Papers

Integrated sensing and communication (ISAC) through Zak-transform-based orthogonal time frequency space (Zak-OTFS) modulation is a promising solution for high-mobility scenarios. Realizing accurate bistatic sensing and robust communication necessitates precise channel estimation; however, this remains a formidable challenge in doubly dispersive environments, where fractional delay-Doppler shifts induce severe channel spreading. This paper proposes a semi-blind atomic norm denoising scheme for Zak-OTFS ISAC with bistatic sensing. We first derive the discrete-time input-output (I/O) relationship of Zak-OTFS under fractional delay-Doppler shifts and rectangular windowing. Based on this I/O relation, we formulate the joint channel parameter estimation and data detection task as an atomic norm denoising problem, utilizing the negative square penalty method to handle the non-convex discrete constellation constraints. To solve this problem efficiently, we develop an accelerated iterative algorithm that integrates majorization-minimization, accelerated projected gradient, and inexact accelerated proximal gradient methods. We provide a rigorous convergence proof for the proposed algorithm. Simulation results demonstrate that the proposed scheme achieves super-resolution sensing accuracy and communication performance approaching the perfect channel state information lower bound.

This paper presents a sub-switching period current-limiting control for a grid-tied inverter to prevent transient overcurrents during grid faults and enable seamless fault ride-through (FRT). Sudden grid-voltage disturbances, such as voltage sags or phase jumps, can induce large transient currents within a switching period, particularly at low switching frequencies. Upon disturbance detection, the proposed method immediately modifies the pulse-width modulation carrier, enabling continuous regulation of the inverter output current within a time much shorter than a switching period without interrupting current flow. The proposed method can be implemented on commonly used digital signal processors without requiring specialized analog or digital circuits or high-speed computing devices. Experimental results from a 2-level, 3-phase inverter switching at 3.6 kHz validate the effectiveness of the proposed method under symmetric and asymmetric voltage sags and phase jumps.

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model's implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios.

Supervised machine learning frameworks rely on extensive labeled datasets for robust performance on real-world tasks. However, there is a lack of large annotated datasets in audio and music domains, as annotating such recordings is resource-intensive, laborious, and often require expert domain knowledge. In this work, we explore the use of label propagation (LP), a graph-based semi-supervised learning technique, for automatically labeling the unlabeled set in an unsupervised manner. By constructing a similarity graph over audio embeddings, we propagate limited label information from a small annotated subset to a larger unlabeled corpus in a transductive, semi-supervised setting. We apply this method to two tasks in Indian Art Music (IAM): Raga identification and Instrument classification. For both these tasks, we integrate multiple public datasets along with additional recordings we acquire from Prasar Bharati Archives to perform LP. Our experiments demonstrate that LP significantly reduces labeling overhead and produces higher-quality annotations compared to conventional baseline methods, including those based on pretrained inductive models. These results highlight the potential of graph-based semi-supervised learning to democratize data annotation and accelerate progress in music information retrieval.

Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADD), moving beyond black-box classifiers by providing transparency to their predictions via reasoning traces. However, such reasoning may not support the model predictions, reflecting poor coherence, or, worse, may rationalize incorrect predictions with plausible but misleading explanation. Moreover, the behavior of ALM reasoning under adversarial attacks remains under-explored, raising questions about the practical reliability of such explanation capabilities. To address this gap, this study introduces SARA (Shift Analysis of Reasoning in Audio), a diagnostic framework that evaluates ALM reasoning across three dimensions: acoustic perception, reasoning-verdict coherence and dissonance. We test five open-source ALMs against both acoustic and linguistic adversarial attacks. We show that acoustic attacks significantly degrade reasoning-verdict coherence (average decrease of 14.20%), frequently inducing internal logical conflicts. Conversely, linguistic attacks achieve higher attack success rates while maintaining reasoning coherence. We further demonstrate that the textual coherence of generated reasoning traces also serves as a latent indicator of adversarial inputs, enabling effective detection of perturbed audio (0.78 in F1) without accessing the raw acoustic signal. These findings suggest that reasoning traces provide diagnostic utility that persists even when final classification outputs are compromised.

