasingly support population mapping, exposure assessment, and urban monitoring, yet comparative evidence remains fragmented across representations, geographic contexts, and evaluation methods. We benchmark seven global or near-global products against harmonized reference building footprints across 135 study areas. Our representation-aware framework integrates complementary measures of detection, geometric agreement, and aggregate quantity accuracy with stratified analyses of settlement characteristics, evaluation resolution, reference provenance, and temporal alignment. Overture Maps achieved the highest median city-level vector F1 (0.786), while 3D-GloBFP showed the closest aggregate building-area agreement despite weaker detection performance. Raster rankings were scale-dependent: Google Open Buildings Temporal (OBT) performed best at 10\,m (F1 = 0.680), whereas WSF Tracker led at 100\,m (F1 = 0.904) but substantially overestimated reference building area (relative bias = 1.845). Raster accuracy increased with building density ($\rho=0.58$–$0.75$), while smaller candidate footprints were disproportionately associated with vector false positives. Temporal alignment improved WSF Tracker mean city-level F1 by 0.060. These findings demonstrate that product reliability depends on representation, spatial scale, and settlement context, providing a reproducible framework for assessing the suitability of EO-derived urban information for different applications.

Studies of machine-learning-based power system protection are difficult to compare because task definitions, measurement access, data partitions, metrics, and generalization conditions often differ. EvEMTBench addresses this gap with an open, executable, and versioned benchmark that fixes these evaluation choices while leaving model design open. Across four grids spanning 20-345 kV, it defines 12 protection and event-analysis functions instantiated as 24 scored tasks and supports structured evaluation across observability conditions, predefined distribution shifts, and zero-shot and fine-tuned cross-grid transfer. Committed partitions, leakage controls, and reproducible reporting provide a common basis for comparing future methods. A reference evaluation spanning trivial, conventional, feature-based, and deep-learning baselines shows that wider observability is not uniformly beneficial, shifted conditions can reveal failures not apparent in-distribution, and cross-grid transfer is substantially stronger for fault detection than for fault localization. Protection-relevant diagnostics identify failure modes not apparent from primary metrics alone. EvEMTBench therefore makes generalization in machine-learning-based protection an explicit and reproducible evaluation problem.

We study the distributed average consensus problem under persistent link-level disturbances modeled as a martingale difference sequence with uniformly bounded conditional second moments. Under such disturbances, the standard stochastic-approximation-based linear iteration with diminishing stepsizes drives the network to consensus on an unbiased random variable with non-vanishing variance instead of the exact initial average. To understand and resolve this limitation, we develop an anchoring-based mechanism derived from a decentralized gradient descent formulation and study the effect of incorporating a decaying anchoring term that continuously pulls each agent state toward its initial value. This perspective provides an intuitive interpretation of how state anchoring counteracts disturbance accumulation. Under standard summability conditions, we prove that the resulting algorithm achieves exact average consensus almost surely. Furthermore, this decentralized gradient perspective offers a unifying framework for several related methods and an interpretable design principle for exact average consensus under persistent disturbances.

Conventional image registration algorithms are robust to domain shifts and achieve low errors, but they are slow and computationally expensive. Deep-learning methods are efficient at inference-time, but face challenges in out-of-domain samples. We propose Recursive Uncertainty-Gated Image Registration (RUGI), an algorithm for iteratively refining deformation fields predicted by learning-based registration models. At each iteration, the registration model predicts an incremental deformation, and a gating map modulates the update. Refinements are hence concentrated in regions that remain difficult to register. We explore two gating strategies: a learned uncertainty-based approach and an image residual error approach. We evaluate RUGI on cardiac MRI and echocardiography datasets and show consistent improvements over single-step inference. Ablation experiments demonstrate that iterative refinement alone improves registration, but informative spatial gating provides a significant additional benefit. The error-gated variant of RUGI can also be applied directly to existing pretrained models; applied to VoxelMorph, TransMorph, and CycleMorph, it yields MSE reductions of 27-37% with no modification to the original training procedure. The improvements in registration performance are reflected in decreased errors in ejection fraction estimation relative to ground truths. These results demonstrate that spatially selective iterative refinement provides an effective strategy to improve registration accuracy at inference-time.

