Papers

In this study, we present a multimodal framework for predicting neuro-facial disorders by capturing both vocal and facial cues. We hypothesize that explicitly disentangling shared and modality-specific representations within multimodal foundation model embeddings can enhance clinical interpretability and generalization. To validate this hypothesis, we propose DIVINE a fully disentangled multimodal framework that operates on representations extracted from state-of-the-art (SOTA) audio and video foundation models, incorporating hierarchical variational bottlenecks, sparse gated fusion, and learnable symptom tokens. DIVINE operates in a multitask learning setup to jointly predict diagnostic categories (Healthy Control,ALS, Stroke) and severity levels (Mild, Moderate, Severe). The model is trained using synchronized audio and video inputs and evaluated on the Toronto NeuroFace dataset under full (audio-video) as well as single-modality (audio-only and video-only) test conditions. Our proposed approach, DIVINE achieves SOTA result, with the DeepSeek-VL2 and TRILLsson combination reaching 98.26% accuracy and 97.51% F1-score. Under modality-constrained scenarios, the framework performs well, showing strong generalization when tested with video-only or audio-only inputs. It consistently yields superior performance compared to unimodal models and baseline fusion techniques. To the best of our knowledge, DIVINE is the first framework that combines cross-modal disentanglement, adaptive fusion, and multitask learning to comprehensively assess neurological disorders using synchronized speech and facial video.

Energy landscape models characterize neural dynamics by assigning energy values to each brain state that reflect their stability or probability of occurrence. The conventional energy landscape models rely on binary brain state representation, where each region is considered either active or inactive based on some signal threshold. However, this binarization leads to significant information loss and an exponential increase in the number of possible brain states, making the calculation of energy values infeasible for large numbers of brain regions. To overcome these limitations, we propose a novel continuous energy landscape framework that employs Graph Neural Networks (GNNs) to learn a continuous precision matrix directly from functional MRI (fMRI) signals, preserving the full range of signal values during energy landscape computation. We validated our approach using both synthetic data and real-world fMRI datasets from brain tumor patients. Our results on synthetic data generated from a switching linear dynamical system (SLDS) and a Kuramoto model show that the continuous energy model achieved higher likelihood and more accurate recovery of basin geometry, state occupancy, and transition dynamics than conventional binary energy landscape models. In addition, results from the fMRI dataset indicate a 0.27 increase in AUC for predicting working memory and executive function, along with a 0.35 improvement in explained variance (R2) for predicting reaction time. These findings highlight the advantages of utilizing the full signal values in energy landscape models for capturing neuronal dynamics, with strong implications for diagnosing and monitoring neurological disorders.

Selective fixed-filter active noise control (SFANC) is a novel approach capable of mitigating noise with varying frequency characteristics. It offers faster response and greater computational efficiency compared to traditional adaptive algorithms. However, spatial factors, particularly the influence of the noise source location, are often overlooked. Some existing studies have explored the impact of the direction-of-arrival (DoA) of the noise source on ANC performance, but they are mostly limited to free-field conditions and do not consider the more complex indoor reverberant environments. To address this gap, this paper proposes a learning-based directional SFANC method that incorporates the DoA of the noise source in reverberant environments. In this framework, multiple reference signals are processed by a convolutional neural network (CNN) to estimate the azimuth and elevation angles of the noise source, as well as to identify the most appropriate control filter for effective noise cancellation. Compared to traditional adaptive algorithms, the proposed approach achieves superior noise reduction with shorter response times, even in the presence of reverberations.

Wake interactions in floating wind farms are inherently coupled to platform motion, yet most experimental studies to date neglect this two-way coupling by prescribing platform movements. This work presents a hardware-in-the-loop (HIL) wind-tunnel methodology to investigate wake interactions between two floating wind turbines with fully coupled aerodynamic loading and platform dynamics. The approach integrates physical wind-tunnel testing of two scaled rotors with a real-time numerical model that accounts for platform motion, mooring restoring forces, and hydrodynamic loads. Experiments conducted under low-turbulence inflow conditions show that a downstream turbine operating in the wake of an upstream turbine experiences reduced mean thrust and platform deflections due to the decreased inflow velocity, alongside enhanced low-frequency platform motions driven by increased turbulent energy in the wake. The proposed HIL framework provides a controlled experimental basis for studying wake-induced excitation mechanisms and supports the validation of floating wind farm models and control strategies.

