Papers

This paper presents a compact, fully differential, two-stage millimeter-wave (mm-wave) cascode power amplifier (PA) designed and implemented in a 22nm FD-SOI CMOS process (22FDX+). The PA employs the newly introduced extended-drain MOS (EDMOS) device in 22FDX+, together with a carefully engineered device core and transformer baluns. At 50 GHz, the prototype achieves 18.8 dBm saturated output power (PSAT), 18.1 dBm 1-dB compression output power P1dB, and 21% power-added efficiency (PAE) at P1dB. To the best of our knowledge, this work achieves the highest reported power density of 2.6 W/mm2 among single-way, two-stage CMOS cascode PAs.

We propose $\textit{recursive encoder and decoder}$ (RED) for building a single deep neural network (DNN) model that can separate multi-speaker mixtures containing unknown numbers of speakers and variable numbers of microphones arranged in an unknown geometry, a task that has not been studied yet. The decoder of RED recursively detects whether there are active speakers left and separates one speaker at a time. It is designed to be trained in an end-to-end fashion to improve separation performance. The encoder of RED recursively encodes each microphone channel of the input mixture, sequentially incorporating spatial cues. Combining both, the DNN can be trained to separate mixtures not only with unknown numbers of speakers but also with variable numbers of microphones, achieving state-of-the-art performance on multiple public datasets.

Deep neural network based deepfake detection systems have achieved high levels of accuracy on benchmark datasets and competitions. However, most models lack interpretability. It is challenging to extract reasoning from the network that can convince the human evaluator to trust the decision. Humans often rely on acoustic cues like unnatural pitch jitter, robotic intonation, acoustic artifacts, and unnatural sounding fricatives to judge the quality of the synthetic audio. This study explores the role played by the voiced and unvoiced regions of speech in discriminating synthetic from bonafide speech. A measure of signal periodicity is used to analyze speech into voiced and unvoiced components. Then, the graph attention based AASIST detection system is trained independently on each component. This work compares the accuracy of deepfake detection system using voiced and unvoiced components and analyzes the results on the MLAAD dataset. Our results show that unvoiced regions are particularly more effective in distinguishing synthetic (deepfake) speech from bonafide, and achieves an equal error rate of 6.62%. When combined with voice regions through score-level fusion, the overall performance improves further, yielding a 5.82% EER, a relative improvement of 49% over the baseline system that uses the full audio.

Approximate Linear Programming (ALP) is widely used for large-scale Markov Decision Processes (MDPs), but its performance can be sensitive to the choice of state-relevance weights, which are typically selected heuristically. Performance bounds suggest aligning these weights with the discounted occupancy measure of the induced policy, and existing primal approaches address this through repeated greedy-policy construction. Nonetheless, they lack convergence guarantees and are computationally expensive. We propose a dual-based method that uses projected occupancy information from the ALP dual solution to construct a smooth stochastic policy and update the state-relevance weights, which avoids separate greedy-action calculations. We establish conditions under which the weights match the discounted occupancy of the induced policy and prove uniqueness and global convergence under appropriate smoothing. We also derive an a posteriori policy-loss bound that separates error from the weighted Bellman residual, occupancy mismatch, and stochastic-versus-greedy disagreement. Experiments on classical queueing and multi-priority scheduling problems show that the proposed approach reduces sensitivity to fixed weights and achieves comparable or better policy quality than primal updates at lower computational cost. Finally, we show that adaptive weighting is most valuable when the basis functions are sufficiently expressive for occupancy information to influence the resulting policy.

Control invariance validates that dynamical systems have a control input that preserves a given property at all times. This paper introduces a set of sound axioms and proof rules in differential dynamic logic (dL) that enable verification of control invariance. First, the scalar and vector comparison principles, relating a system of differential equations to a comparison system such that invariance properties can be established more easily, are axiomatized in dL. This axiomatization primarily utilizes differential ghosts, which are proof-theoretic generalizations of comparison systems. Next, with the comparison principles serving as the basis, comparison invariants are introduced, and sound axioms and proof rules are derived. Comparison invariants reduce the question of control invariance to a functional inequality on its Lie derivative for a suitable class of functions, moreover, the right choice of function can result in decidable arithmetic. Furthermore, the perennially popular control barrier functions (CBFs) used in safety-critical control are shown to be a special instance of comparison invariants. This yields an axiomatization of CBFs that leads to a dedicated set of proof rules. The rules allow for the verification of CBFs, which are traditionally used for synthesizing safe controllers without verification. Lastly, comparison invariants are shown to unify several other safety verification techniques, including Darboux invariants and differential invariants, further cementing their versatility.

