Papers

This paper addresses state of charge (SOC) estimation for lithium iron phosphate (LFP) batteries, where the relatively flat open-circuit voltage (OCV-SOC) characteristic reduces observability. A residual bias compensation dual extended Kalman filter (RBC-DEKF) is developed. Unlike conventional bias compensation methods that treat the bias as an augmented state within a single filter, the proposed dual-filter structure decouples residual bias estimation from electrochemical state estimation. One EKF estimates the system states of a control-oriented parameter-grouped single particle model with thermal effects, while the other EKF estimates a residual bias that continuously corrects the voltage observation equation, thereby refining the model-predicted voltage in real time. Unlike bias-augmented single-filter schemes that enlarge the covariance coupling, the decoupled bias estimator refines the voltage observation without perturbing electrochemical state dynamics. Validation is conducted on an LFP cell from a public dataset under three representative operating conditions: US06 at 0 degC, DST at 25 degC, and FUDS at 50 degC. Compared with a conventional EKF using the same model and identical state filter settings, the proposed method reduces the average SOC RMSE from 3.75% to 0.20% and the voltage RMSE between the filtered model voltage and the measured voltage from 32.8 mV to 0.8 mV. The improvement is most evident in the mid-SOC range where the OCV-SOC curve is flat, confirming that residual bias compensation significantly enhances accuracy for model-based SOC estimation of LFP batteries across a wide temperature range.

We introduce Region-Adaptive Learned Hierarchical Encoding (RALHE) for 3D Gaussian Splatting (3DGS) data. While 3DGS has recently become popular for novel view synthesis, the size of trained models limits its deployment in bandwidth-constrained applications such as volumetric media streaming. To address this, we propose a learned hierarchical latent representation that builds upon the principles of "overfitted" learned image compression (e.g., Cool-Chic and C3) to efficiently encode 3DGS attributes. Unlike images, 3DGS data have irregular spatial distributions of Gaussians (geometry) and consist of multiple attributes (signals) defined on the irregular geometry. Our codec is designed to account for these differences between images and 3DGS. Specifically, we leverage the octree structure of the voxelized 3DGS geometry to obtain a hierarchical multi-resolution representation. Our approach overfits latents to each Gaussian attribute under a global rate constraint. These latents are decoded independently through a lightweight decoder network. To estimate the bitrate during training, we employ an autoregressive probability model that leverages octree-derived contexts from the 3D point structure. The multi-resolution latents, decoder, and autoregressive entropy coding networks are jointly optimized for each Gaussian attribute. Experiments demonstrate that the proposed RALHE compression framework achieves a rendering PSNR gain of up to 2dB at low bitrates (less than 1 MB) compared to the baseline 3DGS compression methods.

We present a safety filter to guarantee constraint satisfaction on the rotation angle in the presence of disturbances. An LMI-based framework simultaneously synthesizes a maximal ellipsoidal robust controlled invariant (RCI) set and its associated state-feedback backup control law by solving a single convex semidefinite program, subject to state and input constraints. To extend this framework to nonlinear quaternion attitude dynamics, we derive exact closed-form sector bounds on the quaternion kinematic nonlinearity and analytically embed them into the LMI via the S-procedure. A smooth mixing law intervenes only as the state approaches the RCI boundary, preserving nominal performance during safe operation. This work is motivated by hierarchical aerial control architectures, where outer-loop commands can generate attitude references that drive the inner-loop attitude state unstable, a cascade failure mode that endangers the entire system. Quadrotor simulations with hierarchical controller structures under bounded disturbances confirm constraint satisfaction across three scenarios specifically designed to stress-test the cascade failure mode: set-point tracking with small initial errors, set-point tracking with large initial position errors that saturate the outer loop, and high-frequency circular trajectory following that persistently excites the inner-loop attitude dynamics.