The anticipated integration of large artificial intelligence (AI) models with wireless communications is estimated to usher a transformative wave in the forthcoming information age. As wireless networks grow in complexity, the traditional methodologies employed for optimization and management face increasingly challenges. Large AI models have extensive parameter spaces and enhanced learning capabilities and can offer innovative solutions to these challenges. They are also capable of learning, adapting and optimizing in real-time. We introduce the potential and challenges of integrating large AI models into wireless communications, highlighting existing AIdriven applications and inherent challenges for future large AI models. In this paper, we propose the architecture of large AI models for future wireless communications, introduce their advantages in data analysis, resource allocation and real-time adaptation, discuss the potential challenges and corresponding solutions of energy, architecture design, privacy, security, ethical and regulatory. In addition, we explore the potential future directions of large AI models in wireless communications, laying the groundwork for forthcoming research in this area.

We present TagSpeech, a unified LLM-based framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization. The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that not only supports fine-grained timestamp prediction but also acts as a synchronization signal between semantic understanding and speaker tracking. Compared to previous works that primarily focus on speaker-attributed ASR or implicit diarization, TagSpeech addresses the challenge of fine-grained speaker-content alignment and explicitly models "who spoke what and when" in an end-to-end manner. Experiments on AMI and AliMeeting benchmarks demonstrate that our method achieves consistent improvements in Diarization Error Rate (DER) over strong end-to-end baselines, including Qwen-Omni and Gemini, particularly in handling complex speech overlaps. Moreover, TagSpeech employs a parameter-efficient training paradigm in which the LLM backbone is frozen and only lightweight projectors are trained, resulting in strong performance with low computational cost.

Recent computational advances enable protein design pipelines to run end-to-end on GPUs, yet their heterogeneous computational behaviors remain undercharacterized at the system level. We implement and profile a representative pipeline at both component and full-pipeline granularities across varying inputs and hyperparameters. Our characterization identifies generally low GPU utilization and high sensitivity to sequence length and sampling strategies. We outline future research directions based on these insights and release an open-source pipeline and profiling scripts to facilitate further studies.

System operators can increasingly exploit distributed energy resources (DERs) and controllable loads (CLs) to provide frequency response services. In conventional practice, communication between the system operator and flexible devices relies on the Border Gateway Protocol (BGP)-based Internet. However, existing BGP-based architectures face challenges in providing latency-guaranteed control, while direct private and proprietary communication networks lead to additional deployment and maintenance costs. In contrast, the SCION-based Internet architecture supports latency-minimum path selection, which makes it suitable for latency-sensitive frequency contingency services such as fast frequency response (FFR). Hence, this paper proposes a real-time reserve dispatch framework to optimally select a portfolio of flexible devices to deliver FFR services using the SCION-based Internet. First, an analytical expression of the system frequency dynamics with respect to heterogeneous communication latencies is derived. Next, a cyber-physical co-optimization model is formulated to jointly schedule communication paths and physical flexibility resources for real-time FFR provision. To improve the computation efficiency, we propose a heuristic FFR allocation algorithm to approximate the optimal response portfolio, integrating contributions from both DERs and CLs. Numerical case studies demonstrate the benefits of the proposed algorithm and its capability to approximate the optimality of the reserves allocation while significantly reducing the computation time.

The quality of the user experience has become one of the most important aspects in todays world, as it directly influences individuals willingness to continue using or abandon a product or service. In this context, video conferencing applications (VCAs), which experienced widespread adoption following the COVID-19 pandemic, must deliver excellent performance to remain competitive in an increasingly crowded market. Although content providers (CPs) such as Zoom, WhatsApp, Telegram, and Google Meet can assess conversation quality by comparing transmitted and received data. The widespread use of end-to-end encryption in VCAs makes quality-of-experience (QoE) evaluation by internet service providers (ISPs) far more challenging. Since ISPs do not have access to the encrypted content, they must rely on passive measurements of unencrypted traffic characteristics on the data path. In this work, we present a simple yet effective QoE prediction framework based on an almost stock convolutional neural network (CNN) architecture that uses only the packet sizes extracted from the communication between two participants in a video conferencing (VC) call to predict two QoE metrics: BRISQUE and MOS. The proposed framework is simple, easy to implement, and does not require high-end computational resources, yet it provides superior prediction performance, as shown in our experiments on two custom datasets collected from WhatsApp and Zoom, which achieve substantial improvements over previous models for the QoE prediction task.

