Papers

Ultrasound (US) interpretation is hampered by multiplicative speckle, acquisition blur from the point-spread function (PSF), and scanner- and operator-dependent artifacts. Supervised enhancement methods assume access to clean targets or known degradations; conditions rarely met in practice. We present a blind, self-supervised enhancement framework that jointly deconvolves and denoises B-mode images using a Swin Convolutional U-Net trained with a physics-guided degradation model. From each training frame, we extract rotated/cropped patches and synthesize inputs by (i) convolving with a Gaussian PSF surrogate and (ii) injecting noise via either spatial additive Gaussian noise or complex Fourier-domain perturbations that emulate phase/magnitude distortions. For US scans, clean-like targets are obtained via non-local low-rank (NLLR) denoising, removing the need for ground truth; for natural images, the originals serve as targets. Trained and validated on UDIAT~B, JNU-IFM, and XPIE Set-P, and evaluated additionally on a 700-image PSFHS test set, the method achieves the highest PSNR/SSIM across Gaussian and speckle noise levels, with margins that widen under stronger corruption. Relative to MSANN, Restormer, and DnCNN, it typically preserves an extra $\sim$1–4\,dB PSNR and 0.05–0.15 SSIM in heavy Gaussian noise, and $\sim$2–5\,dB PSNR and 0.05–0.20 SSIM under severe speckle. Controlled PSF studies show reduced FWHM and higher peak gradients, evidence of resolution recovery without edge erosion. Used as a plug-and-play preprocessor, it consistently boosts Dice for fetal head and pubic symphysis segmentation. Overall, the approach offers a practical, assumption-light path to robust US enhancement that generalizes across datasets, scanners, and degradation types.

Coverage control algorithms have traditionally focused on static target densities, where agents optimally cover a fixed spatial distribution. However, many applications, such as environmental monitoring, surveillance, and adaptive sensing, involve time-varying densities. While time-varying coverage has been studied in Voronoi-based frameworks, extending recent optimal transport formulations of static coverage control to time-varying target densities remains an open problem. This paper presents a semi-discrete optimal transport framework for time-varying coverage control, in which agents track the first-order optimality conditions associated with minimizing the instantaneous Wasserstein distance from an evolving target density. The proposed approach is based on a coupled system of differential equations governing agent positions and the dual variables defining Laguerre regions. The resulting optimality residuals converge exponentially to zero, with global convergence established for one-dimensional domains. We also derive decentralized approximations and numerical simulations demonstrate improved tracking performance over quasi-static and Voronoi-based methods.

Distribution system operators need realistic load and generation profiles when measurements are unavailable, incomplete, or too coarse for the intended analysis. Training separate models for synthetic data generation, imputation, and super-resolution can duplicate modeling effort as observation requirements change. This paper presents SmartMeterFM, a conditional flow matching model trained once on monthly smart meter profiles at 15 min resolution. Customer and calendar attributes condition the model during training, while numerical profile constraints, observed intervals, and coarse measurements are incorporated through projection-based guidance at inference. The same weights serve all tasks without task-specific retraining and preserve temporal patterns and extreme values while producing profiles consistent with the supplied observations. A large-scale case study using Dutch consumption and photovoltaic generation profiles reports lower mean Continuous Ranked Probability Score (CRPS) than the selected task-specific baselines for imputation and 16-fold super-resolution. On a public dataset of 2,400 residential meters, the same weights match the imputation CRPS of a task-trained diffusion model when sampled ancestrally, attain a 4.5% lower super-resolution CRPS with the default sampler, and meet the specified monthly maximum and mean power within 0.01 kW.

Navigating urban intersections, especially when interacting with heterogeneous traffic participants, presents a formidable challenge for autonomous vehicles (AVs). In such environments, safety risks arise simultaneously from multiple sources, each carrying distinct priority levels and sensitivities that necessitate differential protection preferences. While safe reinforcement learning (RL) offers a robust paradigm for constrained decision-making, existing methods typically model safety as a single constraint or employ static, heuristic weighting schemes for multiple constraints. These approaches often fail to address the dynamic nature of multi-source risks, leading to gradient cancellation that hampers learning, and suboptimal trade-offs in critical dilemma zones. To address this, we propose a Bayesian adaptive priority safe reinforcement learning (BAP-SRL) based motion planning framework. Unlike heuristic weighting schemes, BAP formulates constraint prioritization as a probabilistic inference task. By modeling historical optimization difficulty as a Bayesian prior and instantaneous risk evidence as a likelihood, BAP dynamically gates gradient updates using a Bayesian inference mechanism on latent constraint criticality. Extensive experiments demonstrate that our approach outperforms state-of-the-art baselines in handling interactions with stochastic, heterogeneous agents, achieving lower collision rates and smoother conflict resolution.