Early reflections in spatial room impulse responses (SRIRs) measured using spherical microphone arrays (SMAs) play an important role in spatial audio analysis, rendering, and reverberation modeling. Their accurate localization and characterization can facilitate the analysis, processing, and manipulation of measured reverberation fields. This paper proposes a method for detecting and characterizing early reflections based on the Herglotz wavefunction formalism. The measured sound field is represented as a continuous superposition of incident plane waves, from which a localization function is derived in the spherical harmonic domain. An adaptive radial Gaussian fitting procedure is then used to estimate both the directions of arrival (DoAs) and the number of incident reflections within a single analysis frame. The proposed framework is evaluated using simulated and measured SRIRs and compared with conventional steered response power (SRP) and multiple signal classification (MUSIC) localization methods. The results demonstrate improved localization accuracy and more reliable detection of multiple simultaneous reflections, highlighting the potential of the proposed Herglotz-based formulation for the analysis of early reflections in SMA-measured SRIRs.

Compressive sensing (CS) exploits intrinsic signal sparsity for efficient representation of high-dimensional data. However, conventional CS relies on fixed-length measurement representations and dense reconstruction operations, leaving communication and computational costs largely determined by system dimensions rather than signal sparsity. Here, we propose a neuromorphic CS framework centred on a spike-driven learned iterative shrinkage-thresholding algorithm (S-LISTA). By representing compressed measurements and reconstruction updates as sparse events, the framework links intrinsic signal sparsity to the spatiotemporal sparsity of spiking neural networks (SNNs), extending the benefits of sparsity across sensing, transmission and reconstruction. Communication and computational costs consequently depend on event activity, allowing sparse representations to translate into resource savings. Extensive experiments demonstrate substantial reductions in transmitted data volume and estimated reconstruction energy while maintaining competitive reconstruction and downstream task performance. The framework also exhibits robustness under challenging channel conditions. These findings establish neuromorphic CS as a promising paradigm for signal reconstruction in resource-constrained scenarios.

Backscatter communication has proven to be a key enabler for energy-neutral sensor nodes in the IoT. It allows ultra-low-power nodes to transmit sensor data by reflecting incident RF signals. Practical large-scale deployment requires hardware solutions that are both cost-efficient and widely available. This paper investigates the practical limits of implementing backscatter transmitters exclusively using COTS components. We compare a two-load and multi-load architecture in terms of hardware requirements, complexity and spectral efficiency highlighting the most important trade-offs. A multi-load backscatter architecture is developed using a resource constrained low-power microcontroller, levering DMA to achieve high switching speeds while minimizing processing overhead. Furthermore, we present a layout agnostic load design methodology based on scattering parameters, allowing precise control of the reflection coefficients. A prototype implementation demonstrates a successful backscatter transmission of a single-sideband chirp with reduced harmonic distortion. Measurement results show suppression of the backscattered carrier and the second sideband by 10 dBm. This demonstrates that low-cost sensor nodes can be built using COTS components enabling remote monitoring at extended lifetimes.

Outer-hair-cell (OHC) loss is a primary deficit of sensorineural hearing loss (SNHL), impairing cochlear amplification and frequency selectivity and thereby elevating hearing thresholds. Biophysically-inspired DNN-based hearing-aid (HA) algorithms have been proposed to compensate for OHC deficits and have shown clear benefits in objective speech intelligibility and quality metrics (e.g. HASPI, HASQI). However, comprehensive subjective validation of these benefits in human listeners is still missing. In this work, we present a subjective evaluation of a biophysically-inspired HA model targeting OHC deficits. The cochlear module of an auditory model was individualized based on each listener's pure-tone audiogram and integrated into a trainable system, which includes the personalized model and a normal-hearing reference model, and the resulting trained HA was evaluated using a Matrix test comparing intelligibility scores for unprocessed and HA-processed noisy speech. The results revealed a significant benefit of the HA model over the unprocessed condition in the range of +1 to +27%, providing behavioral confirmation of the efficacy of the HA model. This study closes the gap between objective and perceptual evidence for this new generation of DNN-based HA algorithms, paving the way for their integration into next-generation DNN-accelerated chips for hearables and hearing aids.