Radar-based human activity recognition (HAR) is attractive for unobtrusive and privacy-preserving monitoring, yet many CNN/RNN solutions remain too heavy for edge deployment, and even lightweight ViT/SSM variants often exceed practical compute and memory budgets. We introduce Neural-HAR, a dimension-gated CNN accelerator tailored for real-time radar HAR on resource-constrained platforms. At its core is GateCNN, a parameter-efficient Doppler-temporal network that (i) embeds Doppler vectors to emphasize frequency evolution over time and (ii) applies dual-path gated convolutions that modulate Doppler-aware content features with temporal gates, complemented by a residual path for stable training. On the University of Glasgow UoG2020 continuous radar dataset, GateCNN attains 86.4% accuracy with only 2.7k parameters and 0.28M FLOPs per inference, comparable to CNN-BiGRU at a fraction of the complexity. Our FPGA prototype on Xilinx Zynq-7000 Z-7007S reaches 107.5 $\mu$s latency and 15 mW dynamic power using LUT-based ROM and distributed RAM only (zero DSP/BRAM), demonstrating real-time, energy-efficient edge inference. Code and HLS conversion scripts are available at https://github.com/lab-emi/AIRHAR.

Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions in the remote sensing domain is particularly challenging due to the prevalence of small, densely distributed objects and complex backgrounds. This paper introduces a new learning paradigm, Weakly Referring Expression Learning (WREL) for RRSIS, which leverages abundant class names as weakly referring expressions together with a small set of accurate ones to enable efficient training under limited annotation conditions. Furthermore, we provide a theoretical analysis showing that mixed-referring training yields a provable upper bound on the performance gap relative to training with fully annotated referring expressions, thereby establishing the validity of this new setting. We also propose LRB-WREL, which integrates a Learnable Reference Bank (LRB) to refine weakly referring expressions through sample-specific prompt embeddings that enrich coarse class-name inputs. Combined with a teacher-student optimization framework using dynamically scheduled EMA updates, LRB-WREL stabilizes training and enhances cross-modal generalization under noisy weakly referring supervision. Extensive experiments on our newly constructed benchmark with varying weakly referring data ratios validate both the theoretical insights and the practical effectiveness of WREL and LRB-WREL, demonstrating that they can approach or even surpass models trained with fully annotated referring expressions.

Radio frequency (RF) fingerprinting techniques provide a promising supplement to cryptography-based approaches but rely on dedicated equipment to capture in-phase and quadrature (IQ) samples, hindering their wide adoption. Recent advances advocate easily obtainable channel state information (CSI) by commercial WiFi devices for lightweight RF fingerprinting, while falling short in addressing the challenges of coarse granularity of CSI measurements in an open-world setting. In this paper, we propose CSI2Q, a novel CSI fingerprinting system that achieves comparable performance to IQ-based approaches. Instead of extracting fingerprints directly from raw CSI measurements, CSI2Q first transforms frequency-domain CSI measurements into time-domain signals that share the same feature space with IQ samples. Then, we employ a deep auxiliary learning strategy to transfer useful knowledge from an IQ fingerprinting model to the CSI counterpart. Finally, the trained CSI model is combined with an OpenMax function to estimate the likelihood of unknown ones. We evaluate CSI2Q on one synthetic CSI dataset involving 85 devices and two real CSI datasets, including 10 and 25 WiFi routers, respectively. Our system achieves accuracy increases of at least 16% on the synthetic CSI dataset, 20% on the in-lab CSI dataset, and 17% on the in-the-wild CSI dataset.

We introduce the Atlas Urban Index (AUI), a metric for measuring urban development computed using Sentinel-2 \citep{spoto2012sentinel2} satellite imagery. Existing approaches, such as the Normalized Difference Built-up Index (NDBI), often struggle to accurately capture urban development due to factors like atmospheric noise, seasonal variation, and cloud cover. These limitations hinder large-scale monitoring of human development and urbanization. To address these challenges, we propose an approach that leverages Vision-Language Models (VLMs) to provide a development score for regions. Specifically, we collect a time series of Sentinel-2 images for each region. Then, we further process the images within fixed time windows to get an image with minimal cloud cover, which serves as the representative image for that time window. To ensure consistent scoring, we adopt two strategies: (i) providing the VLM with a curated set of reference images representing different levels of urbanization, and (ii) supplying the most recent past image to both anchor temporal consistency and mitigate cloud-related noise in the current image. Together, these components enable AUI to overcome the challenges of traditional urbanization indices and produce more reliable and stable development scores. Our qualitative experiments on Bangalore suggest that AUI outperforms standard indices such as NDBI.