We explore how command stack protection requirements outlined in NASA-STD-1006A can be satisfied within the context of emergency space telemetry. Proposed implementation of lightweight authenticated encryption offers strong security without sacrificing performance in resource-constrained environments. It produces fixed-length messages, maintaining compatibility with the underlying data transport protocols. By focusing on predictable properties and robust authentication, we create a scheme that protects the confidentiality, integrity and authenticity of telemetry data in emergency communications while balancing security requirements with the operational constraints.

The growing electrification of transportation and heating through Electric Vehicles (EVs) and Heat Pumps (HPs) introduces both flexibility and complexity to Active Distribution Networks (ADNs). These resources provide substantial operational flexibility but also create tightly coupled thermal-electrical dynamics that challenge conventional network management. This paper proposes a unified co-optimization framework that integrates a calibrated 3R2C grey-box building thermal model into a network-constrained Optimal Power Flow (OPF). The framework jointly optimizes EVs, HPs, and photovoltaic systems while explicitly enforcing thermal comfort, Distributed Energy Resource (DER) limits, and full power flow physics. To maintain computational tractability, Second-Order Cone Programming (SOCP) relaxations are evaluated on a realistic low-voltage feeder. The analysis shows that, despite network heterogeneity violating some theoretical exactness conditions, the relaxation remains exact in practice. Comparative assessments of convex DistFlow, bus injection, and branch flow formulations reveal that convex DistFlow achieves sub-second runtimes and near-optimal performance even at high DER penetration levels. Simulations confirm the effectiveness of coordinated scheduling, yielding reductions of 41% in transformer aging, 54% in losses, and complete elimination of voltage violations, demonstrating the value of integrated thermal-electrical coordination in future smart grids.

Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for serving modern Large Language Models (LLMs). We present StarSD, a one-for-many speculative decoding framework that uses a single draft model to serve multiple target models across distributed nodes via a star topology. StarSD decouples drafting and verification, enabling effective sharing of draft computation, and preventing distributed accelerators from remaining idle under bursty workloads. We provide a system-level analysis that characterizes when and why a single draft model can remain fully utilized by multiple verifiers, yielding predictable latency and utilization gains. Extensive experiments in real-world distributed inference settings demonstrate that StarSD simplifies deployment and supports flexible resource allocation across heterogeneous accelerators, while maintaining output quality. These results indicate that StarSD is a practical and scalable framework for bringing speculative decoding to modern cloud and edge inference infrastructures.

Bootstrap-based Self-Supervised Learning (SSL) has achieved remarkable progress in audio understanding. However, existing methods typically operate at a single level of granularity, limiting their ability to model the diverse temporal and spectral structures inherent in complex audio signals. Furthermore, bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge. In this work, we propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges. First, to capture hierarchical audio features, CAT incorporates a Multi-resolution Block that aggregates information across varying granularities. Second, to enhance training efficiency, we introduce a Representation Regularization objective. Drawing inspiration from generative modeling, this auxiliary task guides the student model by aligning its predictions with high-quality semantic representations from frozen, pre-trained external encoders. Experimental results demonstrate that CAT significantly outperforms baselines on audio understanding benchmarks. Notably, it achieves competitive performance on the AudioSet 20k dataset with 5 times faster convergence than existing methods. Codes and checkpoints will be released soon at https://github.com/realzhouchushu/CAT.

This letter proposes a decentralized local gain condition (LGC) to guarantee oscillation damping in inverter-based resource (IBR)-dominated power systems. The LGC constrains the dynamic gain between each IBR and the network at its point of connection. By satisfying the LGC locally, the closed-loop poles are confined to a desired region, thereby yielding system-wide oscillation damping without requiring global information. Notably, the LGC is agnostic to different IBR dynamics, well-suited for systems with heterogeneous IBRs, and flexible to various damping requirements. Moreover, a low-complexity algorithm is proposed to parameterize LGC, providing scalable and damping-constrained parameter tuning guidance for IBRs.

