Papers

Medical image segmentation is an important task in clinical analysis. Although deep learning techniques are widely used, training at the individual pixel level ignores geometric prior information about the region being segmented. Integrating the Chan-Vese model into the loss function is a well-established remedy that accounts for the regions inside and outside the segmentation and, through its length term, for boundary regularity. However, such losses still lack an effective characterisation of local boundary geometry. We introduce the mean curvature as a natural geometric constraint and propose a Deep Active Contour and Mean Curvature (DACMC) loss function, in which a fixed convolution kernel approximates the mean curvature at negligible computational cost. The loss has a single hyper-parameter, the curvature weight $\lambda$, fixed at $10^{-3}$ for all experiments. We evaluate DACMC on three public datasets - liver computed tomography (CT), spleen magnetic resonance imaging (MRI) and dermoscopy images from the International Skin Imaging Collaboration (ISIC) - using two encoder-decoder networks as backbones and the Dice similarity coefficient (DSC), the 95th-percentile Hausdorff distance (HD95), the Jaccard similarity (JS) and the average surface distance (ASD) as metrics, against the cross-entropy, Dice, active contour and elastica losses. DACMC attains the best or second-best DSC in five of the six dataset-backbone settings; on spleen MRI it reduces HD95 to 16.28 millimetres and ASD to 1.90 millimetres, and on ISIC it reduces HD95 to 7.08 millimetres. A sensitivity study shows a broad plateau for $\lambda \leq 10^{-3}$ and degeneration only when the curvature term dominates.

Addressing the control and maneuverability of surface vehicles with dynamically changing mass distributions is still an open problem. To solve the problem, we propose an intelligent controller for the path-following problem of a surface vehicle, which is controlled through mass distribution. This means that one of the control inputs is mass-centric. Specifically, we developed a Lyapunov-based nonlinear control scheme to enable an unmanned vessel to follow a smooth path according to a line-of-sight guidance law. The control inputs consist of the thrust force for forward motion and the position of a sliding mass that shifts the system's overall mass distribution. Artificial neural networks are employed to estimate unmodeled dynamics and external disturbances. Simulation results demonstrate the effectiveness of the proposed controller in guiding the vessel along the desired path with minimal error.

Automated epileptic seizure detection from multichannel electroencephalography (EEG) benefits from dimension reduction to obtain compact, discriminative representations. We compare four signal-space dimension reduction methods, Principal Component Analysis (PCA), Dynamical Component Analysis (DyCA), Dynamic Mode Decomposition (DMD), and Average Volatility Dimensioning (AVD), for deep learning-based seizure detection on the Temple University Hospital Seizure Corpus (TUSZ v2.0.3). To enable a comparison of optimal combinations of representation and classifier, an autonomous AI-driven research framework independently optimizes architecture and hyperparameters for each representation. Measured by test ROC-AUC, the variance-based methods AVD (88.28%) and PCA (85.98%) paired with their respective optimal classifiers outperform the dynamics-based methods DMD (74.56%) and DyCA (74.85%) by over 10%, with AVD also showing the smallest validation-to-test gap. The best-performing classifier architecture differs across representations, indicating that representation and classifier should be optimized jointly. Our results highlight the importance of the input representation for EEG seizure detection and indicate the viability of autonomous AI-driven experimentation in biomedical signal processing.

Traditionally, hearing-aid speech enhancement (SE) algorithms rely on input-based feature estimation, often derived by a voice activity detector (VAD), to configure beamformers. Yet features extracted from noisy microphone signals can become unreliable in challenging acoustic scenes where users most need help. We introduce a novel paradigm in which the settings of a sound processing system are determined by evaluating characteristics of its output. To demonstrate this idea, we employ an output-based system that selects among a set of minimum power distortionless response (MPDR) beamformers. Although MPDR beamformers are typically avoided due to their sensitivity to steering errors, we show that they become effective within an output-based framework. We compare the proposed system to a conventional input-based minimum variance distortionless response (MVDR) baseline. Experimental results show that the proposed system consistently outperforms the MVDR baseline, particularly at low SNRs, in terms of SNR, ESTOI and PESQ.