Accurate Direction-of-Arrival (DOA) estimation in reverberant environments remains a fundamental challenge for spatial audio applications. While deep learning methods have shown strong performance in such conditions, they typically lack a mechanism to assess the reliability of their predictions - an essential feature for real-world deployment. In this work, we present the SRP-PHAT-NET, a deep neural network framework that leverages SRP-PHAT directional maps as spatial features and introduces a built-in reliability estimation. To enable meaningful reliability scoring, the model is trained using Gaussian-weighted labels centered around the true direction. We systematically analyze the influence of label smoothing on accuracy and reliability, demonstrating that the choice of Gaussian kernel width can be tuned to application-specific requirements. Experimental results show that selectively using high-confidence predictions yields significantly improved localization accuracy, highlighting the practical benefits of integrating reliability into deep learning-based DOA estimation.

This paper presents an approximate signed multiplier architecture that incorporates a sign-focused compressor, specifically designed for edge detection applications in machine learning and signal processing. The multiplier incorporates two types of sign-focused compressors: A + B + C + 1 and A + B + C + D + 1. Both exact and approximate compressor designs are utilized, with a focus on efficiently handling constant value "1" and negative partial products, which frequently appear in the partial product matrices of signed multipliers. To further enhance efficiency, the lower N - 1 columns of the partial product matrix are truncated, followed by an error compensation mechanism. Experimental results show that the proposed 8-bit approximate multiplier achieves a 29.21% reduction in power delay product (PDP) and a 14.39% reduction in power compared to the best of existing multipliers. The proposed multiplier is integrated into a custom convolution layer and performs edge detection, demonstrating its practical utility in real-world applications.

Time-varying meshes, characterized by dynamic connectivity and varying vertex counts, hold significant promise for applications such as augmented reality. However, their practical utilization remains challenging due to the substantial data volume required for high-fidelity representation. While various compression methods attempt to leverage temporal redundancy between consecutive mesh frames, most struggle with topological inconsistency and motion-induced artifacts. To address these issues, we propose Time-Varying Mesh Compression (TVMC), a novel framework built on multi-stage coarse-to-fine anchor mesh generation for inter-frame prediction. Specifically, the anchor mesh is progressively constructed in three stages: initial, coarse, and fine. The initial anchor mesh is obtained through fast topology alignment to exploit temporal coherence. A Kalman filter-based motion estimation module then generates a coarse anchor mesh by accurately compensating inter-frame motions. Subsequently, a Quadric Error Metric-based refinement step optimizes vertex positions to form a fine anchor mesh with improved geometric fidelity. Based on the refined anchor mesh, the inter-frame motions relative to the reference base mesh are encoded, while the residual displacements between the subdivided fine anchor mesh and the input mesh are adaptively quantized and compressed. This hierarchical strategy preserves consistent connectivity and high-quality surface approximation, while achieving an efficient and compact representation of dynamic geometry. Extensive experiments on standard MPEG dynamic mesh sequences demonstrate that TVMC achieves state-of-the-art compression performance. Compared to the latest V-DMC standard, it delivers a significant BD-rate gain of 10.2% ~ 16.9%, while preserving high reconstruction quality. The code is available at https://github.com/H-Huang774/TVMC.

Speech enhancement is a fundamental challenge in signal processing, particularly when robustness is required across diverse acoustic conditions and microphone setups. Deep learning methods have been successful for speech enhancement, but often assume fixed array geometries, limiting their use in mobile, embedded, and wearable devices. Existing array-agnostic approaches typically rely on either raw microphone signals or beamformer outputs, but both have drawbacks under changing geometries. We introduce HyBeam, a hybrid framework that uses raw microphone signals at low frequencies and beamformer signals at higher frequencies, exploiting their complementary strengths while remaining highly array-agnostic. Simulations across diverse rooms and wearable array configurations demonstrate that HyBeam consistently surpasses microphone-only and beamformer-only baselines in PESQ, STOI, and SI-SDR. A bandwise analysis shows that the hybrid approach leverages beamformer directivity at high frequencies and microphone cues at low frequencies, outperforming either method alone across all bands.