In this paper we discuss the development of a fully pilotless multi-access-point Wi-Fi receiver. This is based on a self-attention Transformer that operates on per-(access point, subcarrier) tokens and outputs bit-wise logits for a standard low-density parity-check decoder. In realistic ray-traced indoor channels, pilotless decoding becomes feasible as soon as some spatial diversity is available. While a single-access point configuration does not attain practical error rates, when compared to an ideal maximum-ratio-combining baseline with perfect channel knowledge, cooperative configurations with three access points achieve coded bit error rates of approximately $10^{-5}$. This is achieved while benefiting from higher spectral efficiency by eliminating pilots.

Spatial audio is a key component of immersive $360^\circ$ media, yet high-quality spatial capture remains limited in real-world speech-dominant scenes. We study visually guided First-Order Ambisonics (FOA) speech spatialization in the wild: given aligned $360^\circ$ video and an omnidirectional audio track, we recover the missing directional FOA components. To support this task, we introduce YT-SPEECH, a speech-oriented $360^\circ$ video-FOA dataset curated from YouTube. We propose a two-stage Localizer-Renderer framework, where an audio-visual segmentation backbone provides frame-wise spatial heatmaps and a conditional complex-domain U-Net reconstructs directional FOA signals from the omnidirectional channel. A confidence-based gating strategy stabilizes conditioning under ambiguous acoustic conditions. Experiments show improved reconstruction fidelity, spatial accuracy, and perceptual speech quality relative to ablated variants and prior approaches.

Spatial audio enhances user immersion by reproducing 3D sound fields, with Ambisonics being a widely adopted representation. While Ambisonics is theoretically independent of the recording setup, practical microphone arrays introduce hardware-dependent encoding artifacts. Moreover, existing data-driven solutions lack flexibility, as they are typically restricted to fixed array geometries. To overcome these limitations, we propose ADEPS, a generative framework that explicitly embeds the physical acquisition model into the inference process. By leveraging this formulation, ADEPS effectively compensates for array-specific distortions while enabling zero-shot encoding across arbitrary array topologies. We train the underlying generative prior in an unsupervised manner solely on target Ambisonic representations. Extensive evaluations across diverse simulated and real microphone arrays demonstrate that ADEPS consistently outperforms both traditional linear and parametric baselines in spatial fidelity and spectral quality.

This paper theoretically analyzes how system model mismatch displaces finite-horizon maximum a posteriori (MAP) initial-state estimates in controlled dynamical systems under partial observation. From pathwise sensitivity analysis, the initial-state nominal-oracle displacement called MAP shift is decomposed into a model-side mismatch injection and an estimator-side curvature resistance to identify a sensor-dependent information-curvature margin as the amplification bottleneck. The margin is governed by the weakest posterior-curvature direction, so that sensor configurations that maximize aggregate information can still be fragile to mismatches. We connect the margin to nominal Gauss-Newton curvature and to the Bayesian Fisher information matrix, distinguishing instance-wise mismatch robustness from design-time inferability. The margin admits a computable nominal proxy in nonlinear systems, becomes explicit in the linear time-invariant case, and is validated through two numerical examples.

Predictive control based on an informative system trajectory, instead of a physics-based model, has received significant attention in recent years. This paper investigates the potential of using such data-driven control for vehicle dynamics control and autonomous path following. By considering the path following problem in the error space, the underlying system is approximately linear and existing results for data-driven predictive control can be applied. Also, scheduling based on longitudinal speed can be readily included. The proposed control algorithm was tested on two different lane change maneuvers in a high-fidelity simulation environment.