This monograph addresses the "Missing Middle" problem in AI music generation - the challenge of producing coherent, phrase-level musical structure. Using Beethoven's piano sonatas as a case study, I introduce the Smart Embedding architecture, a factorized representation grounded in the empirically verified independence of pitch and hand attributes (NMI=0.167). The architecture achieves a 48.3% reduction in embedding parameters while improving validation loss by 9.47%. Theoretically, I establish formal guarantees through information theory, Rademacher complexity analysis (yielding a 28.09% tighter generalization bound), and category-theoretic interpretation. These results are further supported by Singular Value Decomposition analysis and a blind expert listening study (N=53). Collectively, this work presents a dual contribution that combines architectural innovation with mathematical rigor, offering a principled framework for building more efficient, stable, and interpretable generative models for complex sequential data.

Respiratory sounds captured via auscultation contain critical clues for diagnosing pulmonary conditions. Automated classification of these sounds faces challenges due to subtle acoustic differences and severe class imbalance in clinical datasets. This study investigates respiratory sound classification with a focus on mitigating pronounced class imbalance. We propose a hybrid deep learning model that combines a Long Short-Term Memory (LSTM) network for sequential feature encoding with a Kolmogorov-Arnold Network (KAN) for classification. The model is integrated with a comprehensive feature extraction pipeline and targeted imbalance mitigation strategies. Experiments were conducted on a public respiratory sound database comprising six classes with a highly skewed distribution. Techniques such as focal loss, class-specific data augmentation, and Synthetic Minority Over-sampling Technique (SMOTE) were employed to enhance minority class recognition. The proposed Hybrid LSTM-KAN model achieves an overall accuracy of 94.6 percent and a macro-averaged F1 score of 0.703, despite the dominant COPD class accounting for over 86 percent of the data. Improved detection performance is observed for minority classes compared to baseline approaches, demonstrating the effectiveness of the proposed architecture for imbalanced respiratory sound classification.

In 6G mobile communications, acquiring accurate and timely channel state information (CSI) becomes increasingly challenging due to the growing antenna array size and bandwidth. To alleviate the CSI feedback burden, the channel knowledge map (CKM) has emerged as a promising approach by leveraging environment-aware techniques to predict CSI based solely on user locations. However, how to effectively construct a CKM remains an open issue. In this paper, we propose F$^4$-CKM, a novel CKM construction framework characterized by four distinctive features: radiance Field rendering, spatial-Frequency-awareness, location-Free usage, and Fast learning. Central to our design is the adaptation of radiance field rendering techniques from computer vision to the radio frequency (RF) domain, enabled by a novel Wireless Radiator Representation (WiRARE) network that captures the spatial-frequency characteristics of wireless channels. Additionally, a novel shaping filter module and an angular sampling strategy are introduced to facilitate CKM construction. Extensive experiments demonstrate that F$^4$-CKM significantly outperforms existing baselines in terms of wireless channel prediction accuracy and efficiency.

Physical reservoir computing leverages the intrinsic dynamics of mechanical systems to perform computation through their natural responses to input signals. Here, we study a compliant fiber network inspired by orb-weaving spider webs and investigate how its mechanical design and operating conditions shape its computational capability. Using Cosserat rod-based simulations, we identify how network topology, geometry, actuation, and axial tension impact the nonlinear computation and memory capacity of the network. We further evaluate several readout reduction strategies to assess how computational performance varies with the number and placement of measured outputs. We then experimentally validate these results using a physical fiber-network prototype. Overall, results provide insights and guidance on design, actuation, and sensing choices to enable fiber networks for mechano-intelligent computation. They demonstrate the ability of structured compliant fibers networks to serve as physical reservoirs capable of nonlinear transformation and input-history retention.