Reconfigurable Intelligent Surface (RIS) technology has emerged as a key enabler for future wireless communications. However, its potential is constrained by the difficulty of acquiring accurate user-to-RIS channel state information (CSI), due to the cascaded channel structure and the high pilot overhead of non-parametric methods. Unlike a passive RIS, where the reflected signal suffers from multiplicative path loss, an active RIS amplifies the signal, improving its practicality in real deployments. In this letter, we propose a parametric channel estimation method tailored for active RISs. The proposed approach integrates an active RIS model with an adaptive Maximum Likelihood Estimator (MLE) to recover the main channel parameters using a minimal number of pilots. To further enhance performance, an adaptive active RIS configuration strategy is employed, which refines the beam direction based on an initial user location estimate. Moreover, an orthogonal angle-pair codebook is used instead of the conventional Discrete Fourier Transform (DFT) codebook, significantly reducing the codebook size and ensuring reliable operation for both far-field and near-field users. Extensive simulations demonstrate that the proposed method achieves near-optimal performance with very few pilots compared to non-parametric approaches. Its performance is also benchmarked against that of a traditional passive RIS under the same total power budget to ensure fairness. Results show that active RIS yields higher spectral efficiency (SE) by eliminating the multiplicative fading inherent in passive RISs and allocating more resources to data transmission

Large language models (LLMs) have recently advanced auditory speech recognition (ASR), visual speech recognition (VSR), and audio-visual speech recognition (AVSR). However, understanding of their internal dynamics under fine-tuning remains limited. In natural language processing, recent work has revealed attention sinks, tokens that attract disproportionately high attention, and associated massive activations in which some features of sink tokens exhibit huge activation in LLMs. In this work, we are the first to study these phenomena in multimodal speech recognition. Through a detailed analysis of audio-visual LLMs, we identify attention sinks and massive activations not only at the BOS token but also at intermediate low-semantic tokens across ASR, VSR, and AVSR. We show that massive activations originate in the MLP layers and correspond to fixed feature indices across all sink tokens. We further show that intermediate sink tokens exhibit high cosine similarity to the BOS token, thereby amplifying attention and activation. Building on these insights, we introduce a simple decorrelation loss that reduces cosine similarity between BOS and other tokens, effectively mitigating intermediate sinks and massive activations. Furthermore, our method improves word error rate (WER) under high audio-visual feature downsampling while remaining stable at lower downsampling rates.

Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction that is often overlooked in favor of purely functional capabilities like reasoning and question answering. To address this limitation, we introduce UltraVoice, the first large-scale speech dialogue dataset engineered for multiple fine-grained speech style control. Encompassing over 830 hours of speech dialogues, UltraVoice provides instructions across six key speech stylistic dimensions: emotion, speed, volume, accent, language, and composite styles. Fine-tuning leading models such as SLAM-Omni and VocalNet on UltraVoice significantly enhances their fine-grained speech stylistic controllability without degrading core conversational abilities. Specifically, our fine-tuned models achieve improvements of 29.12-42.33% in Mean Opinion Score (MOS) and 14.61-40.09 percentage points in Instruction Following Rate (IFR) on multi-dimensional control tasks designed in the UltraVoice. Moreover, on the URO-Bench benchmark, our fine-tuned models demonstrate substantial gains in core understanding, reasoning, and conversational abilities, with average improvements of +10.84% on the Basic setting and +7.87% on the Pro setting. Furthermore, the dataset's utility extends to training controllable Text-to-Speech (TTS) models, underscoring its high quality and broad applicability for expressive speech synthesis. The complete dataset and model checkpoints are available at: https://github.com/bigai-nlco/UltraVoice.