In the evolving landscape of sixth-generation (6G) mobile communication, multiple-input multiple-output (MIMO) systems are incorporating an unprecedented number of antenna elements, advancing towards Extremely large-scale multiple-input-multiple-output (XL-MIMO) systems. This enhancement significantly increases the spatial degrees of freedom, offering substantial benefits for wireless positioning. However, the expansion of the near-field range in XL-MIMO challenges the traditional far-field assumptions used in previous MIMO models. Among various configurations, uniform circular arrays (UCAs) demonstrate superior performance by maintaining constant angular resolution, unlike linear planar arrays. Addressing how to leverage the expanded aperture and harness the near-field effects in XL-MIMO systems remains an area requiring further investigation. In this paper, we introduce an attention-enhanced deep learning approach for precise positioning. We employ a dual-path channel attention mechanism and a spatial attention mechanism to effectively integrate channel-level and spatial-level features. Our comprehensive simulations show that this model surpasses existing benchmarks such as attention-based positioning networks (ABPN), near-field positioning networks (NFLnet), convolutional neural networks (CNN), and multilayer perceptrons (MLP). The proposed model achieves superior positioning accuracy by utilizing covariance metrics of the input signal. Also, simulation results reveal that covariance metric is advantageous for positioning over channel state information (CSI) in terms of positioning accuracy and model efficiency.

Can classical consensus models predict the group behavior of large language models (LLMs)? We examine multi-round interactions among LLM agents through the DeGroot framework, where agents exchange text-based messages over diverse communication graphs. To track opinion evolution, we map each message to an opinion score via sentiment analysis. We find that agents typically reach consensus and the disagreement between the agents decays exponentially. However, the limiting opinion departs from DeGroot's network-centrality-weighted forecast. The consensus between LLM agents turns out to be largely insensitive to initial conditions and instead depends strongly on the discussion subject and inherent biases. Nevertheless, transient dynamics align with classical graph theory and the convergence rate of opinions is closely related to the second-largest eigenvalue of the graph's combination matrix. Together, these findings can be useful for LLM-driven social-network simulations and the design of resource-efficient multi-agent LLM applications.

Acquiring channel state information (CSI) through traditional methods, such as channel estimation, is increasingly challenging for the emerging sixth generation (6G) mobile networks due to high overhead. To address this issue, channel extrapolation techniques have been proposed to acquire complete CSI from a limited number of known CSIs. To improve extrapolation accuracy, environmental information, such as visual images or radar data, has been utilized, which poses challenges including additional hardware, privacy and multi-modal alignment concerns. To this end, this paper proposes a novel channel extrapolation framework by leveraging environment-related multi-path characteristics induced directly from CSI without integrating additional modalities. Specifically, we propose utilizing the multi-path characteristics in the form of power-delay profile (PDP), which is acquired using a CSI-to-PDP module. CSI-to-PDP module is trained in an AE-based framework by reconstructing the PDPs and constraining the latent low-dimensional features to represent the CSI. We further extract the total power & power-weighted delay of all the identified paths in PDP as the multi-path information. Building on this, we proposed a MAE architecture trained in a self-supervised manner to perform channel extrapolation. Unlike standard MAE approaches, our method employs separate encoders to extract features from the masked CSI and the multi-path information, which are then fused by a cross-attention module. Extensive simulations demonstrate that this framework improves extrapolation performance dramatically, with a minor increase in inference time (around 0.1 ms). Furthermore, our model shows strong generalization capabilities, particularly when only a small portion of the CSI is known, outperforming existing benchmarks.

Indoor mobile robot navigation requires fast responsiveness and robust semantic understanding, yet existing methods struggle to provide both. Classical geometric approaches such as SLAM offer reliable localization but depend on detailed maps and cannot interpret human-targeted cues (e.g., signs, room numbers) essential for indoor reasoning. Vision-Language-Action (VLA) models introduce semantic grounding but remain strictly reactive, basing decisions only on visible frames and failing to anticipate unseen intersections or reason about distant textual cues. Vision-Language Models (VLMs) provide richer contextual inference but suffer from high computational latency, making them unsuitable for real-time operation on embedded platforms. In this work, we present IROS, a real-time navigation framework that combines VLM-level contextual reasoning with the efficiency of lightweight perceptual modules on low-cost, on-device hardware. Inspired by Dual Process Theory, IROS separates fast reflexive decisions (System One) from slow deliberative reasoning (System Two), invoking the VLM only when necessary. Furthermore, by augmenting compact VLMs with spatial and textual cues, IROS delivers robust, human-like navigation with minimal latency. Across five real-world buildings, IROS improves decision accuracy and reduces latency by 66% compared to continuous VLM-based navigation.