Modern cellular systems employ wide bandwidths and large antenna arrays to meet high data rate requirements. The high spatial and temporal resolution for communication also enables high-accuracy positioning as an ancillary benefit. Standard convolutional neural networks (CNNs) and vision Transformers have demonstrated excellent performance in positioning by leveraging delay-angle domain channel representations. However, they still face practical challenges in complicated cellular environments with low signal-to-noise ratios and severe inter-cell interference. This paper proposes a hybrid convolutional vision Transformer (ConViT) architecture that integrates the local receptive fields of CNNs to suppress local noise and employs Transformers to capture global attention among different multipath components. Various fusion strategies for combining signals from multiple distributed base stations are also evaluated. An extended Kalman filter with sensor fusion is applied to further mitigate long tail fluctuations of model estimates. Comprehensive validation is conducted with commercial long-term-evolution signals received by a large antenna array in urban environments with non line-of-sight signals and strong inter-cell interference. ConViT achieves a distance root mean square error (RMSE) of 3.46 meters and a yaw RMSE of 2.54 degrees, significantly outperforming benchmark models, while maintaining a lower parameter count and reduced computational complexity. Finally, a correspondence analysis between delay-angle power distributions and Transformer attention weights demonstrates the interpretability of the model.

Thanks to inter-element interconnections and flexible element arrangements, the beyond diagonal reconfigurable intelligent surface (BD-RIS) breaks through the limitation of traditional RIS to achieve enhanced performance and enlarged coverage. However, existing BD-RIS research assumes that BD-RIS is always turned ON to assist transmission, while, in some scenarios where the transmitter-receiver direct link exists and remains strong, the performance gains of BD-RIS may not justify its manipulation complexity. In order to smartly use BD-RIS, a novel adaptive transmission scheme is proposed in this paper. The proposed scheme first defines two working states of the BD-RIS, namely ON and OFF. Based on these two states, we design a new beam training protocol that enables BD-RIS to intelligently switch its working state according to real-time channel conditions. Furthermore, we construct a decision threshold as the decision basis for state switching to ensure the efficiency and reliability of protocol execution. Simulation results show that, without always turning ON the BD-RIS and performing sophisticated wave manipulation, the proposed protocol can guarantee successful transmission regardless of whether there is a strong transmitter-receiver link or not.

This paper proposes an affine frequency division multiplexing (AFDM)-aided faster-than-Nyquist (FTN) waveform, termed AFDM-FTN, to enhance spectral efficiency (SE) in high-mobility communication scenarios. We first derive the AFDM-FTN input-output relationship and analyze the FTN-induced interference pattern in AFDM-FTN. To address the channel estimation challenges, a low-complexity channel estimator based on the basis expansion model (BEM) is developed. By exploiting the intrinsic characteristics of the AFDM channel matrix and the FTN coefficient matrix, a multi-layer message passing (MLMP) algorithm is proposed that leverages the sparsity of the time-domain (TD) channel and the FTN coefficient matrix, where belief messages are iteratively propagated across the TD channel, FTN, and transform layers. Building upon the BEM-assisted channel estimation and MLMP, a low-complexity joint channel estimation and data detection scheme (BEM-MLMP-JCED) is further developed to iteratively refine channel estimation with the aid of transmitted data. Finally, the channel estimation lower bound, the mean square error (MSE) performance of the BEM-MLMP-JCED, and the computational complexity are analyzed. Simulation results demonstrate that the proposed AFDM-FTN system with BEM-MLMP-JCED achieves comparable BER to conventional AFDM while providing enhanced SE and reduced complexity compared to benchmark receivers.