Reliable clot-volume quantification and subsequent risk assessment in pulmonary embolism depend on precise segmentation of emboli on computed tomography pulmonary angiography. Deep learning models for this task must be trained on accurate voxel-level labels. The three public datasets that provide such labels were annotated under different protocols, and some of their studies contain unlabeled emboli or labels that are discontinuous across slices. This Data Descriptor presents voxel-level pulmonary embolism annotations for 149 of the 166 studies in these datasets. A primary rater drew all annotations under a single protocol. A thoracic radiologist with more than 20 years of experience reviewed and revised them. Three raters at three different centers independently annotated a subset of 15 studies. The subset was selected by source dataset and embolus location. Technical validation quantifies volumetric agreement with the source annotations, changes in within-mask attenuation, and inter-rater agreement on the subset. The dataset is intended to allow segmentation models to be developed and compared under a common reference standard.

This paper describes the electricity markets and operational processes in the Irish power system and translates them into a Mixed Integer Linear Programming (MILP) model. The model is designed to estimate renewable generation Curtailment and Constraint. A full mathematical formulation is presented and tested on both a simple example and a realistic model of the Irish transmission network. The results show that the proposed formulation works as intended, capturing curtailment and constraint effects, while also highlighting model limitations and directions for future improvement.

We present a high-performance channelizer for Microwave Kinetic Inductance Detectors (MKIDs), designed to mitigate spectral leakage and scalloping loss through a 50% overlapping polyphase filter bank (PFB). The design is implemented on a Xilinx Zynq UltraScale+ RFSoC ZCU111 using a custom design - primarily in Vitis High-Level Synthesis (HLS), with the time-critical output serializer and glue logic in VHDL - that processes a 4.096 GSPS input stream with a per-branch super-sample rate (SSR) of 16. Rather than relying on aggressive 512 MHz clocking and vendor IP cores, our split-path architecture computes the delayed and non-delayed polyphase branches concurrently, so that the bulk of the channelizer operates at a robust 256 MHz while a single 512 MHz subdomain is confined to the BRAM-to-FFT section. This architectural parallelism enables a deep 16-tap prototype filter that doubles the filter depth of comparable high-speed systems and substantially improves channel isolation. We report the complete internal architecture of the reordering engine that implements the overlap, including two implementation hazards not documented in prior art: a pipeline-stage skew affecting state toggles in HLS, and the state-preservation requirements of a restartable design. The 2/1 overlapped channel response is validated in simulation - recovering the ~3.9 dB scalloping loss of a critically sampled channelizer to below 0.1 dB across the full 2 MHz channel - and characterized systematically with a 100-tone batch frequency sweep, while the parent readout system has been operated cryogenically with an MKID array in an adiabatic demagnetization refrigerator (ADR), identifying individual resonators in total darkness. The result is a resource-efficient, high-isolation benchmark for wideband frequency-division-multiplexed readouts.

Vibration and impact measurements in mechanical systems are invariably corrupted by noise, which degrades every quantity derived from them, such as modal parameters and contact forces. Classical filters attenuate noise only when its statistics are known a priori and often fail at very low signal-to-noise ratio (SNR) or under spectrally coloured noise. This work presents Time-Window Noise2Noise (TWN2N), a self-supervised method for blind denoising of signals produced by deterministic mechanical systems. The method requires neither a clean reference signal nor paired noisy observations, nor any prior characterization of the noise: by reconstructing each time instant from its temporal neighbourhood while masking the instant itself, a compact autoencoder is forced to learn the underlying dynamics rather than the noise. The formulation is general for any deterministic dynamical system, is computationally lightweight (a single feed-forward pass per sample at inference), and is assessed on two benchmarks with exactly known ground truth: the impulse response of a linear 3-degree-of-freedom system and a nonlinear Hunt-Crossley impact. Across white, pink, brown and quantization noise, and over repeated realizations, TWN2N yields statistically significant SNR gains (p < 0.001) without any prior noise information, and it is benchmarked against optimally-tuned Savitzky-Golay and wavelet (VisuShrink) filters. The benefit propagates to identification: at 15 dB input SNR, modal parameters that are unidentifiable from the raw signal are recovered within 4% of their reference values after denoising.