Near-field localization for ISAC requires large-aperture arrays, making fully-digital implementations prohibitively complex and costly. While sparse subarray architectures can reduce cost, they introduce severe estimation ambiguity from grating lobes. To address both issues, we propose SHARE (Sparse Hierarchical Angle-Range Estimation), a novel two-stage sparse recovery algorithm. SHARE operates in two stages. It first performs coarse, unambiguous angle estimation using individual subarrays to resolve the grating lobe ambiguity. It then leverages the full sparse aperture to perform a localized joint angle-range search. This hierarchical approach avoids an exhaustive and computationally intensive two-dimensional grid search while preserving the high resolution of the large aperture. Simulation results show that SHARE significantly outperforms conventional one-shot sparse recovery methods, such as Orthogonal Matching Pursuit (OMP), in both localization accuracy and robustness. Furthermore, we show that SHARE's overall localization accuracy is comparable to or even surpasses that of the fully-digital 2D-MUSIC algorithm, despite MUSIC having access to the complete, uncompressed data from every antenna element. SHARE therefore provides a practical path for high-resolution near-field ISAC systems.

Integrated sensing and communication is a key feature in next-generation wireless networks, enabling joint data transmission and environmental radar sensing on shared spectrum. In multi-user scenarios, simultaneous transmissions cause mutual interference on overlapping frequencies, leading to spurious target detections and degraded sensing accuracy. This paper proposes an interference detection and exploitation algorithm for sensing using spectrally interleaved orthogonal frequency division multiplexing. A statistically rigorous procedure is introduced to detect interference while controlling the familywise error rate. We propose an algorithm that estimates the angle by exploiting interference, while estimating the delay by avoiding the interference. Numerical experiments demonstrate that the proposed method reliably detects interference, and that the delay and angle estimation error approaches the Cramér-Rao lower bound.

In recent years, Text-to-Audio Generation has achieved remarkable progress, offering sound creators powerful tools to transform textual inspirations into vivid audio. However, existing models predominantly operate directly in the acoustic latent space of a Variational Autoencoder (VAE), often leading to suboptimal alignment between generated audio and textual descriptions. In this paper, we introduce SemanticAudio, a novel framework that conducts both audio generation and editing directly in a high-level semantic space. We define this semantic space as a compact representation capturing the global identity and temporal sequence of sound events, distinct from fine-grained acoustic details. SemanticAudio employs a two-stage Flow Matching architecture: the Semantic Planner first generates these compact semantic features to sketch the global semantic layout, and the Acoustic Synthesizer subsequently produces high-fidelity acoustic latents conditioned on this semantic plan. Leveraging this decoupled design, we further introduce a training-free text-guided editing mechanism that enables precise attribute-level modifications on general audio without retraining. Specifically, this is achieved by steering the semantic generation trajectory via the difference of velocity fields derived from source and target text prompts. Extensive experiments demonstrate that SemanticAudio surpasses existing mainstream approaches in semantic alignment. Demo available at: https://semanticaudio1.github.io/

The presence of interharmonics in power systems can lead to asynchronous sampling, a phenomenon further aggravated by shifts in the fundamental frequency, which significantly degrades the accuracy of power measurements. Under such asynchronous conditions, interharmonics lose orthogonality with the fundamental and harmonic components, giving rise to additional power components. To address these challenges, this paper introduces a linearization algorithm based on DFT spectrum analysis for precise power measurement in systems containing interharmonics. The proposed approach constructs a system of linear equations from the DFT spectrum and solves it through efficient matrix operations, enabling accurate extraction of interharmonic components near the fundamental and harmonic frequencies (with a frequency interval $\geq$1 Hz). This allows for precise measurement of power across the fundamental, harmonic, interharmonic, and cross-power bands, as well as total power. Test results demonstrate that the proposed method accurately computes various power components under diverse conditions–including varying interharmonic/fundamental/harmonic intervals, fundamental frequency deviations, and noise. Compared to existing methods such as fast Fourier transform (FFT), Windowed interpolation FFT, and Matrix pencil-Singular value decomposition, the proposed technique reduces estimation error by several times to multiple folds and exhibits improved robustness, while maintaining a computational time of only 7 ms for processing 10-power-line-cycle (200 ms) data.