Future wireless communication systems will increasingly rely on the integration of millimeter wave (mmWave) and sub-6 GHz bands to meet heterogeneous demands on high-speed data transmission and extensive coverage. To fully exploit the benefits of mmWave bands in massive multiple-input multiple-output (MIMO) systems, highly accurate channel state information (CSI) is required. However, directly estimating the mmWave channel demands substantial pilot overhead due to the large CSI dimension and low signal-to-noise ratio (SNR) led by severe path loss and blockage attenuation. In this paper, we propose an efficient Multi-Domain Fusion Channel Extrapolator (MDFCE) to extrapolate sub-6 GHz band CSI to mmWave band CSI, so as to reduce the pilot overhead for mmWave CSI acquisition in dual band massive MIMO systems. Unlike traditional channel extrapolation methods based on mathematical modeling, the proposed MDFCE combines the mixture-of-experts framework and the multi-head self-attention mechanism to fuse multi-domain features of sub-6 GHz CSI, aiming to characterize the mapping from sub-6 GHz CSI to mmWave CSI effectively and efficiently. The simulation results demonstrate that MDFCE can achieve superior performance with less training pilots compared with existing methods across various antenna array scales and signal-to-noise ratio levels while showing a much higher computational efficiency.

Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn disentangled and interpretable representations is critical for uncovering latent generative mechanisms. Traditional approaches to unsupervised representation learning, including variational autoencoders (VAEs), often struggle to capture the temporal and spectral diversity inherent in such data. Here we introduce variational decomposition autoencoding (VDA), a framework that incorporates a strong structural bias toward signal decomposition into variational representation learning. VDA is instantiated through variational decomposition autoencoders (DecVAEs), i.e., encoder-only neural networks that perform latent autoencoding at the level of distributions to learn multiple latent subspaces aligned with time-frequency characteristics. We evaluate DecVAEs on simulated data and three publicly available scientific datasets, spanning speech recognition, dysarthric speech evaluation, and emotional speech classification. DecVAEs improve on VAE-based methods in disentanglement quality and robustness, and their latent subspaces become factor-specific when the generative factors have distinct spectral signatures. These findings position decomposition-aware architectures as potential tools for extracting structured representations from speech, and potentially from other dynamic signals with factors exhibiting distinct spectral signatures, with applications in clinical diagnostics, human-computer interaction, and adaptive neurotechnologies.

This letter proposes a movable beyond-diagonal reconfigurable intelligent surfaces (MA-BD-RIS) design, combining inter-element connectivity and movability for channel enhancement. We study a MA-BD-RIS assisted multi-user multiple input single output system where beamforming, BD-RIS configuration, and elements positions are jointly optimized to maximize the sum-rate. An efficient algorithm is developed, incorporating closed-form beamforming, a low-complexity partially proximal alternating direction method of multipliers for BD-RIS design, and successive convex approximation for element placement. Simulations show that the high-movability structure yields superior performance in small-scale RIS and rich scattering scenarios, while the high-connectivity structure dominates in large-scale RIS and massive transmit array configurations.

This study proposes a non-contact method for identifying individuals through the use of heartbeat features measured with millimeter-wave radar. Although complex-valued radar signal spectrograms are commonly used for this task, little attention has been paid to the choice of signal components, namely, whether to use amplitude, phase, or the complex signal itself. Although spectrograms can be constructed independently from amplitude or phase information, their respective contributions to identification accuracy remain unclear. To address this issue, we first evaluate identification performance using spectrograms derived separately from amplitude, phase, and complex signals. We then propose a feature fusion method that integrates these three representations to enhance identification accuracy. Experiments conducted with a 79-GHz radar system and involving six participants achieved an identification accuracy of 97.67%, demonstrating the effectiveness of the proposed component-wise analysis and integration approach.

In this paper, we investigate a reconfigurable intelligent surface (RIS)-assisted integrated sensing and communications (ISAC) framework equipped with multiple Rydberg atomic receiver (RAR)-aided users. By leveraging the reference-assisted reception mechanism of RARs, we develop a unified signal model that jointly captures downlink multi-user communication with RARs and monostatic radar sensing. To explicitly balance communication performance and sensing accuracy, we formulate a Cramer-Rao bound (CRB)-constrained utility maximization problem. To address these challenges, we propose a joint optimization framework that combines fractional programming (FP), majorization-minimization (MM), and the alternating direction method of multipliers (ADMM). Simulation results demonstrate that the proposed framework consistently outperforms the conventional approach over a wide range of system environments, thereby highlighting the importance of the proposed framework in unlocking the potential of RARs for 6G.