Integrated sensing and communication (ISAC) is envisioned to be one of the key usage scenarios for the sixth generation (6G) mobile communication networks. While significant progresses have been achieved for the theoretical studies, the further advancement of ISAC is hampered by the lack of accessible, open-source, and real-time experimental platforms. To address this gap, we introduce OpenISAC, a versatile and high-performance open-source platform for real-time ISAC experimentation. OpenISAC utilizes orthogonal frequency division multiplexing (OFDM) waveform and implements crucial sensing functionalities, including both monostatic and bistatic delay-Doppler sensing. A key feature of our platform is a novel over-the-air (OTA) synchronization mechanism that enables robust bistatic operations without requiring a wired connection between nodes. The platform is built entirely on open-source software, leveraging the universal software radio peripheral (USRP) hardware driver (UHD) library, thus eliminating the need for any commercial licenses. It supports a wide range of software-defined radios, from the cost-effective USRP B200 series to the high-performance X400 series. The physical layer modulator and demodulator are implemented with C++ for high-speed processing, while the sensing data is streamed to a Python environment, providing a user-friendly interface for rapid prototyping and validation of sensing signal processing algorithms. With flexible parameter selection and real-time communication and sensing operation, OpenISAC serves as a powerful and accessible tool for the academic and research communities to explore and innovate within the field of OFDM-ISAC.

Cross-Phase Modulation (XPM), a critical nonlinear effect in long-haul optical communication systems utilizing Wavelength Division Multiplexing (WDM), is significantly influenced by intensity fluctuations (IFs) originating from the transmitted signal and altered by chromatic dispersion. A linear model is employed to characterize the growth of intensity fluctuations along the transmission path, demonstrating that these fluctuations are sufficient to predict the spectral characteristics of XPM on an adjacent channel. A direct correlation between frequency-domain IF growth and XPM-induced phase distortions is established and analyzed. Furthermore, the impact of XPM on the bit error ratio (BER) is shown to be analytically predictable. These analytical predictions align closely with results obtained from full nonlinear simulations. Results reveal that the evolution of IFs, especially at lower frequencies, has a pronounced effect on the XPM phase fluctuation spectra and overall phase variance. Validation through simulation confirms the model's accuracy in predicting XPM-induced phase fluctuation spectra and variance under various system configurations. These findings highlight the necessity of accounting for frequency-domain IF evolution during signal propagation in order to accurately model XPM-induced impairments, offering valuable guidance for the optimization and design of advanced optical communication systems.

Synthetic aperture radar (SAR) image generation can mitigate data scarcity, but controllablegeneration under sparse observation angles remains difficult. Recent SAR generative studies im-prove texture realism, yet explicit geometry-aware control is still limited. This paper studiesthe focused and verifiable setting of intermediate-azimuth completion: 3D-model-derived geo-metric priors guide a diffusion model to synthesize the views missing from sparse-angle trainingdata. GeoDiff-SAR constructs a lightweight multi-bounce ray-tracing prior, encodes the result-ing point cloud, and fuses it with text conditioning while adapting Stable Diffusion 3.5 Mediumthrough low-rank adaptation. On a real four-category aircraft dataset, GeoDiff-SAR reaches anSSIM of 0.812 and azimuth consistency of 0.940, compared with 0.738 and 0.782 for the text-conditioned SD3.5 Medium baseline. The same sparse-angle protocol on five MSTAR vehicleclasses yields an SSIM of 0.878 and azimuth consistency of 0.917. These results support theconclusion that a lightweight 3D geometric prior improves viewpoint adherence for controllableSAR generation; it is intended as generation guidance rather than high-fidelity electromagneticreconstruction.

Modern microgrids depend on distributed sensing and communication interfaces, making them increasingly vulnerable to cyber physical disturbances that threaten operational continuity and equipment safety. In this work, a complete virtual microgrid was designed and implemented in MATLAB/Simulink, integrating heterogeneous renewable sources and secondary controller layers. A structured cyberattack framework was developed using MGLib to inject adversarial signals directly into the secondary control pathways. Multiple attack classes were emulated, including ramp, sinusoidal, additive, coordinated stealth, and denial of service behaviors. The virtual environment was used to generate labeled datasets under both normal and attack conditions. The datasets trained Light Gradient Boosting Machine (LightGBM) models to perform two functions: detecting the presence of an intrusion (binary) and distinguishing among attack types (multiclass). The multiclass model attained 99.72% accuracy and a 99.62% F1 score, while the binary model attained 94.8% accuracy and a 94.3% F1 score. A knowledge-distillation step reduced the size of the multiclass model, allowing faster predictions with only a small drop in performance. Real-time tests showed a processing delay of about 54 to 67 ms per 1000 samples, demonstrating suitability for CPU-based edge deployment in microgrid controllers. The results confirm that lightweight machine learning based intrusion detection methods can provide fast, accurate, and efficient cyberattack detection without relying on complex deep learning models. Key contributions include: (1) development of a complete MATLAB-based virtual microgrid, (2) structured attack injection at the control layer, (3) creation of multiclass labeled datasets, and (4) design of low-cost AI models suitable for practical microgrid cybersecurity.