We prove the rank-one Lyapunov spectral identity recorded as Problem 9.1 in the 2004 collection of unsolved problems in mathematical systems and control theory. Let $P,Q,R$ solve the coupled discrete Lyapunov and Sylvester equations associated with $A$ and its rank-one update $A_2=A+vw^\top$. When the displayed inverses exist, we show that $P^{-1}RQ^{-1}R^\top$ and $(I+PQ)^{-1}$ have the same characteristic polynomial. A rank-one determinant factorization of the equation for $Q$ produces a scalar bilinear kernel. Evaluating it at the eigenvalues of $A$ and at their reciprocals gives $RQ^{-1}R^\top=BQ^{-1}B=P-BPB$, after which the two target matrices are the same two factors in opposite order. Polynomial continuation extends the identity from a nonempty open set of admissible systems to the full admissible domain and yields a determinant corollary without stability assumptions; when the spectra of $A$ and $A_2$ are disjoint, $Z=b(A)^{-1}P$ gives an explicit similarity. In the Schur-stable realization setting, the result recovers the associated principal-angle and past/future canonical-correlation spectra.

State estimation in partially known state space (SS) models is challenging when the dynamics or observation model varies across short data blocks. Classical model-based approaches, such as the expectation-maximization (EM) Kalman filter, jointly recover the latent states and the unknown model parameters, but rely on linear-Gaussian assumptions that should accurately describe the system and require numerous forward-backward passes. Consequently, their performance and computational efficiency may deteriorate under complex and non-stationary real-world conditions. On the other hand, learned Kalman smoothers are robust to model mismatch yet cannot adapt at inference to unseen model variations without labeled data. In this work, we propose EM-KalmanNet, an AI-aided tracking algorithm for adaptive smoothing in blockwise time-varying SS models. The method unfolds a fixed, small number of EM-like iterations into a trainable architecture: a parameter-aware RTSNet implements a learned E-step conditioned on the current model-parameter estimate, while a lightweight M-Net implements a learned M-step that updates the state-transition or the observation matrix using empirical moments, residuals, and gradient-related statistics. The two modules are shared across the unfolded iterations and are trained offline via a dedicated three-stage procedure. During deployment, the per-block parameter estimate is propagated between consecutive blocks, enabling observation-driven adaptation without labeled online data or knowledge of the noise statistics. Experiments involving linear and nonlinear models, Gaussian and non-Gaussian noise, Lorenz attractor tracking, and acoustic source localization demonstrate that EM-KalmanNet consistently outperforms model-based and data-driven benchmarks while substantially reducing inference latency relative to the EM-KF.

The rapidly expanding scale of electric vehicle (EV) fleets and continuously decreasing battery costs are making vehicle-to-grid services a reality. In this paper, we study the interaction between the problems of an EV aggregator's bidding in the regulation market and power allocation (i.e., determining the (dis)charging powers of the EVs in regulation deployment). Although the two problems are coupled, they are often regarded as decoupled and optimized separately for complexity issues. However, failing to consider the coupling of bidding and power allocation can lead to a decline in the profit of the EV aggregator (EVA). In this paper, we propose a framework for co-optimizing EVA bidding and power allocation in the regulation market. The bidding model is formulated as a stochastic programming problem with embedded power allocation in discretized regulation signal scenarios. To meet the solution time requirement for regulation deployment, we further propose a power allocation model that can be solved online. It utilizes the Lagrange multipliers from the bidding problem to ensure that the allocation results correspond to the optimal solution of the bidding problem. The effect of the proposed framework on improving EVA profits and reducing degradation costs is verified in the case study.

The intricate mixed-integer constraints in industrial load models not only pose challenges for their direct integration into economic dispatch or market clearing processes but also render current analytical dimension-reduction methods ineffective. We propose a novel data-driven dimension-reduction approach for industrial load modeling, which uses the optimal energy usage data from industrial loads to train a dimension-reduced model that best fits the original constraints. Our approach, implemented by the adjustable load fleet model, outperformed analytical methods across three industrial load datasets.