The ongoing evolution of 5G and its enhanced version, 5G+, has significantly transformed the telecommunications landscape, driving an unprecedented demand for ultra-high-speed data transmission, ultra-low latency, and resilient connectivity. These capabilities are essential for enabling mission-critical applications such as the Internet of Things, autonomous vehicles, and smart city infrastructures. This survey investigates the important role of Artificial Intelligence (AI) in addressing the key challenges faced by 5G/5G+ networks, including interference mitigation, dynamic resource allocation, and maintaining seamless network operation. The study particularly focuses on AI-driven innovations in coding theory, which offer advanced solutions to the limitations of conventional error correction and modulation techniques. By employing deep learning, reinforcement learning, and neural network-based approaches, including convolutional neural networks, recurrent neural networks, and Transformer-based models, this research demonstrates significant advancements in error correction performance, decoding efficiency, and adaptive transmission strategies. Additionally, the integration of AI with emerging technologies, such as massive multiple-input and multiple-output, intelligent reflecting surfaces, and privacy-enhancing mechanisms, is discussed, highlighting their potential to propel the next generation of wireless networks. This survey provides an insightful overview of the transformative impact of AI on modern wireless communication, establishing a foundation for scalable, adaptive, and more efficient network architectures.

The growing integration of renewable energy sources into distribution networks poses significant challenges to frequency and voltage stability due to their intermittent nature and low-inertia dynamics. This paper proposes a multilevel control framework for a future decarbonized power system, using energy storage systems as power buffers to mitigate frequency and voltage fluctuations. A nonlinear interconnected model is formulated to describe the multilevel aggregated dynamics of the distribution network. To reduce the operational complexity and communication overhead of the control system, a distributed linear quadratic regulator strategy is developed based on bottom-up information exchange, where each level implements local feedback control over a short time horizon. Local stability conditions are established for the open-loop nonlinear model, and the closed-loop stability is characterized by the Hurwitz property of the system matrix. Performance bounds are also derived to quantify the gap between the distributed and centralized control strategies.

Determining the maximum demand a water distribution network can satisfy is crucial for ensuring reliable supply and planning network expansion. This problem, typically formulated as a mixed-integer nonlinear program (MINLP), is computationally challenging. A common strategy to address this challenge is to solve mixed-integer linear program (MILP) relaxations derived by partitioning variable domains and constructing linear over- and under-estimators to nonlinear constraints over each partition. While MILP relaxations are easier to solve up to a modest level of partitioning, their solutions often violate nonlinear water flow physics. Thus, recovering feasible MINLP solutions from the MILP relaxations is crucial for enhancing MILP-based approaches. In this paper, we propose a robust solution recovery method that efficiently computes feasible MINLP solutions from MILP relaxations, regardless of partition granularity. Combined with iterative partition refinement, our method generates a sequence of feasible solutions that progressively approach the optimum. Through extensive numerical experiments, we demonstrate that our method outperforms baseline methods and direct MINLP solves by consistently recovering high-quality feasible solutions with significantly reduced computation times.

This paper addresses the challenges of thermal sensor allocation and full-chip temperature reconstruction in multi-core systems by leveraging an entropy-based sensor placement strategy and an adaptive compressive sensing approach. By selecting sensor locations that capture diverse thermal behaviors and dynamically adjusting the measurement matrix, our method significantly enhances the accuracy of the full-chip temperature reconstruction. Experimental results demonstrate that our approach reduces full-chip temperature reconstruction error by 18% to 95%. In addition to the full-chip temperature reconstruction efficiency enhancement, our proposed method improves hardware efficiency by 5% to 514% over the related works. These findings highlight the potential of our method for more effective dynamic temperature management in future high-performance multi-core systems.