The National Synchrotron Light Source II (NSLS-II) uses highly stable electron beam to produce high-quality X-ray beams with high brightness and low-emittance synchrotron radiation. The traditional algorithm to stabilize the beam applies singular value decomposition (SVD) on the orbit response matrix to remove noise and extract actions. Supervised learning has been studied on NSLS-II storage ring stabilization and other accelerator facilities recently. Several problems, for example, machine status drifting, environment noise, and non-linear accelerator dynamics, remain unresolved in the SVD-based and supervised learning algorithms. To address these problems, we propose an adaptive training framework based on model-based reinforcement learning. This framework consists of two types of optimizations: trajectory optimization attempts to minimize the expected total reward in a differentiable environment, and online model optimization learns non-linear machine dynamics through the agent-environment interaction. Through online training, this framework tracks the internal status drifting in the electron beam ring. Simulation and real in-facility experiments on NSLS-II reveal that our method stabilizes the beam position and minimizes the alignment error, defined as the root mean square (RMS) error between adjusted beam positions and the reference position, down to ~1$\mu$m.

Vehicle-to-building (V2B) systems integrate physical infrastructures, such as smart buildings and electric vehicles (EVs) connected to chargers at the building, with digital control mechanisms to manage energy use. By utilizing EVs as flexible energy reservoirs, buildings can dynamically charge and discharge them to optimize energy use and cut costs under time-variable pricing and demand charge policies. This setup leads to the V2B optimization problem, where buildings coordinate EV charging and discharging to minimize total electricity costs while meeting users' charging requirements. However, the V2B optimization problem is challenging because of: (1) fluctuating electricity pricing, which includes both energy charges ($/kWh) and demand charges ($/kW); (2) long planning horizons (typically over 30 days); (3) heterogeneous chargers with varying charging rates, controllability, and directionality (i.e., unidirectional or bidirectional); and (4) user-specific battery levels at departure to ensure user requirements are met. In contrast to existing approaches that often model this setting as a single-shot combinatorial optimization problem, we highlight critical limitations in prior work and instead model the V2B optimization problem as a Markov decision process (MDP), i.e., a stochastic control process. Solving the resulting MDP is challenging due to the large state and action spaces. To address the challenges of the large state space, we leverage online search, and we counter the action space by using domain-specific heuristics to prune unpromising actions. We validate our approach in collaboration with Nissan Advanced Technology Center - Silicon Valley. Using data from their EV testbed, we show that the proposed framework significantly outperforms state-of-the-art methods.

Prompt tuning has achieved remarkable progress in vision-language models (VLMs) and is recently being adopted for audio-language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that conventional prompt tuning for ALMs also suffers from the Base-New Tradeoff, and we identify that this issue stems from the disrupted semantic structure of the embedding space. To address this issue, we propose Semantically Expanded Prompt Tuning (SEPT)-a plug-and-play framework that explicitly regularizes the prompt embedding space by incorporating semantic neighbors generated by large language models. SEPT introduces a novel semantic expansion loss with margin constraints that promote intra-class compactness and inter-class separability, thereby enhancing the semantic structure of the prompt embedding space. For comprehensive evaluation, we establish the first benchmark setup for prompt generalization in ALMs, covering both base-to-new generalization and cross-dataset transferability. Extensive experiments demonstrate that SEPT consistently improves generalization performance across multiple prompt tuning baselines, while maintaining computational cost during inference.