Pretrained EEG backbones improve transfer performance, but downstream diagnosis heads remain hard to audit: predictions are made from unrestricted hidden states, whereas explanations are usually produced only after the decision. We introduce tPoE-EIB, an evidence-information bottleneck head for adapting EEG backbones under an evidence-only prediction constraint. tPoE-EIB selects temporal and channel evidence, maps the selected summaries to Gaussian experts over a shared latent variable, and fuses them with a tempered product-of-experts posterior. The classifier observes only this latent, so the decision path is explicit and rate-limited by the expected posterior KL. This gives a tractable supervised objective with an information-rate penalty, while the closed-form tempered posterior mitigates overconfident fusion from correlated evidence axes. We evaluate tPoE-EIB on pretrained EEG foundation-model backbones across six diagnosis settings: event-type classification, abnormality detection, seizure detection, cognitive-decline staging, depression screening, and cerebrovascular-disease classification. The evaluation spans public benchmarks and in-house clinical cohorts, binary screening and fine-grained staging, and sparse and dense montages. tPoE-EIB preserves competitive balanced accuracy and improves over representative post-hoc explanations on selection-faithfulness audits, including insertion-deletion and gate-causality tests. Its structured posterior further enables integration-faithfulness audits, including expert-drop, posterior-reliance, and expert-disagreement tests. Overall, these results suggest that evidence-only, rate-limited fusion is a practical route to auditable diagnosis on top of frozen EEG foundation backbones.

With the advent of Large Language Models and its instruction following capabilities a promising application is the task of summarization. Within this domain of task the extractive sub-task of clinical protocolling has emerged as a topic of particular interest as it can significantly reduce the downtime and protocolling burden of health-care workers thus enabling them to focus on their core work helping humans. A further step towards automation is the direct generation of clinical notes from speech without intermediate transcripts, reducing processing time while preserving information such as coughing or other paralinguistic cues that may be lost in transcript-based systems. To this end, we present KIT's submission to this years BeTraC challenge in the lightweight track. Our main contribution is a scalable data augmentation pipeline that unifies heterogeneous medical dialogue datasets through synthetic speech generation and automatically generated SOAP supervision, enabling robust adaptation of a speech foundation model for end-to-end speech-to-SOAP generation.

An intelligent system does not merely reason: it governs its own reasoning - how much to compute, when to stop, which module to activate. Can that role be played by a dynamic internal field - a low-dimensional homeostatic state with explicit physics and certified stability - that modulates cognition without performing it? Ours is a field on the module graph governed by a family of PDEs on the graph Laplacian, advancing with an adaptive-depth reasoner. We certify the stability of the integrator of the whole family - an integrator certificate, not a closed-loop one. New, and proved here: a discrete Schur-Cohn criterion for Verlet with velocity coupling, necessary and sufficient per latent root, with no commutation hypothesis. The answer is threefold: substance no, structure only in part, certifiability yes. The type of the field's physics is irrelevant for accuracy: wave, diffusion, gated mixtures and a 2D Navier-Stokes substrate tie. A twenty-seed preregistered deconfounding campaign bounds the structural claim: at equalized caps the second-order effect is strong in one family (+0.087 [+0.042, +0.132], t=4.0) but is not detected in the other (+0.014 [-0.013, +0.040], n.s.), so part of the original contrast was capacity, not order; and a matched-interface GRU is indistinguishable in the first and nominally exceeds the field in the second (-0.035 [-0.067, -0.002]). What distinguishes the field is not capability but that its one-step operator admits an exact runtime stability check - a difference of kind, not of existence: learned recurrences carry certificates too, sufficient and conservative ones. A kill-gate with a positive control finds no evidence for the field as evidence accumulator (Delta AUC +0.0007 [-0.0065, +0.0079] vs a 0.03 threshold). A dynamic internal field is a viable, certifiable compute governor, but not an enhancer of cognition: it modulates, it does not think.

With the increasing penetration of electric vehicles (EVs), uncoordinated EV charging and the resulting chaos, disorder, and long waiting times at EV charging stations (EVCSs) will no longer be tolerable. An EV charging right (CR) is the right to reserve a predefined charging service. By purchasing CRs, EVs can reduce their charging waiting time, and the price of CRs can guide EVs toward optimized charging behaviors. In this article, we define CR, propose the CR trading mechanism (CRM), and analyze the effect of CRM on reducing waiting times and mitigating congestion in EV charging. In the proposed CRM, EVs can purchase CRs in advance, and the CRs are used to estimate the waiting time and update the price of charging. Queue theory is utilized in the waiting time estimation, in which the impact of disclosing queue states at EVCSs is considered for the first time. The simulation results verify the accuracy of the waiting time estimation and the effect of the proposed mechanism.