The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones. Under an explicit generative model this goodness is the sufficient statistic of a likelihood-ratio test, and the pairwise form of the objective admits a gauge: a layer can lower its loss by inflating the scale of its weights rather than by separating the two populations. The analysis prescribes the repair - a whitened, scale-invariant goodness trained online within each layer - which we evaluate as a training procedure. Across three corpora, three depths and a fourfold range of layer width (13 seeds per cell), it raises linear-probe accuracy over the standard pairwise objective in every measured cell - by 4 to 7 points on eight of nine corpus-depth combinations - and closes 16-61% of the gap to end-to-end backpropagation. A control isolates the mechanism: Hinton's fixed-threshold loss also bounds the runaway, to a factor of 1.4 against 133, yet tracks the unmodified baseline - invariance to the gauge, not a bound on it, is what pays. Against the strongest published alternative - a sparse, top-k goodness - the derived objective is statistically indistinguishable on two corpora of three, yet only it removes the runaway: sparsity and gauge-invariance are independent axes, and the published variant recovers accuracy while leaving the pathology in place. We state the boundaries we measured, and every prediction was recorded before its experiment with the refutations reported.

Zero-shot dialog TTS benefits from flow-matching, but minute-scale generation on dense mel-spectrograms causes severe memory bottlenecks, often forcing unnatural chunked synthesis. We propose ZipL-Dialog, which shifts conditional flow-matching into a 4x time-compressed (25 Hz) latent space. To preserve acoustic fidelity under compression, we employ a deterministic mel autoencoder with auxiliary mel-domain supervision and optimize the ZipFormer's hierarchical downsampling schedule. Experiments show that ZipL-Dialog reduces maximum peak GPU memory by 11.22x and accelerates inference by 2.23x over the baseline, substantially lowering the memory footprint of single-pass multi-minute dialog synthesis while maintaining perceptual naturalness.

The direction-of-arrival (DOA) estimation problem using one-bit quantized magnitude-only measurements is studied, where magnitude-only measurements offer robustness against phase errors, thereby avoiding the need for array calibration, while one-bit quantization significantly reduces hardware cost and system complexity. As their direct combination results in meaningless constant measurements, we formulate a sign-consistency optimization problem using a smooth logistic surrogate with ell_2,1-norm regularization to promote joint sparsity. To solve this problem, a proximal-gradient algorithm is developed with guaranteed convergence to a critical point. Numerical results demonstrate that the proposed method achieves accuracy comparable to coherent one-bit baselines under ideal conditions, while maintaining robust performance under severe phase errors that substantially impair coherent methods.

This paper develops a scenario-free uncertainty-aware bilevel optimization framework for coordinated electric vehicle (EV) charging and reactive power support in distribution networks using distribution locational marginal prices (DLMPs). The upper-level EV aggregator jointly schedules active and reactive charging power to minimize charging costs, while the lower-level energy management system performs network-constrained economic dispatch and determines DLMPs subject to feeder and voltage constraints. To capture uncertainties in load demand and photovoltaic (PV) generation, a compact robust counterpart (RC) reformulation is developed that avoids the computational burden of large-scale stochastic programming and conventional robust optimization. Unlike existing robust counterpart methods that primarily assume Gaussian uncertainties, the proposed approach derives a deterministic reformulation for net-demand uncertainty modeled by a normal-minus-beta distribution, providing a more realistic representation of asymmetric load and renewable variability. An exactness lemma preserves the economic interpretation of DLMPs after KKT reformulation and Big-M linearization. EV chargers also provide reactive power support through non-unity power factor operation to improve voltage regulation. Simulation results on the IEEE 33-bus distribution system demonstrate improved voltage security, effective uncertainty-aware EV coordination, and significantly lower computational complexity than conventional stochastic and robust optimization approaches.