In the last few years, energy efficiency has become a challenge. Not only mitigating environmental impact but reducing energy waste can lead to financial advantages. Buildings play an important role in this: they are among the biggest consumers. So, finding manners to reduce energy consumption is a way to minimise energy waste, and a technique for that is creating Demand Response (DR) strategies. This paper proposes a novel way to decrease computational effort of simulating the behaviour of a building using surrogate models based on active learning. Before going straight to the problem of a building, which is complex and computationally costly, the paper proposes the approach of active learning to a smaller problem: with reduced simulations, regress the curve of voltage versus current of a thermo-resistor. Then, the paper implements a surrogate model of energy consumption of a building. The goal is to be able to learn the consumption pattern based on a limited number of simulations. The result given by the surrogate can be used to set the reference temperature, maximising the PV self-consumption, and reducing energy usage from the grid. Thanks to the surrogate, the total time spent to map all possible consumption scenarios is reduced around 7 times.

The growing prevalence of extreme weather events driven by climate change poses significant challenges to power system resilience. Infrastructure damage and prolonged power outages highlight the urgent need for effective grid-hardening strategies. While some measures provide long-term protection against specific hazards, they can become counterproductive under conflicting threats. In this work, we develop an adaptive two-stage stochastic optimization framework to support dynamic decision-making for hardening critical grid components under multiple hazard exposures. Unlike traditional approaches, our model adapts to evolving climate conditions, enabling more resilient investment strategies. Furthermore, we integrate long-term (undergrounding) and short-term (vegetation management) hardening actions to jointly minimize total system costs. Extensive simulation results validate the effectiveness of the proposed framework in reducing outage and repair costs while enhancing the adaptability and robustness of grid infrastructure planning.

While Automatic Speech Recognition (ASR) is typically benchmarked by word error rate (WER), real-world applications ultimately hinge on semantic fidelity. This mismatch is particularly problematic for dysarthric speech, where articulatory imprecision and disfluencies can cause severe semantic distortions. To bridge this gap, we introduce a Large Language Model (LLM)-based agent for post-ASR correction: a Judge-Editor over the top-k ASR hypotheses that keeps high-confidence spans, rewrites uncertain segments, and operates in both zero-shot and fine-tuned modes. In parallel, we release SAP-Hypo5, the largest benchmark for dysarthric speech correction, to enable reproducibility and future exploration. Under multi-perspective evaluation, our agent achieves a 14.51% WER reduction alongside substantial semantic gains, including a +7.59 pp improvement in MENLI and +7.66 pp in Slot Micro F1 on challenging samples. Our analysis further reveals that WER is highly sensitive to domain shift, whereas semantic metrics correlate more closely with downstream task performance.

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects. Both of them leverage large-scale speech training data and the strong audio understanding ability of their foundation model Qwen3-Omni. We conduct comprehensive internal evaluation besides the open-sourced benchmarks as ASR models might differ little on open-sourced benchmark scores but exhibit significant quality differences in real-world scenarios. The experiments reveal that the 1.7B version achieves SOTA performance among open-sourced ASR models and is competitive with the strongest proprietary APIs while the 0.6B version offers the best accuracy-efficiency trade-off. Qwen3-ASR-0.6B can achieve an average TTFT as low as 92ms and transcribe 2000 seconds speech in 1 second at a concurrency of 128. Qwen3-ForcedAligner-0.6B is an LLM based NAR timestamp predictor that is able to align text-speech pairs in 11 languages. Timestamp accuracy experiments show that the proposed model outperforms the three strongest force alignment models and takes more advantages in efficiency and versatility. To further accelerate the community research of ASR and audio understanding, we release these models under the Apache 2.0 license.