Rapid growth of data centers and artificial-intelligence services is producing computational loads at scales once associated mainly with largest power plants. Recent grid events show that a routine transmission disturbance can cause several gigawatts of data-center demand to disconnect or transfer to backup nearly at once. This article revisits the classical synchronization and transient-stability theory needed to reason about such events. We organize four lines of work—graph-based synchronization conditions, winding-number descriptions of nonlinear power flow, separable convex network optimization, and direct energy methods—into a single cycle-space certificate framework for the lossless fixed-voltage model. The static layer gives an exact strict-cohesion test within a prescribed winding cell and reveals the widely used Dörfler–Chertkov–Bullo test as a quadratic surrogate of the same convex problem. The dynamic layer converts the critical-energy calculation into a finite family of convex boundary problems. Standard MATPOWER benchmarks illustrate both what the stronger static test gains and where it gains nothing: the 118-bus case admits $16.2\%$ more loading than the sufficient screen, while the 39-bus case is bridge-limited and the thresholds coincide. A stylized $2.7$-GW 39-bus event further shows that transient margin can change by about a factor of two depending on where balancing power is supplied, even when every final balanced operating point remains statically feasible. The result is a tutorial synthesis and an extensible deterministic certificate for emerging gigawatt-scale computational-load contingencies.

As extremely large antenna arrays (ELAAs) become central to next-generation wireless systems, the transition into the near-field propagation regime enables the exploitation of spherical wavefronts for radial-domain beamfocusing. This capability is pivotal for emerging applications requiring precise spatial isolation, such as Space Division Multiple Access (SDMA), hierarchical localization and advanced sensing. However, fully realizing these technologies requires specific design rules to dimension multi-user systems without relying on computational expensive full-wave simulations. To address the gap in modeling contiguous focal regions with controllable radial resolution, this paper expands the Angular Spectrum Representation (ASR) approach to propose a comprehensive analytical framework. Through the introduction of a tunable inter-beam overlap parameter $\rho$, we derive closed-form expressions to synthesize multiple focal regions, providing the flexibility to tailor their radial resolution. Furthermore, the resolution capabilities are analyzed to characterize the interplay between key operational variables, such as the transmitter size, beam radius and operation frequency. System-level assessment of per-user and sum-rate spectral efficiencies across varying signal-to-noise (SNR) regimes reveals how the inter-beam overlap dictates a fundamental trade-off between user capacity and inter-user interference, delivering design guidelines for future near-field communications.

In neuropsychiatry, the primary goal is often not only to decode brain activity but to change it, for example to lessen a negative affective bias or an overly salient memory. Motivated by control theory, we develop an AI-driven neural-surrogate framework that proposes candidate representational changes and tests their predicted perceptual effects from snapshots of stimulus-evoked fMRI activity, without physical stimulation. The framework combines fMRI decoding, deep generative modeling, and constrained latent-space steering. Valence and memorability are used only as worked examples. Using more than 36,000 image-fMRI observations from four deeply sampled Natural Scenes Dataset participants, subject-specific models recovered coarse generative structure from visually responsive cortex (two-way identification, 0.79-0.88; chance, 0.5). Graded perturbations were reconstructed as images and evaluated with automated scorers and human ratings from 7,200 trials by 18 participants. In the primary VDVAE model, valence shifted from -0.61 to +1.03 SD and memorability from -1.34 to +1.45 SD; a later Versatile Diffusion refinement reduced or altered these effects. Across five perturbation levels, human valence ratings moved in the predicted direction under the linear time-correction model (mean slope, 0.038 SD per unit of alpha; 95 percent CI, 0.003-0.074; positive in 16 of 18 participants). Perceived memorability did not change reliably. Baseline agreement with the automated assessor was suggestive for valence (r = 0.30) and weak for memorability (r = 0.10). Extreme perturbations drifted from the original stimulus, so intended change must be weighed against loss of fidelity. These findings provide a falsifiable upstream method for designing and behaviorally testing candidate representational targets for future neuromodulation in psychiatry, while marking the limits of the present static approximation.