We classify the local maximizers of the entrywise fourth-power objective \[ Q\longmapsto \lVert Q\rVert_4^4 =\sum_{i,j=1}^r q_{ij}^4 \] over the real orthogonal group $\mathcal O(r)$. We prove that the signed permutation matrices are the only local maximizers, and hence the only global maximizers, in every dimension. More strongly, every other stationary point has an explicit rank-two tangent direction with strictly positive second variation. The proof is based on a maximum-entry pivot for the orthostochastic matrix $Q^{\circ2}$: the associated full Riemannian Hessian can be evaluated exactly and is positive at a largest nonunit squared entry. The argument is self-contained and handles zeros, repeated magnitudes, reducible support, and Hadamard-type stationary points.

Although vast amounts of data, such as audio signal spectra, are naturally represented using complex numbers, conventional machine learning methods often simplify complex-domain problems by employing frameworks designed for real-valued variables. While this simplification offers computational benefits, it discards structural information regarding the inherent relationship between amplitude and phase. In this paper, we propose a novel Boltzmann machine (BM), named PolarBM, capable of naturally handling complex-valued variables in the polar coordinate (i.e., an amplitude-phase representation). PolarBM defines a probability density function for complex variables in which the phase explicitly depends on the amplitude, thereby capturing the physically important relationships of complex-valued signals. Furthermore, to process audio signals in accordance with human auditory perception, we propose LogPolarBM, which models amplitude on a logarithmic scale. This extension yields a flexible conditional probability density function, a power-weighted noncentral complex Gaussian (PW-NCCG) distribution, whose marginal amplitude distribution encompasses the Rice, Nakagami, and noncentral chi distributions as special cases. For practical applications, we also introduce the restricted variants of these proposed models: PolarRBM and LogPolarRBM. Experimental results demonstrate that by explicitly modeling the dependency between amplitude and phase, the proposed RBMs achieve superior modeling accuracy compared to conventional models, including deep neural networks. Although our experiments focus on audio signals, the utility of the proposed BMs is not limited to audio applications; their potential extends widely across various fields of science and engineering that involve complex-valued data, such as wireless communications and quantum mechanics.

Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability. Recent approaches based on multimodal large language models (MLLMs) introduce textual reasoning for quality prediction, yet their judgments rely heavily on semantically biased internal representations, making them insensitive to low-level perceptual degradations. We propose IQA-T1, a tool-based visual evidence reasoning framework that augments MLLM reasoning with explicit perceptual observations. During inference, the model autonomously invokes specialized analysis tools to generate structured visual evidence, such as noise residual maps, gradient statistics, and frequency spectra, which are progressively integrated into the reasoning process. To support this paradigm, we construct Q-Tool, a dataset containing 11k multimodal reasoning chains grounded in tool-generated evidence. Extensive experiments on seven IQA benchmarks show that IQA-T1 achieves the best overall performance across datasets while producing interpretable and evidence-grounded quality assessments. Code and dataset are available at https://github.com/zibuyu-02/IQA-T1.

This paper studies learning-based MPC for constrained stabilization of discrete-time linear systems with unknown system parameters and additive bounded disturbances. We develop a tractable homothetic-tube MPC scheme in which a high-probability parameter confidence set is generated from non-asymptotic regularized least-squares estimation, rather than assumed a priori. The resulting uncertainty set is embedded into robust tube propagation and constraint tightening, yielding a convex formulation with linear and second-order-cone constraints. We prove high-probability recursive feasibility, robust constraint satisfaction, and input-to-state stability, together with explicit non-asymptotic state bounds. A numerical example illustrates the effectiveness and theoretical guarantees.