Time-domain ADCs are attractive for high-speed wireline receivers, as time resolution scales favorably with advanced CMOS technologies, enabling multi-GS/s single-channel sampling rates. However, conventional time-domain ADCs require explicit reset of voltage-to-time and time-domain signal paths between samples, introducing dead time that fundamentally limits resolution, speed, and energy efficiency. This paper introduces a dual-edge reset-free quantization concept for asynchronous pipelined SAR time-domain ADCs, in which both rising and falling signal edges are exploited to enable reset-free quantization within a single conversion period. By eliminating explicit reset phases, the proposed approach expands the effective conversion window and relaxes the resolution-speed tradeoff at high sampling rates. An 8-bit dual-edge asynchronous pipelined SAR time-domain ADC is implemented in 22-nm FD-SOI, incorporating a linearity-compensated dual-edge voltage-to-time converter and a dual-edge time-to-digital converter with independently tunable rising- and falling-edge delays. The prototype occupies a core area of 0.0089 mm^2 and achieves continuous single-channel operation at 3.5 GS/s, with architectural scalability demonstrated through intermittent operation at 10.5 GS/s and higher. At 3.5 GS/s, the ADC achieves 21.6 dB SNDR and 32.2 dB SFDR. The measured performance is primarily limited by identifiable implementation-level factors rather than by architectural constraints, demonstrating the feasibility of dual-edge reset-free quantization for high-speed time-domain ADCs.

In this paper, we develop a tractable analytical framework for a three-dimensional (3D) indoor terahertz (THz) communication system to theoretically assess the impact of the pointing error on its coverage performance. Specifically, we model the locations of access points (APs) using a Poisson point process, human blockages as random cylinder processes, and wall blockages through a Boolean straight line process. A pointing error refers to beamforming gain and direction mismatch between the transmitter and receiver. We characterize it based on the inaccuracy of location estimate. We then analyze the impact of this pointing error on the received signal power and derive a tractable expression for the coverage probability, incorporating the multi-cluster fluctuating two-ray distribution to accurately model small-scale fading in THz communications. Aided by simulation results, we corroborate our analysis and demonstrate that the pointing error has a pronounced impact on the coverage probability. Specifically, we find that merely increasing the antenna array size is insufficient to improve the coverage probability and mitigate the detrimental impact of the pointing error, highlighting the necessity of advanced estimation techniques in THz communication systems.

In this paper, we address the problem of circumnavigation of a stationary target by a heterogeneous group comprising of $\textbf{n}$ autonomous agents, having unicycle kinematics. The agents are assumed to have constant linear speeds, we control only the angular speeds. Assuming limited sensing capabilities of the agents, only a subset of agents, termed as leaders, know the target location. The rest, termed as followers, do not. We propose a distributed guidance law which drives all the agents towards the desired objective; global asymptotic stability (GAS) is ensured by using Zubov's theorem. The efficacy of the approach is demonstrated through both numerical simulations and hardware experiments.

Complex networks are powerful representations of complex systems across scales and domains, and the field is experiencing unprecedented growth in data availability. However, real-world network data often suffer from noise, biases, and missing data in edge weights, which undermine the reliability of downstream network analyses. Standard noise filtering approaches, whether treating individual edges one-by-one or assuming a uniform global noise level, are suboptimal, because in reality both signal and noise can be heterogeneous and correlated across multiple edges. As a solution, we introduce the Network Wiener Filter, a principled method for collective edge-level noise filtering that leverages both network structure and noise characteristics, to reduce error in the observed edge weights and to infer missing edge weights. We demonstrate the broad practical efficacy of the Network Wiener Filter in two distinct settings, the genetic interaction network of the budding yeast S. cerevisiae and the Enron Corpus email network, noting compelling evidence of successful noise suppression in both applications. With the Network Wiener Filter, we advocate for a shift toward error-aware network science, one that embraces data imperfection as an inherent feature and learns to navigate it effectively.

We introduce Deep QP Safety Filter, a fully data-driven safety layer for black-box dynamical systems. Our method learns a Quadratic-Program (QP) safety filter without model knowledge by combining Hamilton-Jacobi (HJ) reachability with model-free learning. We construct contraction-based losses for both the safety value and its derivatives, and train two neural networks accordingly. In the exact setting, the learned critic converges to the viscosity solution (and its derivative), even for non-smooth values. Across diverse dynamical systems – even including a hybrid system – and multiple RL tasks, Deep QP Safety Filter substantially reduces pre-convergence failures while accelerating learning toward higher returns than strong baselines, offering a principled and practical route to safe, model-free control.