The coordination of multiple autonomous agents in high-speed, competitive environments represents a significant engineering challenge. This paper presents CRUISE (Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing), a reinforcement learning framework designed to solve this challenge in the demanding domain of multi-drone racing. CRUISE overcomes key scalability limitations by synergistically combining a progressive difficulty curriculum with an efficient self-play mechanism to foster robust competitive behaviors. Validated in high-fidelity simulation with realistic quadrotor dynamics, the resulting policies significantly outperform both a standard reinforcement learning baseline and a state-of-the-art game-theoretic planner. CRUISE achieves nearly double the planner's mean racing speed, maintains high success rates, and demonstrates robust scalability as agent density increases. Ablation studies confirm that the curriculum structure is the critical component for this performance leap. By providing a scalable and effective training methodology, CRUISE advances the development of autonomous systems for dynamic, competitive tasks and serves as a blueprint for future real-world deployment.

This paper introduces SPIRAL (Self-Play Incremental Racing Algorithm for Learning), a novel approach for training autonomous drones in multi-agent racing competitions. SPIRAL distinctively employs a self-play mechanism to incrementally cultivate complex racing behaviors within a challenging, dynamic environment. Through this self-play core, drones continuously compete against increasingly proficient versions of themselves, naturally escalating the difficulty of competitive interactions. This progressive learning journey guides agents from mastering fundamental flight control to executing sophisticated cooperative multi-drone racing strategies. Our method is designed for versatility, allowing integration with any state-of-the-art Deep Reinforcement Learning (DRL) algorithms within its self-play framework. Simulations demonstrate the significant advantages of SPIRAL and benchmark the performance of various DRL algorithms operating within it. Consequently, we contribute a versatile, scalable, and self-improving learning framework to the field of autonomous drone racing. SPIRAL's capacity to autonomously generate appropriate and escalating challenges through its self-play dynamic offers a promising direction for developing robust and adaptive racing strategies in multi-agent environments. This research opens new avenues for enhancing the performance and reliability of autonomous racing drones in increasingly complex and competitive scenarios.

Exposure-agnostic video frame interpolation (VFI) is a challenging task that aims to recover sharp, high-frame-rate videos from blurry, low-frame-rate inputs captured under unknown and dynamic exposure conditions. Event cameras are sensors with high temporal resolution, making them especially advantageous for this task. However, existing event-guided methods struggle to produce satisfactory results on severely low-frame-rate blurry videos due to the lack of temporal constraints. In this paper, we introduce a novel event-guided framework for exposure-agnostic VFI, addressing this limitation through two key components: a Target-adaptive Event Sampling (TES) and a Target-adaptive Importance Mapping (TIM). Specifically, TES samples events around the target timestamp and the unknown exposure time to better align them with the corresponding blurry frames. TIM then generates an importance map that considers the temporal proximity and spatial relevance of consecutive features to the target. Guided by this map, our framework adaptively blends consecutive features, allowing temporally aligned features to serve as the primary cues while spatially relevant ones offer complementary support. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our approach in exposure-agnostic VFI scenarios.

The emergence of extremely large-scale antenna arrays (ELAA) in millimeter-wave (mmWave) communications, particularly in high-mobility scenarios, highlights the importance of near-field beam prediction. Unlike the conventional far-field assumption, near-field beam prediction requires codebooks that jointly sample the angular and distance domains, which leads to a dramatic increase in pilot overhead. Moreover, unlike the far-field case where the optimal beam evolution is temporally smooth, the optimal near-field beam index exhibits abrupt and nonlinear dynamics due to its joint dependence on user angle and distance, posing significant challenges for temporal modeling. To address these challenges, we propose a novel Convolutional Neural Network-Generative Pre-trained Transformer 2 (CNN-GPT2) based near-field beam prediction framework. Specifically, an uplink pilot transmission strategy is designed to enable efficient channel probing through widebeam analog precoding and frequency-varying digital precoding. The received pilot signals are preprocessed and passed through a CNN-based feature extractor, followed by a GPT-2 model that captures temporal dependencies across multiple frames and directly predicts the near-field beam index in an end-to-end manner.