This paper jointly optimizes the base-station (BS) continuous aperture array (CAPA) dimensions and beamforming functions to maximize energy efficiency (EE) of the downlink multiuser multi-CAPA system, where both the BS and the users are equipped with CAPAs. Since the beamforming functions are continuous current distribution over the BS CAPA, the resulting EE maximization problem is a nontrivial functional optimization problem that couples aperture sizing and beamforming design. To address this challenge, we propose a cascaded network architecture consisting of a graph neural network (GNN) and a functional-gradient based implicit neural representation (FGB-INR) to learn the BS CAPA dimensions and beamforming functions, respectively. Both networks exploit the permutation equivariance of the optimal optimization policy, and the update equations of FGB-INR are designed according to the functional-gradient structure of the EE objective. Simulation results show that the proposed method approaches the EE of the numerical method while substantially reducing inference latency. They also demonstrates that the functional-gradient structure in FGB-INR improves EE while reducing sample complexity and training time.

Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-only evaluation hides a key limitation: these models fail to encode negated sound concepts, mapping affirmative and negated captions to nearly identical representations. To expose this blind spot, we introduce NegEval-Audio, a framework that converts existing datasets into two negation-aware tasks, Retrieval-Neg and Multiple-Choice Negation (MCQ-Neg), to probe whether models distinguish present from absent events. On AudioCaps and Clotho, performance degrades sharply under negation, with negation-type MCQ accuracy falling far below chance, and the failure persists even for a recent multimodal LLM-based embedding model. While a training-free steering method improves MCQ-Neg, it yields marginal gains for Retrieval-Neg. This indicates that affirmation bias is a fundamental flaw in the representation geometry, necessitating explicit negation-aware training objectives.

Quadrotors flying in tight formations are severely affected by turbulent aerodynamic interactions, such as downwash, that can cause catastrophic collisions if left unmodeled. To compensate for these effects, we propose a physics-informed residual dynamics learning framework that captures complex aerodynamic interactions while ensuring the joint multi-quadrotor system remains differentially flat. We leverage this preserved flatness to design a computationally efficient feedback linearization controller that is easily tunable with linear control techniques and cancels aerodynamic disturbances via feedforward compensation. Hardware experiments demonstrate our framework reduces average tracking errors by 31% compared to nominal baselines. Crucially, our lightweight approach matches the tracking performance of state-of-the-art nonlinear model predictive control (NMPC) while requiring an order of magnitude less computation. We are the first to show that stable, tight formation flight can be achieved with under 30 seconds of training data and a 5ms loop rate, unlocking high-fidelity aerodynamic compensation for compute-constrained flight stacks. The video of our physical experiments can be found at https://www.youtube.com/watch?v=uF26IkRFQMk

Radar sensing is increasingly used in mobile systems because it operates reliably under poor lighting, adverse weather, and privacy-sensitive settings where cameras and LiDAR often fail. However, most existing radar SLAM systems estimate motion through scan matching on discretized radar heatmaps, which breaks geometric continuity and fails to capture key radar sensing properties, often leading to unstable pose estimation and degraded mapping in regenerate or dynamically changing environments. We present DiffRadar, a real-time radar SLAM system that models radar observations as a differentiable, physics-aware Gaussian field rather than discrete scans. DiffRadar represents the scene as anisotropic Gaussian primitives and renders radar measurements in range-azimuth and Doppler-azimuth spaces through a differentiable radar forward model, enabling joint optimization of robot pose and scene structure directly from radar measurements. We implement DiffRadar on commodity FMCW radar hardware and evaluate it on both the public Radarize benchmark and a controlled stress-test suite that targets common radar SLAM failure modes, including corridor degeneracy, motion regime transitions, dynamic clutter, and long-horizon loop closures. DiffRadar achieves substantial reductions in trajectory error on the benchmark, with especially large gains under feature-poor corridor motion, while more than doubling map consistency and maintaining real-time performance at 70 FPS. These results show that modeling radar observations directly in the signal domain enables substantially more robust and consistent radar-only SLAM for mobile platforms.