Most Integrated Sensing and Communications (ISAC) systems require dividing airtime across their two modes. However, the specific impact of this decision on sensing performance remains unclear and underexplored. In this paper, we therefore investigate the impact on a gesture recognition system using a Millimeter-Wave (mmWave) ISAC system. With our dataset of power per beam pair gathered with two mmWave devices performing constant beam sweeps while test subjects performed distinct gestures, we train a gesture classifier using Convolutional Neural Networks. We then subsample these measurements, emulating reduced sensing airtime, showing that a sensing airtime of 25 % only reduces classification accuracy by 0.15 percentage points from full-time sensing. Alongside this high-quality sensing at low airtime, mmWave systems are known to provide extremely high data throughputs, making mmWave ISAC a prime enabler for applications such as truly wireless Extended Reality.

Resiliency has garnered attention in the management of critical infrastructure as a metric of system performance, but there are significant roadblocks to its implementation in a realistic decision-making framework. Contrasted to risk and reliability, which have robust quantification approaches and undergird many regulatory approaches to system safety (e.g., "risk-informed decision-making"), resiliency is a diffuse, qualitatively-understood characteristic, often treated differently or distinctly. However, in the emerging context of highly-complex, highly-interdependent critical systems, the idea of reliability (as the probability of non-failure) may not be an appropriate metric of system health. As a result, focus is shifting towards resiliency-centered approaches that value the response to failure as much as the avoidance of failure. Supporting this approach requires a robustly-defined, quantitative understanding of resiliency. In this paper, we explore the foundations of reliability and resiliency engineering, and propose an approach to resiliency-informed decision-making bolstered by a quantitative understanding of resiliency.

High altitude platform station (HAPS) systems are becoming crucial facilitators for future wireless communication networks, enhancing connectivity across all vertical communication layers, including small Internet of Things (IoT) sensors and devices, terrestrial users, and aerial devices. In the context of the widely recognized vertical heterogeneous network (VHetNet) architecture, HAPS systems can provide service to both aerial and ground users. However, integrating HAPS systems as a core element in the VHetNet architecture presents a considerable energy challenge, marking a prominent constraint for their operation. Driven by this challenge, we introduce an energy harvesting (EH) strategy tailored for HAPS systems, enabling a HAPS system to gather energy from another HAPS system, which is not constrained by energy limitations. To assess the performance capabilities of the proposed model, we derive outage probability (OP), ergodic capacity (EC) and verify them by using Monte Carlo (MC) simulations. Moreover, we explore the system in terms of throughput. The findings reveal that harnessing full potential of EH stands as a viable approach to meet the energy demands of HAPS systems.

Decision-making under uncertainty is central to many safety-critical applications, where decisions must be guided by probabilistic modeling formalisms. This paper introduces a novel approach to policy synthesis in multi-objective interval Markov decision processes using polyhedral Lyapunov functions. Unlike previous Lyapunov-based methods that mainly rely on quadratic functions, our method utilizes polyhedral functions to enhance accuracy in managing uncertainties within value iteration of dynamic programming. We reformulate the value iteration algorithm as a switched affine system with interval uncertainties and apply control-theoretic stability principles to synthesize policies that guide the system toward a desired target set. By constructing an invariant set of attraction, we ensure that the synthesized policies provide convergence guarantees while minimizing the impact of transition uncertainty in the underlying model. Our methodology removes the need for computationally intensive Pareto curve computations by directly determining a policy that brings objectives within a specified range of their target values. We validate our approach through numerical case studies, including a recycling robot and an electric vehicle battery, demonstrating its effectiveness in achieving policy synthesis under uncertainty.

Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution (ADSR), producing perceptually convincing wideband audio from narrowband inputs. However, existing evaluations primarily rely on signal-level or perceptual metrics, leaving open the question of how closely the distributions of synthetic super-resolved and real wideband audio match. Here we address this problem by analyzing the separability of real and super-resolved audio in various embedding spaces. We consider both middle-band ($4\to 16$~kHz) and full-band ($16\to 48$~kHz) upsampling tasks for speech and music, training linear classifiers to distinguish real from synthetic samples based on multiple types of audio embeddings. Comparisons with objective metrics and subjective listening tests reveal that embedding-based classifiers achieve near-perfect separation, even when the generated audio attains high perceptual quality and state-of-the-art metric scores. This behavior is consistent across datasets and models, including recent diffusion-based approaches, highlighting a persistent gap between perceptual quality and true distributional fidelity in ADSR models.