Despite the promising applications of electronic noses (e-Noses) in medical diagnosis and industrial process control, sensor drift remains a critical challenge that degrades long-term sensing reliability by inducing gradual shifts in sensor responses. Conventional drift compensation methods are typically designed for batch learning and lack the ability to support continuous online learning in non-stationary environments. Although several online drift compensation methods have recently been proposed, they are mainly based on quasi-online mini-batch learning for distribution adaptation, while true sample-wise online learning without buffering remains largely unexplored. To address these issues, this paper proposes a sample-wise online drift compensation method based on spiking neural networks (SNNs) for feature adaptation and spiking reservoir computing (SRC) for classification. By exploiting spike-timing-dependent plasticity (STDP), the SNN self-organizes spatiotemporal attractor dynamics for label-free feature adaptation (STDP-FA), and the adapted features are classified by SRC with self-supervised adaptation driven by winner-take-all (WTA) competition. The proposed method addresses various concept drift patterns, including gradual drift, random drift, sensor failures, and abrupt changes. Simulations on a real-world sensor drift dataset demonstrate a clear improvement in classification accuracy over baseline methods.

Visible light communication (VLC) offers wireless data connectivity indoors, yet its performance is severely limited by link blockages. While optical reconfigurable intelligent surfaces (ORISs) have been proposed to overcome these blockages, existing literature predominantly relies on the unrealistic assumption of ideal channel state information. In this paper we investigate the contribution of ORIS elements in VLC systems under practical, non-ideal channel estimation scenarios. We analyze the communication performance using two pilot-based estimation techniques: pilot symbol assisted modulation (PSAM) and superimposed training (ST), evaluating the impact of data power allocation factors and averaged orthogonal frequency division multiplexing (OFDM) symbols. Our results show that PSAM with an ORIS deployment enables optimal large data power allocation factors, resulting in spectral efficiency improvements that surpass scenarios with ideal channel estimates but without ORIS deployment. While ST performs well with a large number of averaged OFDM symbols, it is unable to overcome the performance of PSAM when ORIS elements are deployed. We also find the system robust to imperfect ORIS orientation; even with only half of the elements accurately aligned, performance remains acceptable. Ultimately, we show that spectral efficiency values of approximately 5 bits/s/Hz are achievable using ORIS with PSAM, a performance comparable to, or even exceeding, that of unobstructed line-of-sight links.

Modern energy management systems, even within advanced energy internet (EI) infrastructures, remain fundamentally reactive, optimization-bound, and incapable of reasoning about context, intent, or uncertainty. While the EI paradigm has established a powerful cyber-physical architecture for interconnecting distributed energy resources via software-defined packetized networks, the question of how such systems should think, adapt, and govern energy decisions intelligently remains an open challenge. This paper introduces cognitive energy management (CEM); a new conceptual framework that addresses this gap by redefining how energy systems perceive, reason, learn, and act within complex operational environments. Grounded in the EI cyber-physical foundation, CEM extends beyond conventional optimization by embedding goal-directed reasoning and continuous adaptation into the energy management loop, positioning itself as the cognitive governance layer of EI-based infrastructures. We formally define CEM, distinguish it from rule-based and optimization-based paradigms through structured comparison, and articulate its core architectural layers. To demonstrate the framework's practical value, we develop a toy problem grounded in smart port energy management; one of the most operationally demanding EI node environments in modern infrastructure. Specifically, we model a predictive vessel turnaround scenario in which a CEM-enabled system plans energy procurement, storage pre-charging, and load scheduling across a six-hour operational horizon. The demonstration illustrates how CEM moves the EI beyond feasibility-seeking toward intelligent, anticipatory energy governance.