Machine-learned surrogates for the AC power flow (ACPF) problem amortize the cost of repeated solves on a fixed network, but lose one to two orders of magnitude of accuracy when a line outage changes the topology. This degradation is an operator shift. The altered admittance matrix changes the input-to-output map, so identical inputs yield a different output distribution. Existing methods correct this with target-topology data and per-topology gradient steps. We ask whether the correction can instead be made statistical and gradient-free. We propose In-Context Whitening (ICW), which trains an ACPF surrogate in an output space whitened by the base topology's first two moments, and adapts it to an unseen N-1 or N-2 topology by re-estimating that whitening from a few hundred solved cases on the new topology. This adaptation is gradient-free, weight-free, and architecture-agnostic. We prove that among affine whiteners the unique choice that preserves the coordinate-wise semantics of the physical output vector is ZCA whitening, so within efficient invertible corrections, two moments are sufficient. Across the IEEE 30-, 118-, and 300-bus systems under N-1 and N-2 contingencies, ICW reduces overall error by 6$\times$ to 28$\times$ over frozen surrogates (up to 54$\times$ per-quantity under N-2) and cuts worst-bus power-balance mismatch by up to 30$\times$, with consistent gains across three backbones. At deployment scale it matches or beats gradient-based adaptation in accuracy while adapting 21$\times$ to 34$\times$ faster, with a cost that parallelizes on commodity CPU cores rather than requiring one GPU per contingency.

Current analog complexity theory, built on the General-Purpose Analog Computer (GPAC) model and polynomial ODEs, allows unbounded state variables – an assumption that is physically unrealistic for chemical reaction networks and other laboratory-scale analog computers. We develop a bounded analog complexity theory in which all state variables remain in compact intervals and physical time (wall-clock time) is the only diverging resource. Our main technical contribution is bounded surrogate compilation, a compilation framework that transforms unbounded polynomial ODE systems into bounded ones while preserving computational limits and time-to-precision guarantees. We prove that if a system is compiled into a bounded system through our algorithm, the wall-clock time of the compiled system is polynomial in the arc length and physical time of the original system. We exhibit concrete constructions demonstrating fine-grained bounded time complexity – a tunable polynomial-degree family, a Lambert-$W$-based system achieving $\Theta(r\log r)$ time-to-precision (where $r$ is the desired precision parameter, in nats: $|x(t)-\alpha|<e^{-r}$), and an iterated-logarithm tower realizing arbitrarily high complexity classes – all for the task of computing the constant 1. We show that bounded GPACs are closed under exponentiation ($\alpha^\beta$) with time complexity equal to the harder input, and that the full GPAC-to-CRN compilation pipeline preserves time complexity class via a low-pass filter analysis of readout modules.

Brain-computer interfaces (BCIs) decode neural activity into commands, yet most existing systems rely on fixed-window decoding that may result in redundant observation or unreliable predictions due to insufficient evidence. Adaptive temporal decision-making (ATDM) addresses this accuracy-time trade-off by progressively accumulating EEG evidence and deciding when to stop. However, existing EEG encoders are mainly designed for fixed-window decoding and may not provide reliable state representations under variable observation lengths. In addition, current ATDM-oriented encoders are typically tailored to specific EEG paradigms, limiting their applicability across different BCI tasks. To address these limitations, we propose ProtoTrigger, a two-stage prototype learning-based EEG state encoder for ATDM. ProtoTrigger uses prototype matching to extract stable local EEG embeddings and prototype-based attention to aggregate decision-relevant temporal evidence during progressive observation. Offline evaluations across three EEG paradigms demonstrated state-of-the-art accuracy-time trade-offs and strong generalizability across different EEG paradigms. An online human-in-the-loop augmented reality-based BCI experiment further demonstrated its real-time feasibility. These results suggest that ProtoTrigger provides a general EEG state encoding framework for efficient ATDM-based BCI systems.