Image downscaling is one of the key operations in recent display technology and visualization tools. By this process, the dimension of an image is reduced, aiming to preserve structural integrity and visual fidelity. In this paper, we propose a new image downscaling method which is built on the core ideas of image filtering and edge detection. In particular, we present a structure-informed downscaling algorithm that maintains fine details through edge-aware processing. The proposed method comprises three steps: (i) edge map computation, (ii) edge-guided interpolation, and (iii) texture enhancement. To faithfully retain the strong structures in an image, we first compute the edge maps by applying an efficient edge detection operator. This is followed by an edge-guided interpolation to preserve fine details after resizing. Finally, we fuse local texture enriched component of the original image to the interpolated one to restore high-frequency information. By integrating edge information with adaptive filtering, our approach effectively minimizes artifacts while retaining crucial image features. To demonstrate the effective downscaling capability of our proposed method, we validate on four datasets: DIV2K, BSD100, Urban100, and RealSR. For downscaling by 4x, our method could achieve as high as 39.07 dB PSNR on the DIV2K dataset and 38.71 dB on the RealSR dataset. Extensive experimental results confirm that the proposed image downscaling method is capable of achieving superior performance in terms of both visual quality and performance metrics with reference to recent methods. Most importantly, the downscaled images by our method do not suffer from edge blurring and texture loss, unlike many existing ones.

Images acquired in low-light environments present significant obstacles for computer vision systems and human perception, especially for applications requiring accurate object recognition and scene analysis. Such images typically manifest multiple quality issues: amplified noise, inadequate scene illumination, contrast reduction, color distortion, and loss of details. While recent deep learning methods have shown promise, developing simple and efficient frameworks that naturally integrate global illumination adjustment with local detail refinement continues to be an important objective. To this end, we introduce a dual-stage deep learning architecture that combines adaptive gamma correction with attention-enhanced refinement to address these fundamental limitations. The first stage uses an Adaptive Gamma Correction Module (AGCM) to learn suitable gamma values for each pixel based on both local and global cues, producing a brightened intermediate output. The second stage applies an encoder-decoder deep network with Convolutional Block Attention Modules (CBAM) to this brightened image, in order to restore finer details. We train the network using a composite loss that includes L1 reconstruction, SSIM, total variation, color constancy, and gamma regularization terms to balance pixel accuracy with visual quality. Experiments on LOL-v1, LOL-v2 real, and LOL-v2 synthetic datasets show our method reaches PSNR of upto 29.96 dB and upto 0.9458 SSIM, outperforming existing approaches. Additional tests on DICM, LIME, MEF, and NPE datasets using NIQE, BRISQUE, and UNIQUE metrics confirm better perceptual quality with fewer artifacts, achieving the best NIQE scores across all datasets. Our GAtED (Gamma learned and Attention-enabled Encoder-Decoder) method effectively handles both global illumination adjustment and local detail enhancement, offering a practical solution for low-light enhancement.

In this paper, we propose an optimally structured gradient coding scheme to mitigate the straggler problem in distributed learning. Conventional gradient coding methods often assume homogeneous straggler models or rely on excessive data replication, limiting performance in real-world heterogeneous systems. To address these limitations, we formulate an optimization problem minimizing residual error while ensuring unbiased gradient estimation by explicitly considering individual straggler probabilities. We derive closed-form solutions for optimal encoding and decoding coefficients via Lagrangian duality and convex optimization, and propose data allocation strategies that reduce both redundancy and computation load. We also analyze convergence behavior for $\lambda$-strongly convex and $\mu$-smooth loss functions. Numerical results show that our approach significantly reduces the impact of stragglers and accelerates convergence compared to existing methods.