Ultrasound offers a safe, cost-effective, and widely accessible technology for fetal brain imaging, making it especially suitable for routine clinical use. However, it suffers from view-dependent artifacts, operator variability, and a limited field of view, which make interpretation and quantitative evaluation challenging. Ultrasound compounding aims to overcome these limitations by integrating complementary information from multiple 3D acquisitions into a single, coherent volumetric representation. This work provides four main contributions: (1) We present the first systematic categorization of computational strategies for fetal brain ultrasound compounding, including both classical techniques and modern learning-based frameworks. (2) We implement and compare representative methods across four key categories - multi-scale, transformation-based, variational, and deep learning approaches - emphasizing their core principles and practical advantages. (3) Motivated by the lack of full-view, artifact-free ground truth required for supervised learning, we focus on unsupervised and self-supervised strategies and introduce two new deep learning based approaches: a self-supervised compounding framework and an adaptation of unsupervised deep plug-and-play priors for compounding. (4) We conduct a comprehensive evaluation on ten multi-view fetal brain ultrasound datasets, using both expert radiologist scoring and standard quantitative image-quality metrics. We also release the USFetal Compounding Toolbox, publicly available to support benchmarking and future research. Keywords: Ultrasound compounding, fetal brain, deep learning, self-supervised, unsupervised.

Neuromorphic vision made significant progress in recent years, thanks to the natural match between spiking neural networks and event data in terms of biological inspiration, energy savings, latency and memory use for dynamic visual data processing. However, optimising its energy requirements still remains a challenge within the community, especially for embedded applications. One solution may reside in preprocessing events to optimise data quantity thus lowering the energy cost on neuromorphic hardware, proportional to the number of synaptic operations. To this end, we extend an end-to-end neuromorphic line detection mechanism to introduce line-based event data preprocessing. Our results demonstrate on three benchmark event-based datasets that preprocessing leads to an advantageous trade-off between energy consumption and classification performance. Depending on the line-based preprocessing strategy and the complexity of the classification task, we show that one can maintain or increase the classification accuracy while significantly reducing the theoretical energy consumption. Our approach systematically leads to a significant improvement of the neuromorphic classification efficiency, thus laying the groundwork towards a more frugal neuromorphic computer vision thanks to event preprocessing.

The detection of advanced persistent threats (APTs) remains a crucial challenge due to their stealthy, multistage nature and the limited availability of realistic, labeled datasets for systematic evaluation. Synthetic dataset generation has emerged as a practical approach for modeling APT campaigns; however, existing methods often rely on computationally expensive alert correlation mechanisms that limit scalability. Motivated by these limitations, this paper presents a near realistic synthetic APT dataset and an efficient alert correlation framework. The proposed approach introduces a machine learning based correlation module that employs K Nearest Neighbors (KNN) clustering with a cosine similarity metric to group semantically related alerts within a temporal context. The dataset emulates multistage APT campaigns across campus and organizational network environments and captures a diverse set of fourteen distinct alert types, exceeding the coverage of commonly used synthetic APT datasets. In addition, explicit APT campaign states and alert to stage mappings are defined to enable flexible integration of new alert types and support stage aware analysis. A comprehensive statistical characterization of the dataset is provided to facilitate reproducibility and support APT stage predictions.

Power electronic converter control is typically tuned per topology, limiting transfer across heterogeneous designs. This letter proposes a topology-agnostic meta-control framework that encodes converter netlists as typed bipartite graphs and uses a task-conditioned graph neural network backbone with distributed control heads. The policy is trained end-to-end via differentiable predictive control to amortize constrained optimal control over a distribution of converter parameters and reference-tracking tasks. In simulation on randomly sampled buck converters, the learned controller achieves near-optimal tracking performance relative to an online optimal-control baseline, motivating future extension to broader topologies, objectives, and real-time deployment.

This work introduces a robust single-channel inverse filter for dereverberation of non-ideal recordings, validated on real audio. The developed method focuses on the calculation and modification of a discrete impulse response in order to filter the characteristics from a known digital single channel recording setup and room characteristics such as early reflections and reverberations. The aim is a dryer and clearer signal reconstruction, which ideally would be the direct-path signal. The time domain impulse response is calculated from the cepstral domain and faded by means of frequency bin specific exponential decay in the spectrum. The decay rates are obtained by using the blind estimates of reverberation time ratio between recorded output and test signals for each frequency bin. The modified impulse response does filter a recorded audio-signal by deconvolution. The blind estimation is well known and stands out for its robustness to noise and non-idealities. Estimation of a direct path signal is key to many applications.