Safety verification is a fundamental problem in control theory. Barrier certificates (BCs) provide a powerful formal mechanism, yet deriving BCs is computationally intensive. This paper introduces a generative framework that leverages large language models (LLMs) to synthesize BCs through reasoning. Based on the classical Sum-of-Squares (SOS) approach, we train a domain-specific LLM capable of generating high-quality BC candidates for nonlinear systems. Then, the LLM-generated BCs transform the intractable Bilinear Matrix Inequality (BMI) solving problems into convex Linear Matrix Inequality (LMI) feasibility test, significantly improving efficiency while preserving correctness. Experimental results show that our generative method achieves several orders of magnitude speedup over traditional numerical BC approaches and, perhaps surprisingly, surpasses the state-of-the-art dedicated neural BC model. These findings mark a substantive step toward integrating generative AI with formal safety verification for dynamical systems.

Vision-language models (VLMs) have achieved strong performance on general remote sensing tasks. However, their capability for rare scenes remains insufficiently understood, because existing benchmarks are dominated by common urban and rural imagery. To address this gap, we present RRS-10K, a benchmark for rare remote sensing image interpretation. RRS-10K contains 10,738 military-related remote sensing images and corresponding multiple format question-answer pairs for comprehensive evaluation. All of the images are collected from first-hand sources and organized into three capability dimensions, six sub-dimensions, and 20 leaf tasks, covering perception, reasoning, and robustness. To improve the quality of multiple-choice questions, we introduce a similarity-based distractor filtering strategy (SDFS) during benchmark construction. We further evaluate 52 representative models and show that current VLMs achieve only moderate zero-shot performance on rare remote sensing image interpretation, with clear weaknesses in visual grounding, referring segmentation, and complex semantic reasoning tasks. RRS-10K enables systematic analysis of failure modes in long-tail remote sensing interpretation and provides guidance for developing more reliable remote sensing VLMs.

Trajectory datasets used in ADAS evaluation are heavily biased toward routine driving; genuine vehicle-to-vehicle conflict events are rare, and the rarer the event, the higher the cost when an ADAS system fails to handle it. Existing generative approaches address this imbalance by conditioning on scene-level properties - spatial goals, agent structure, or natural-language adversarial objectives - but none can accept a target Time-to-Collision (TTC) value as input and be held to producing it within a measurable error. This paper introduces SevDiff, a severity-conditioned denoising diffusion probabilistic model (DDPM) that accepts a requested minimum TTC value as a scalar conditioning signal and generates paired vehicle interaction trajectories whose realized conflict severity matches the request, evaluated through a hit-rate metric. Trained on 468 interaction windows extracted from the UTE SQM-W-1 expressway weaving-section dataset (1,041 vehicles, 822,691 observations after smoothing), SevDiff achieves 100% hit-rate within +/-0.5 s for TTC targets of 0.5-1.5 s and 97-99% at 2.0-2.5 s, with graceful degradation to 39% at TTC = 5.0 s. Generated kinematic features are physically plausible, with a maximum out-of-range rate of 4.7% across 12 features and no negative speed or gap values in more than 96.5% of samples. The hit-rate degradation pattern is physically interpretable as the strength of the conditioning signal relative to the training prior, making it a precision characterization of the generator rather than a pass/fail result.

Continuous EEG monitoring for epilepsy is constrained by the limited power and memory budgets of wearable and implantable devices. Deep neural networks can detect seizures with high accuracy, but their computational cost and model size make them difficult to deploy on such platforms. In this work we use a single 1D CNN seizure detector on the CHB-MIT scalp EEG dataset as a common baseline, and then investigate three brain-inspired efficiency strategies: (i) conversion of the CNN into a spiking neural network (SNN) via parameter transfer, (ii) EEG channel pruning combined with 2:4 structured weight sparsity, and (iii) INT8 quantization using FX- and ONNX-based workflows, including quantization-aware training and operator fusion. The quantized CNN variants reduce stored model size from 1.63 MB to 0.44 MB, lower estimated energy per inference by up to 64%, and achieve as much as 2.8 times speedup in CPU latency while preserving, and in one case slightly improving, AUC. The pruned CNN halves the number of input channels and non-zero weights with only a modest accuracy drop, and the SNN conversion provides a spiking implementation with sparse temporal activity. Together, these experiments characterize three complementary efficiency directions for seizure detection.