In time-critical eXtended reality (XR) scenarios where users must rapidly reorient their attention to hazards, alerts, or instructions while engaged in a primary task, spatial audio can provide an immediate directional cue without occupying visual bandwidth. However, such scenarios can afford only a brief auditory exposure, requiring users to interpret sound direction quickly and without extended listening or head-driven refinement. This paper reports a controlled exploratory study of rapid spatial-audio localization in XR. Using HRTF-rendered broadband stimuli presented from a semi-dense set of directions around the listener, we quantify how accurately users can infer coarse direction from brief audio alone. We further examine the effects of short-term visuo-auditory feedback training as a lightweight calibration mechanism. Our findings show that brief spatial cues can convey coarse directional information, and that even short calibration can improve users' perception of aural signals. While these results highlight the potential of spatial audio for rapid attention guidance, they also show that auditory cues alone may not provide sufficient precision for complex or high-stakes tasks, and that spatial audio may be most effective when complemented by other sensory modalities or visual cues, without relying on head-driven refinement. We leverage this study on spatial audio as a preliminary investigation into a first-stage attention-guidance channel for wearable XR (e.g., VR head-mounted displays and AR smart glasses), and provide design insights on stimulus selection and calibration for time-critical use.

Recently, the problem of music plagiarism has emerged as an even more pressing social issue. As music information retrieval research advances, there is a growing effort to address issues related to music plagiarism. However, many studies, including our previous work, have conducted research without clearly defining what the music plagiarism detection task actually involves. This lack of a clear definition has slowed research progress and made it hard to apply results to real-world scenarios. To fix this situation, we defined how Music Plagiarism Detection is different from other MIR tasks and explained what problems need to be solved. We introduce the Similar Music Pair dataset to support this newly defined task. In addition, we propose a method based on segment transcription as one way to solve the task. Our demo and dataset are available at https://github.com/Mippia/ICASSP2026-MPD.

This paper proposes a Koopman-based framework for modeling, prediction, and control of unknown nonlinear time-varying systems. We present a novel Koopman-based learning method for predicting the state of unknown nonlinear time-varying systems, upon which a robust controller is designed to ensure that the resulting closed-loop system is input-to-state stable with respect to the Koopman approximation error. The error of the lifted system model learned through the Koopman-based method increases over time due to the time-varying nature of the nonlinear time-varying system. To address this issue, an online iterative update scheme is incorporated into the learning process to update the lifted system model, aligning it more precisely with the time-varying nonlinear system by integrating the updated data and discarding the outdated data. A necessary condition for the feasibility of the proposed iterative learning method is derived. In order to reduce unnecessary system updates while ensuring the prediction accuracy of the lifted system, the update mechanism is enhanced to determine whether to update the lifted system and meanwhile to reduce updates that deteriorate the fitting performance. Furthermore, based on the online-updated lifted system, a controller is designed to ensure the closed-loop controlled system be input-to-state stable with respect to the Koopman approximation error. Numerical simulations on the Duffing oscillator, the serial manipulator, and the synthetic biological network system are presented to demonstrate the effectiveness of the proposed method for the approximation and control of unknown nonlinear time-varying systems. The results show that the proposed approach outperforms existing methods in terms of approximation accuracy and computational efficiency, even under significant system variations.

We study how model architecture and temporal context interact in naturalistic EEG decoding. Using the HBN movie-watching dataset, we benchmark five architectures, CNN, LSTM, a stabilized Transformer (EEGXF), S4, and S5, on a 4-class task across segment lengths from 8s to 128s. Accuracy improves with longer context: at 64s, S5 reaches 98.7%+/-0.6 and CNN 98.3%+/-0.3, while S5 uses ~20x fewer parameters than CNN. To probe real-world robustness, we evaluate zero-shot cross-frequency shifts, cross-task OOD inputs, and leave-one-subject-out generalization. S5 achieves stronger cross-subject accuracy but makes over-confident errors on OOD tasks; EEGXF is more conservative and stable under frequency shifts, though less calibrated in-distribution. These results reveal a practical efficiency-robustness trade-off: S5 for parameter-efficient peak accuracy; EEGXF when robustness and conservative uncertainty are critical.