Tuning PID controllers to satisfy competing objectives - low tracking error, fast settling, limited overshoot, and moderate control effort - is labor-intensive and requires expertise. Genetic algorithms (GAs) offer gradient-free optimization of controller gains against a weighted fitness function, but success depends on meta-level choices: population size, generation budget, gain bounds, and fitness weights. These are usually set by manual trial-and-error or costly bilevel optimization, exposing a tension: GAs excel at dense numerical search, but configuring them needs high-level, context-dependent semantic reasoning. We propose GA-Agent, which decouples these modes. A standard GA handles low-level PID gain optimization. A large language model (LLM) agent operates at the meta-level: it observes completed GA runs, diagnoses gaps versus user control objectives, and proposes updated GA configurations. The architecture uses structured memory, quantitative goal translation, resource-aware termination, and outcome-driven routing. We evaluate GA-Agent on eight control case studies with diverse dynamics (DC motor, inverted pendulum, aircraft pitch, autonomous underwater vehicle, and others). GA-Agent achieves 100% success on all benchmarks, outperforming a Regular GA with fixed hyperparameters in solution quality and sample efficiency. It matches or surpasses a Cascade-GA baseline while reducing function evaluations by one to two orders of magnitude, typically converging in one to three optimization attempts. Sensitivity analysis shows robustness across LLM backbones and memory configurations. A compact memory buffer (size 2-3) and cost-effective models (DeepSeek-V4-Flash at about $0.002 per run) achieve superior performance.

Power swings in large Data Centers (DTCs) running Artificial Intelligence (AI) workloads can excite poorly damped modes in power systems. The resulting forced oscillations can lead to flicker, equipment disconnection, or blackouts. This paper investigates the risks of such load fluctuations for different system strengths and damping conditions. Using an analytical approach based on transfer functions, we identify critical DTC locations in the power grid at which load fluctuations could induce the largest forced oscillations and further characterize the harmonic spectrum of the resulting system response. Depending on the frequency and magnitude of the DTC load fluctuations, forced oscillations can become unbounded. The underlying instabilities are classified into saddle-node bifurcations of the forced periodic response and impasse-surface encounters, using Floquet multipliers and the minimum singular value of the algebraic Jacobian. Furthermore, the impact of different duty cycles and harmonic components beyond the fundamental oscillation frequency in square-wave load profiles is analyzed. Finally, the interaction of two oscillating DTCs is investigated for different locations and forcing frequencies, considering both synchronized and unsynchronized operation. The findings can help system operators to define new regulations on the maximum load fluctuations permitted for DTC facilities at specific grid locations, without negatively affecting the stability and operation of the system.

Generating controllable and human-like emphasis remains an open challenge in text-to-speech, even when explicit emphasis control signals are provided in the text input, limiting the communicative accuracy of synthetic speech in real-world applications. Reinforcement learning has recently shown promise for post-training TTS systems to align with human preference, yet existing methods have not been applied to word-level prosodic control. We present EmphTTS, a non-autoregressive TTS system that applies Group Relative Policy Optimization (GRPO) to the duration predictor with an emphasis localization reward, enabling direct optimization for word-level emphasis. Evaluations show that EmphTTS achieves the best emphasis controllability and performs the best in emphasis objective evaluation. In subjective preference tests, EmphTTS is significantly preferred over synthetic groundtruth and most baselines. Ablation studies show that GRPO improves emphasis realization beyond supervised-finetuning-based duration modeling and simple speaking-rate adjustment, while alleviating the mismatch between the independently trained duration predictor and TTS model.

Recent one-step text-to-audio (TTA) models substantially reduce inference cost, yet their generated distributions can still be improved through post-training. We propose DriftAudio, a distributional post-training method that adapts Drifting to pretrained one-step TTA generators. Applying Drifting condition-wise is challenging under free-form text conditioning, where only one or a few real samples are typically available for a particular condition. DriftAudio instead performs Drifting on the marginal audio distribution while retaining text-conditioned generation. The drifting field is estimated in a frozen audio feature space using resampled real samples, a rolling bank of generated samples, and the current batch of generated samples. The resulting Drifting field provides a detached training target for updating only the generator, keeping the original one-step inference procedure. On AudioCaps, starting from MeanAudio, DriftAudio reduces FAD and FD by 33.9% and 17.6%, respectively, while also improving KL and CLAP. Starting from FdAudio, it further reduces FAD, FD, and KL, with trade-offs in IS and CLAP. These results demonstrate the effectiveness of marginal distributional post-training for one-step TTA generation.