Optimal sensor placement (OSP) is critical for efficient, accurate monitoring, control, and inference in complex physical systems. We propose a machine-learning-based feature attribution (FA) framework to identify OSP for target predictions. FA quantifies input contributions to a model output; however, it struggles with highly correlated input data often encountered in practical applications for OSP. To address this, we propose a Correlation-Assisted Attribution Framework (CAAF), which introduces a clustering step on the candidate sensor locations before performing FA to reduce redundancy and enhance generalizability. We first illustrate the core principles of the proposed framework through a series of validation cases, then demonstrate its effectiveness in realistic dynamical systems such as structural health monitoring, airfoil lift prediction, and wall-normal velocity estimation for turbulent channel flow. The results show that the CAAF outperforms alternative approaches that typically struggle due to the presence of nonlinear dynamics, chaotic behavior, and multi-scale interactions, and enables the effective application of FA for identifying OSP in real-world environments.

This paper presents a constructive framework for synthesizing provably safe controllers for nonlinear multi-agent systems subject to bounded disturbances. The methodology applies to systems representable in Brunovsky canonical form, accommodating arbitrary-order dynamics in multi-dimensional spaces. The central contribution is a method of constraint tightening that formally couples robust error feedback with nominal trajectory planning. The key insight is that the design of an ancillary feedback law, which confines state errors to a robust positively invariant (RPI) tube, simultaneously provides the exact information needed to ensure the safety of the nominal plan. Specifically, the geometry of the resulting RPI tube is leveraged via its support function to derive state-dependent safety margins. These margins are then used to systematically tighten the high relative-degree exponential control barrier function (eCBF) constraints imposed on the nominal planner. This integrated synthesis guarantees that any nominal trajectory satisfying the tightened constraints corresponds to a provably safe trajectory for the true, disturbed system. We demonstrate the practical utility of this formal synthesis method by implementing the planner within a distributed Model Predictive Control (MPC) scheme, which optimizes performance while inheriting the robust safety guarantees.

This paper derives a new class of vector-valued reproducing kernel Hilbert spaces (vRKHS) defined in terms of operator-valued kernels for the representation of functional uncertainty arising in nonparametric adaptive control methods. These are referred to as maneuver or trajectory vRKHS KM in the paper, and they are introduced to address the curse of dimensionality that can arise for some types of nonparametric adaptive control strategies. The maneuver vRKHSs are derived based on the structure of a compact, l-dimensional, smooth Riemannian manifold M that is regularly embedded in the state space X = Rn, where M is assumed to approximately support the ultimate dynamics of the reference system to be tracked.

The rapid increase in renewable energy sources (RES) implementation in the power system creates more severe network congestion, which may reduce grid operation efficiency and cause renewable curtailment. Deterministic optimization for the unit commitment shows that battery energy storage system (BESS)-based Virtual Transmission Line (VTL), as an alternative to physical transmission lines, can offer a quick solution for congestion relief, reduced operational costs, and lowered renewable curtailment. This paper aims to evaluate the benefits of VTL when considering Renewable Energy Sources uncertainty. Particularly, this work proposes a scenario-based stochastic security-constrained unit commitment model considering VTL, referred to as SSCUC-VTL. It incorporates the forecast error of RES into the commitment decision for systems with VTL. The performance of applying the VTL strategy is compared to that of adding a new physical transmission line and a standalone BESS. A case study has been conducted on an enhanced IEEE 24-bus test system. The simulation results demonstrate that VTL provides 23% more operational cost reduction than the physical transmission line, and up to 67% more congestion relief than the standalone BESS in a power system with solar and wind generation.

Extracting pulsive temporal patterns from a small dataset without their repetition or singularity shows significant importance in manufacturing applications but does not sufficiently attract scientific attention. We propose to quantify how long temporal patterns appear without relying on their repetition or singularity, enabling to extract such temporal patterns from a small dataset. Inspired by the celebrated time delay embedding and data-driven Hankel matrix analysis, we introduce a linear dynamical system model on the time-delay coordinates behind the data to derive the discrete-time bases each of which has a distinct exponential decay constant. The derived bases are fitted onto subsequences that are extracted with a sliding window in order to quantify how long patterns are dominant in the set of subsequences. We call the quantification method Data-driven Exponential Framing (DEF). A toy model-based experiment shows that DEF can identify multiple patterns with distinct lengths. DEF is also applied to electric current measurement on a punching machine, showing its possibility to extract multiple patterns from real-world oscillatory data.