Artificial intelligence holds strong potential to support clinical decision making in intensive care units where timely and accurate risk assessment is critical. However, many existing models focus on isolated outcomes or limited data types, while clinicians integrate longitudinal history, real time physiology, and heterogeneous clinical information. To address this gap, we developed MDS ICU, a unified multimodal machine learning framework that fuses routinely collected data including demographics, biometrics, vital signs, laboratory values, ECG waveforms, surgical procedures, and medical device usage to provide continuous predictive support during ICU stays. Using 63001 samples from 27062 patients in MIMIC IV, we trained a deep learning architecture that combines structured state space S4 encoders for ECG waveforms with multilayer perceptron RealMLP encoders for tabular data to jointly predict 33 clinically relevant outcomes spanning mortality, organ dysfunction, medication needs, and acute deterioration. The model achieved strong discrimination with AUROCs of 0.90 for 24 hour mortality, 0.92 for sedative administration, 0.97 for invasive mechanical ventilation, and 0.93 for coagulation dysfunction. Calibration analysis showed close agreement between predicted and observed risks, with consistent gains from ECG waveform integration. Comparisons with clinicians and large language models showed that model predictions alone outperformed both, and that providing model outputs as decision support further improved their performance. These results demonstrate that multimodal AI can deliver clinically meaningful risk stratification across diverse ICU outcomes while augmenting rather than replacing clinical expertise, establishing a scalable foundation for precision critical care decision support.

A binaural rendering framework for personal sound zones (PSZs) is proposed to enable multiple head-tracked listeners to receive fully independent stereo audio programs. Current PSZ systems typically rely on monophonic rendering and therefore cannot control the left and right ears separately, which limits the quality and accuracy of spatial imaging. The proposed method employs a Binaural Spatially Adaptive Neural Network (BSANN) to generate ear-optimized loudspeaker filters that reconstruct the desired acoustic field at each ear of multiple listeners. The framework integrates anechoically measured loudspeaker frequency responses, analytically modeled transducer directivity, and rigid-sphere head-related transfer functions (HRTFs) to enhance acoustic accuracy and spatial rendering fidelity. An explicit active crosstalk cancellation (XTC) stage further improves three-dimensional spatial perception. Experiments show significant gains in measured objective performance metrics, including inter-zone isolation (IZI), inter-program isolation (IPI), and crosstalk cancellation (XTC), with log-frequency-weighted values of 10.23/10.03 dB (IZI), 11.11/9.16 dB (IPI), and 10.55/11.13 dB (XTC), respectively, over 100-20,000 Hz. The combined use of ear-wise control, accurate acoustic modeling, and integrated active XTC produces a unified rendering method that delivers greater isolation performance, increased robustness to room asymmetry, and more faithful spatial reproduction in real acoustic environments.

Programmable photonic integrated circuits (PPICs) offer a versatile platform for implementing diverse optical functions on a generic hardware mesh. However, the scalability of PPICs faces critical power consumption barriers. Therefore, we propose a novel non-volatile PPIC architecture utilizing MEMS with mechanical latching, enabling stable passive operation without any power connection once configured. To ensure practical applicability, we present a system-level solution including both this hardware innovation and an accompanying automatic error-resilient configuration algorithm. The algorithm compensates for the lack of continuous tunability inherent in the non-volatile hardware design, thereby enabling such new operational paradigm without compromising performance, and also ensuring robustness against fabrication errors. Functional simulations were performed to validate the proposed scheme by configuring five distinct functionalities of varying complexity, including a Mach-Zehnder interferometer (MZI), a MZI lattice filter, a ring resonator (ORR), a double ORR ring-loaded MZI, and a triple ORR coupled resonator waveguide filter. The results demonstrate that our non-volatile scheme achieves performance equivalent to conventional PPICs. Robustness analysis was also conducted, and the results demonstrated that our scheme exhibits strong robustness against various fabrication errors. Furthermore, we explored the trade-off between the hardware design complexity of such non-volatile scheme and its performance. This study establishes a viable pathway to a new generation of power-connection-free PPICs, providing a practical and scalable solution for future photonic systems.