AI data centers are emerging as a dominant new load class with their power dynamics fundamentally from conventional industrial loads. Inside a training job, the bulk-synchronous-parallel algorithm moves each node through compute, sync, and checkpoint steps, which swings power between full load and near idle within seconds. Across the whole facility, jobs arrive, take blocks of nodes for hours to days, then leave, so the number of busy nodes changes daily, weekly, and yearly. This slower shift drives facility-wide swings and the peak demand that sets the size of the grid link. A model that looks only at within-job behavior, and treats the facility as a fixed set of busy nodes, smooths out these swings and misses the true peak-to-average ratio. This paper develops a hierarchical semi-Markov Data-Center (HSM-DC) load model that couples two layers across two timescales. A job-scheduling layer creates jobs through a non-homogeneous compound-Poisson process shaped by daily, weekly, and seasonal patterns, gives each job a heavy-tailed node count and length, and places jobs on a fixed pool of nodes on a first-come basis. A within-job layer moves each busy node through a five-state semi-Markov chain for the BSP steps, with state-based Ornstein-Uhlenbeck noise. Facility power comes from this changing node count and the per-node power, set to match measured node data and the facility's straight-line power-versus-load curve. Configured to the reference facility at the same scale, the model matches mean power, its spread, and the peak-to-average ratio across load levels, with fit scores of 0.9997, 0.92, and 0.82. It also matches the share of queued jobs to within one point at high load. Facility-wide swings and peak demand come from how jobs arrive and get scheduled, so grid planning must model that process, not just scale up a single node's power curve.

We prove new necessary and sufficient conditions for uniform asymptotic stability under arbitrary switching of two-dimensional switched homogeneous systems with a finite number of subsystems using a worst-case switching analysis. The novelty of our approach is in its explicit nature, which allows us to then study in detail the codimension-one bifurcations of stability of the origin in switched linear systems and further conclude new local and global stability results for certain classes of nonlinear switched systems. In particular, we formulate an analogue of Lyapunov's indirect method for $\mathcal{C}^{1}$ switched nonlinear systems and derive a new method for determining the existence of a bounded basin of attraction for a class of switched nonlinear systems.

Many recently proposed Calderbank-Shor-Steane (CSS) quantum low-density parity-check (QLDPC) codes have sparse decoding graphs, enabling syndrome-based belief propagation (BP) decoding at low complexity. Their construction, however, often results in properties that impair BP performance, such as short cycles and degeneracy. In this work, we propose a general framework for introducing auxiliary variable nodes (AVNs) and auxiliary check nodes (ACNs) into the decoding graph of CSS codes, compatible with the standard stabilizer measurement framework. This provides an additional degree of freedom in the design of the decoding graph itself and can be used to tackle the aforementioned shortcomings. We show that recently proposed techniques, 4-cycle removal and subcode ensemble decoding, can be interpreted as instances of this framework. For 4-cycle removal, we find that the gains depend strongly on the BP iteration count and check-node message scaling. Building on this framework, we further propose a graph-derived subcode ensemble decoder and demonstrate under circuit-level noise that it substantially reduces the per-round logical error rate compared with BP on the corresponding 4-cycle-free decoding graph.

In this article we present a method to generate safe sets for linear discrete-time systems subject to non-convex constraints that can be represented as a union of polytopes. It is then shown how a reference governor can be implemented for safe reference tracking tasks. A theoretical analysis of the safe set is presented and properties of the reference governor scheme are derived. The guarantees include safety at any time as well as finite-time convergence of the applied reference command to any strictly admissible reference command. For the proposed reference governor, online computational overhead is low. Moreover, it is shown that for specific instances of the complex constraint sets, the safe set can be computed efficiently. Extensive simulation results demonstrating the applicability of the method and online/offline computation times are reported.