Intelligent vehicles are one of the most important outcomes gained from the world tendency toward automation. Applications of IVs, whether in urban roads or robot tracks, do prioritize lane path detection. This paper proposes an FPGA-based Lane Detector Vehicle LDV architecture that relies on the Sobel algorithm for edge detection. Operating on 416 x 416 images and 150 MHz, the system can generate a valid output every 1.17 ms. The valid output consists of the number of present lanes, the current lane index, as well as its right and left boundaries. Additionally, the automated light and temperature control units in the proposed system enhance its adaptability to the surrounding environmental conditions.

Accurate diagnosis of Alzheimer's disease (AD) is essential for enabling timely intervention and slowing disease progression. Multimodal diagnostic approaches offer considerable promise by integrating complementary information across behavioral and perceptual domains. Eye-tracking and facial features, in particular, are important indicators of cognitive function, reflecting attentional distribution and neurocognitive state. However, few studies have explored their joint integration for auxiliary AD diagnosis. In this study, we propose a multimodal cross-enhanced fusion framework that synergistically leverages eye-tracking and facial features for AD detection. The framework incorporates two key modules: (a) a Cross-Enhanced Fusion Attention Module (CEFAM), which models inter-modal interactions through cross-attention and global enhancement, and (b) a Direction-Aware Convolution Module (DACM), which captures fine-grained directional facial features via horizontal-vertical receptive fields. Together, these modules enable adaptive and discriminative multimodal representation learning. To support this work, we constructed a synchronized multimodal dataset, including 25 patients with AD and 25 healthy controls (HC), by recording aligned facial video and eye-tracking sequences during a visual memory-search paradigm, providing an ecologically valid resource for evaluating integration strategies. Extensive experiments on this dataset demonstrate that our framework outperforms traditional late fusion and feature concatenation methods, achieving a classification accuracy of 95.11% in distinguishing AD from HC, highlighting superior robustness and diagnostic performance by explicitly modeling inter-modal dependencies and modality-specific contributions.

Secure and reliable medical image classification is crucial for effective patient treatment, but centralized models face challenges due to data and privacy concerns. Federated Learning (FL) enables privacy-preserving collaborations but struggles with heterogeneous, non-IID data and high communication costs, especially in large networks. We propose CFL-SparseMed, an FL approach that uses Top-k Sparsification to reduce communication overhead by transmitting only the top k gradients. This unified solution effectively addresses data heterogeneity while maintaining model accuracy. It enhances FL efficiency, preserves privacy, and improves diagnostic accuracy and patient care in non-IID medical imaging settings. The reproducibility source code is available on \href{https://github.com/Aniket2241/APK_contruct}{Github}.

Multimodal Large Language Models (LLMs) claim "musical understanding" via evaluations that conflate listening with score reading. We benchmark three SOTA LLMs (Gemini 2.5 Pro, Gemini 2.5 Flash, and Qwen2.5-Omni) across three core music skills: Syncopation Scoring, Transposition Detection, and Chord Quality Identification. Moreover, we separate three sources of variability: (i) perceptual limitations (audio vs. MIDI inputs), (ii) exposure to examples (zero- vs. few-shot manipulations), and (iii) reasoning strategies (Standalone, CoT, LogicLM). For the latter we adapt LogicLM, a framework combining LLMs with symbolic solvers to perform structured reasoning, to music. Results reveal a clear perceptual gap: models perform near ceiling on MIDI but show accuracy drops on audio. Reasoning and few-shot prompting offer minimal gains. This is expected for MIDI, where performance reaches saturation, but more surprising for audio, where LogicLM, despite near-perfect MIDI accuracy, remains notably brittle. Among models, Gemini Pro achieves the highest performance across most conditions. Overall, current systems reason well over symbols (MIDI) but do not yet "listen" reliably from audio. Our method and dataset make the perception-reasoning boundary explicit and offer actionable guidance for building robust, audio-first music systems.