The proportional-integral-derivative (PID) controller and its variants are widely used in control engineering, but they often rely on linearization around equilibrium points and empirical parameter tuning, making them ineffective for multi-input-multi-output (MIMO) systems with strong coupling, intense external disturbances, and high nonlinearity. Moreover, existing methods rarely explore the intrinsic stabilization mechanism of PID controllers for disturbed nonlinear systems from the perspective of modern robust control theories such as dissipativity and $\mathcal{L}_2$-gain. To address this gap, this study focuses on $\gamma$-dissipativity (partially equivalent to $\mathcal{L}_2$-gain) and investigates the optimal parameter tuning of MIMO-PI controllers for general disturbed nonlinear MIMO systems. First, by integrating dissipativity theory with the Hamilton-Jacobi-Isaacs (HJI) inequality, sufficient conditions for the MIMO-PI-controlled system to achieve $\gamma$-dissipativity are established, and the degree of $\gamma$-dissipativity in a local region containing the origin is quantified. Second, an optimal parameter tuning strategy is proposed, which reformulates the $\gamma$-dissipativity optimization problem into a class of standard eigenvalue problems (EVPs) and further converts it into linear matrix inequality (LMI) formulations for efficient online computation. Comprehensive simulation experiments validate the effectiveness and optimality of the proposed approach. This work provides a theoretical basis for the robust stabilization of general disturbed nonlinear MIMO systems and enriches the parameter tuning methods of PID controllers from the perspective of dissipativity.

Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This paper proposes a resolution-aware audio deepfake detection framework that explicitly models and aligns multi-resolution spectral representations through cross-scale attention and consistency learning. Unlike conventional single-resolution or implicit feature-fusion approaches, the proposed method enforces agreement across complementary time–frequency scales. The proposed framework is evaluated on three representative benchmarks: ASVspoof 2019 (LA and PA), the Fake-or-Real (FoR) dataset, and the In-the-Wild Audio Deepfake dataset under a speaker-disjoint protocol. The method achieves near-perfect performance on ASVspoof LA (EER 0.16%), strong robustness on ASVspoof PA (EER 5.09%), FoR rerecorded audio (EER 4.54%), and in-the-wild deepfakes (AUC 0.98, EER 4.81%), significantly outperforming single-resolution and non-attention baselines under challenging conditions. The proposed model remains lightweight and efficient, requiring only 159k parameters and less than 1~GFLOP per inference, making it suitable for practical deployment. Comprehensive ablation studies confirm the critical contributions of cross-scale attention and consistency learning, while gradient-based interpretability analysis reveals that the model learns resolution-consistent and semantically meaningful spectral cues across diverse spoofing conditions. These results demonstrate that explicit cross-resolution modeling provides a principled, robust, and scalable foundation for next-generation audio deepfake detection systems.

This paper presents a PDE-based auto-aggregation model for simulating descriptive norm dynamics in autonomous multi-agent systems, capturing convergence and violation through non-local perception kernels and external potential fields. Extending classical transport equations, the framework represents opinion popularity as a continuous distribution, enabling direct interactions without Bayesian guessing of beliefs. Applied to a real-world COVID-19 dataset from a major medical center, the experimental results demonstrate that: when clinical guidelines serve as a top-down constraint mechanism, it effectively generates convergence of novel descriptive norms consistent with the dataset; in the bottom-up experiment, potential field guidance successfully promotes the system's reconstruction of descriptive norms aligned with the dataset through violation-and-recoupling; whereas fully autonomous interaction leads to the emergence of multi-centric normative structures independent of the dataset.

This paper proposes a novel reinforcement learning framework, named Self-Organizing Dual-buffer Adaptive Clustering Experience Replay (SODACER), designed to achieve safe and scalable optimal control of nonlinear systems. The proposed SODACER mechanism consisting of a Fast-Buffer for rapid adaptation to recent experiences and a Slow-Buffer equipped with a self-organizing adaptive clustering mechanism to maintain diverse and non-redundant historical experiences. The adaptive clustering mechanism dynamically prunes redundant samples, optimizing memory efficiency while retaining critical environmental patterns. The approach integrates SODACER with Control Barrier Functions (CBFs) to guarantee safety by enforcing state and input constraints throughout the learning process. To enhance convergence and stability, the framework is combined with the Sophia optimizer, enabling adaptive second-order gradient updates. The proposed SODACER-Sophia's architecture ensures reliable, effective, and robust learning in dynamic, safety-critical environments, offering a generalizable solution for applications in robotics, healthcare, and large-scale system optimization. The proposed approach is validated on a nonlinear Human Papillomavirus (HPV) transmission model with multiple control inputs and safety constraints. Comparative evaluations against random and clustering-based experience replay methods demonstrate that SODACER achieves faster convergence, improved sample efficiency, and a superior bias-variance trade-off, while maintaining safe system trajectories, validated via the Friedman test.