The growing demand for automation in the mining industry, particularly for the autonomous operation of articulated dump trucks (ADTs), has drawn increased attention to accurate vehicle modeling. The importance of such models lies in their use in model predictive control (MPC), model-based estimation methods, and vehicle simulation. While dynamic modeling offers a viable solution for these purposes, it is associated with complex setup and parametrization and may require recalibration in changing operating environments. As a result, kinematic models have dominated ADT modeling, especially in MPCs, at the expense of reduced prediction accuracy. In this work, we propose an approach using Gaussian Process Regression (GPR) to learn the sideslip angle of the vehicle, which is identified as the primary contributor to the reduced accuracy of kinematic models. The learned GPR function is augmented into the kinematic model to form a gray-box model that aims to reduce the gap to dynamic models. We show that the gray-box model can predict the sideslip angle and, consequently, the vehicle's lateral velocity, thereby improving the MPC's prediction performance. The resulting gray-box MPC is compared against two white-box MPCs in a simulation environment. The results indicate an improvement in terms of maximum lateral tracking error from over 2 m to 0.56 m.

Distributed intelligence concerns systems in which semi-autonomous components with local dynamics and partial observations coordinate through information exchange to maintain a shared function. This paper proposes an operational way to study such systems: measure information at the interface where a message changes a receiving action, then connect that measure to function by intervention and disturbance evaluation. We instantiate this proposal in DI-Walker, a two-dimensional four-limb embodied plant controlled by frozen Cross-Entropy-Method policies. We compare a controller using each limb's own realized-force sensor with one using the realized-force sensors of peer limbs. Under limb loss, limb slip, and weak central-control dropout, Peer-Sensor has lower late tracking error in several conditions. A corrected finite-history action-predictive estimator shows a substantially larger peer-message gain under compound failure. A future scalar functional-prediction estimator does not show the same stable advantage. We interpret this discrepancy as a methodological result: information useful for an intermediate control action can be hidden by later plant dynamics, redundancy, and context. The paper relates this result to Predictive Information, Transfer Entropy, Directed Information, information-to-go/IT-PAC ideas, empowerment, and the robust control data-rate perspective, while explicitly distinguishing operational predictive gains from exact Directed Information, channel capacity, and a formal data-rate theorem.

Magnetic navigation has emerged as a promising alternative for navigation in Global Positioning System (GPS)-denied environments, leveraging geomagnetic field maps in conjunction with onboard magnetometer measurements. However, its performance is highly sensitive to trajectory-dependent observability, which limits its practical effectiveness under conventional flight paths. This paper proposes an optimal trajectory design framework for magnetic navigation that maximizes information content along the flight path. The trajectory generation problem is formulated as an optimal control problem that minimizes the posterior Cramér–Rao lower bound on the position estimation error, subject to a penalty on path length. The resulting trajectories are non-intuitive and significantly enhance the observability of the navigation system. Simulation results demonstrate that the proposed optimal trajectories yield substantial reductions in estimation error compared to conventional straight-line trajectories, highlighting the critical role of trajectory design in enabling high-accuracy magnetic navigation. These findings suggest that trajectory optimization can substantially improve the viability of magnetic navigation as a robust alternative for aerospace applications in GPS-denied environments.

This paper proposes a robust high-dimensional minimum variance distortionless response (MVDR) beamforming method for array observations corrupted by heavy-tailed noise. The proposed approach constructs an MVDR-oriented precision matrix estimator by combining Maronna's robust scatter estimator with spiked covariance modeling. Using tools from random matrix theory, we derive a deterministic equivalent of the MVDR output power and obtain asymptotically optimal shrinkage weights for the dominant signal subspace. A fully sample-based implementation is then developed for practical beamformer design. Numerical simulations under elliptically distributed noise demonstrate that the proposed beamformer achieves stronger interference suppression and higher output SINR than competing methods in high-dimensional and implusive noise regimes.