The widespread idealization of road surfaces as horizontal planes can introduce significant inaccuracies into vehicle dynamics simulations, a phenomenon termed the “Flat Earth Error.” This article provides an expository guide to the use of classical differential geometry to model vehicular motion on curved surfaces. The influence of road curvature is characterized using the metric tensor, the second fundamental form, the shape operator, and the Christoffel symbols. Reproducible MATLAB scripts using an elliptic cone as a benchmark example illustrate the construction of geodesic curves and the simulation of particle dynamics on curved surfaces. The resulting geometric structures are integrated into a single-track vehicle-and-track model within a pseudospectral optimal control framework. Trajectory optimization results over a high-density mobile LiDAR profile of Darlington Raceway are used to generate a high-fidelity road-surface model. This model is used within an hp-adaptive collocation framework to investigate minimum lap time optimal control vehicular trajectories. These computations capture the non-smooth traction saturation limits of the tyres alongside position-dependent variations in gravitational forcing. Integrating differential geometry, multibody mechanics, and optimal control is essential for high-fidelity driven and autonomous vehicle-dynamics simulations. The optimized velocity and tyre slip profiles show that real-world racing track geometries induce dynamically significant three-dimensional effects. These results are particularly relevant to performance-limited simulations on highly banked track surfaces such as NASCAR ovals.

Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive TTS, but the effectiveness of preference optimization for NV generation remains poorly understood. We systematically study preference optimization for NV-capable TTS, focusing on preference signals, preference-pair construction, and DPO-based optimization objectives. We formulate an NV-aware character error rate (NV-CER) by treating NV tags as distinct output symbols and computing a weighted pinyin-based CER over both verbal and non-verbal content, enabling controllable optimization of NV realization without modifying the underlying optimization algorithm. Experiments on Emilia-NV and the augmented NV-Bench covering 18 NV types reveal how different design choices affect NV realization and lexical fidelity, and establish an effective setup using standard DPO. Objective, LLM-based, and human evaluations provide converging evidence for our findings, offering practical insights into NV-aware post-training for expressive TTS.

Industrial actor–critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited interactions which process variables each action affects, in which direction, and after what delay. Fixed industrial documents already describe part of these relations, but their open-text statements neither represent the current operating condition nor directly fit a numerical policy. This article presents LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes (LCAE), which uses a large language model before training to normalize fixed documents into a frozen action–observation–direction–delay relation basis. Recent numerical action–response history then modulates the current strength of each relation, while the evaluated action forms a state-conditioned nonlinear action-effect field in the same basis. The critic evaluates actions through this field, and the actor uses the same relation gains to generate actions, making document semantics part of maximum-entropy policy learning. Neither the LLM nor the embedding model runs online during training or deployment; the deployed policy uses only frozen semantic artifacts and visible numerical history. The method states a falsifiable hypothesis: when documented relations are correct and recent history reflects their contextual strength, this action representation should provide a more useful decision bias than raw action coordinates.

This paper investigates the stabilization of complex networks via event-triggered pinning impulsive control in the presence of actuation delays. Unlike existing event-triggered impulsive control schemes that assume instantaneous implementation, the proposed framework explicitly accounts for the delay between event detection and impulse execution. By constructing suitable Lyapunov functions and analyzing the network dynamics during the delay intervals, explicit delay-dependent sufficient conditions are derived to guarantee asymptotic stability. The obtained conditions characterize the interplay among network topology, actuation delays, impulsive control gains, and triggering parameters. In addition, a strictly positive lower bound on inter-event times is established, which excludes Zeno behavior and ensures practical implementability. A topology-based criterion for selecting pinned nodes is also developed through a spectral condition on the network Laplacian. Numerical simulations on a network of coupled Chua circuits illustrate the design procedure and verify the effectiveness of the proposed method.

Controllability of nonlinear systems has been extensively studied by using the Lie algebra methods. Although local controllability can be proved, global controllability is in general hard to obtain even for bilinear systems. Recently, a new approach is developed to study controllability of bilinear systems by checking whether the reduced rank points corresponding to the bilinear terms form hyperplanes or hypersurfaces, so that near-controllability, in the global sense, can be algebraically verified once no hypersurface exists. In this paper, we show that there is a flaw in the algorithm for checking the reduced rank hypersurface germ condition (RRHGC) that some special cases are overlooked. We thus propose a new algorithm for testing the RRHGC based on a Darboux-polynomial characterization, which can be used to deal with all cases. An example is provided to demonstrate the proposed new algorithm.