Inspired by the success of performing multiple local optimization steps between communication rounds in federated learning, incorporating such local updates into distributed optimization has recently attracted growing interest. However, unlike federated learning, where local updates can accelerate training by reducing gradient estimation error under minibatch settings, it remains unclear whether similar benefits persist when exact gradients are available. Moreover, existing theoretical results typically require reducing the step size when multiple local updates are employed, which can entirely offset any potential benefit of these additional local updates. In this paper, we focus on the classic DIGing algorithm and leverage the tight performance bounds provided by Performance Estimation Problems (PEP) to show that incorporating local updates can indeed accelerate distributed optimization. To the best of our knowledge, this is the first rigorous demonstration of such acceleration for a broad class of objective functions. Our analysis further reveals that, under an appropriate step size, performing only two local updates is sufficient to achieve the maximal possible improvement, and that additional local updates provide no further gains. Because more updates increase computational cost, these findings offer practical guidance for efficient implementation. We also show that these speed gains depend critically on the network structure, with sparser or less connected graphs, characterized by the spectral properties of the mixing matrix, yielding smaller improvements. Extensive experiments on both synthetic and real-world datasets corroborate the theoretical findings.

The deployment of extremely large aperture arrays (ELAAs) in sixth-generation (6G) networks is expected to shift communications into the near-field regime, where spherical-wave propagation enables distance-aware beamfocusing but remains highly vulnerable to physical blockages that cause non-line-of-sight (NLoS) conditions. To resolve this inherent vulnerability, reconfigurable intelligent surfaces (RIS) can be utilized to circumvent these blockages and effectively establish reliable NLoS communication links. In envisioned deployment scenarios, accurately acquiring instantaneous CSI and predicting sudden blockages is profoundly challenging due to the prohibitive pilot overhead associated with massive passive arrays and the unpredictable mobility of environmental scatterers. To address this, we propose the Dual-Transformer Hierarchical Deep Reinforcement Learning (DT-HDRL) framework, which integrates two specialized transformer models with a two-timescale hierarchical control agent. The first transformer integrates a ray-tracing digital twin prior with distance-aware geometric correction features to yield rapid and precise CSI estimates, while a complementary vision transformer (ViT) processes sequential camera frames to forecast impending blockages prior to link degradation. These predictive outputs are then fed directly into the hierarchical control agent. Within this architecture, a high-level controller processes the slow-timescale blockage predictions to jointly dictate the user transmission path (line-of-sight (LoS) or RIS-assisted NLoS) and RIS active/sleep scheduling, whereas a low-level controller employs the fast-timescale CSI estimates to perform joint base station (BS) beamfocusing and RIS phase-shift optimization.

This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that can be processed by Neural Networks, extracting its spatial features and producing novel decentralized motion control rules. We evaluate our approach on a multi-agent convergence task of agents with limited-range and bearing-only sensing that aim to keep the swarm cohesive during the aggregation. The algorithm's performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures convergence but progresses slowly, and VariAntNet, a neural network-based framework that converges much faster but shows medium success rates in hard constellations. Our method achieves high convergence, with a pace nearly matching that of VariAntNet. In some scenarios, it serves as the only practical alternative.

Molecular subtyping of PDAC into basal-like and classical has established prognostic and predictive value. However, its use in clinical practice is limited by cost, turnaround time, and tissue requirements, thereby restricting its application in the management of PDAC. We introduce PanSubNet, an interpretable deep learning framework that predicts therapy-relevant molecular subtypes directly from standard H&E-stained WSIs. PanSubNet was developed using data from 1,055 patients across two multi-institutional cohorts (PANCAN, n=846; TCGA, n=209) with paired histology and RNA-seq data. Ground-truth labels were derived using the validated Moffitt 50-gene signature refined by GATA6 expression. The model employs dual-scale architecture that fuses cellular-level morphology with tissue-level architecture, leveraging attention mechanisms for multi-scale representation learning and transparent feature attribution. On internal validation within PANCAN using five-fold cross-validation, PanSubNet achieved mean AUC of 88.5% with balanced sensitivity and specificity. External validation on the independent TCGA cohort without fine-tuning demonstrated robust generalizability (AUC 84.0%). PanSubNet preserved and, in metastatic disease, strengthened prognostic stratification compared to RNA-seq based labels. Prediction uncertainty linked to intermediate transcriptional states, not classification noise. Model predictions are aligned with established transcriptomic programs, differentiation markers, and DNA damage repair signatures. By enabling rapid, cost-effective molecular stratification from routine H&E-stained slides, PanSubNet offers a clinically deployable and interpretable tool for genetic subtyping. We are gathering data from two institutions to validate and assess real-world performance, supporting integration into digital pathology workflows and advancing precision oncology for PDAC.

Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. Large pre-trained text-conditioned image editing models encode rich priors about image structure, quality, and degradation, yet we find that this knowledge does not, on its own, make them restorers: state-of-the-art editing models largely fail at restoration in the zero-shot regime. We show that what these priors lack is not capability but direction, and that a small amount of parameter-efficient adaptation supplies it. Fine-tuning LoRA adapters on FLUX.1 Kontext, a 12B-parameter flow matching model for image-to-image translation, with only 32–128 paired images per task and guided by simple text prompts, we turn a mediocre zero-shot editor into a competitive restorer. A single unified adapter, conditioned on task-specific prompts, handles five diverse degradations. Despite using three to four orders of magnitude less data, our few-shot model surpasses a recent restoration baseline trained on over a million curated pairs on the majority of perceptual and distribution-level metrics, on which we evaluate in keeping with our focus on perceptual rather than pixel-fidelity quality. Through comprehensive studies, we analyze the impact of training-set size, the trade-off between task-specific and unified multi-task adapters, the effect of text encoder adaptation, and zero-shot baseline performance, establishing pre-trained editing models as a compelling, data-efficient foundation for few-shot, prompt-guided image restoration.

In this paper, the average symbol error probability (SEP) of a phase-quantized single-input multiple-output (SIMO) system with M-ary phase-shift keying (PSK) modulation is analyzed under Rayleigh fading and additive white Gaussian noise. By leveraging a novel method, we derive exact SEP expressions for a quadrature PSK (QPSK)-modulated n-bit phase-quantized SIMO system with maximum ratio combining (SIMO-MRC), along with the corresponding high signal-to-noise ratio (SNR) characterizations in terms of diversity and coding gains. For a QPSK-modulated 2-bit phase-quantized SIMO system with selection combining, the diversity and coding gains are further obtained for an arbitrary number of receive antennas, complementing existing results. Interestingly, the proposed method also reveals a duality between a SIMO-MRC system and a phase-quantized multiple-input single-output (MISO) system with maximum ratio transmission, when the modulation order, phase-quantization resolution, antenna configuration, and the channel state information (CSI) conditions are reciprocal. This duality enables direct inference to obtain the diversity of a general M-PSK-modulated n-bit phase-quantized SIMO-MRC system, and extends the results to its MISO counterpart. All the above results have been obtained assuming perfect CSI at the receiver (CSIR). Finally, the SEP analysis of a QPSK-modulated 2-bit phase-quantized SIMO system is extended to the limited CSIR case, where the CSI at each receive antenna is represented by only 2 bits of channel phase information. In this scenario, the diversity gain is shown to be further halved in general.

Unmanned aerial vehicle (UAV) with slung load system is a classic air transportation system. In practical applications, the suspension point of the slung load does not always align with the center of mass (CoM) of the UAV due to mission requirements or mechanical interference. This offset creates coupling in the system's nonlinear dynamics which leads to a complicated motion control problem. In existing research, modeling of the system are performed about the UAV's CoM. In this work we use the point of suspension instead. Based on the new model, a cascade control strategy is developed. In the middle-loop controller, the acceleration of the suspension point is used to regulate the swing angle of the slung load without the need for considering the coupling between the slung load and the UAV. An inner-loop controller is designed to track the UAV's attitude without the need of simplification on the coupling effects. We prove local exponential stability of the closed-loop using Lyapunov approach. Finally, simulations and experiments are conducted to validate the proposed control system.

Continuous-time state estimation has been shown to be an effective means of (i) handling asynchronous and high-rate measurements, (ii) introducing smoothness to the estimate, (iii) post hoc querying the estimate at times other than those of the measurements, and (iv) addressing certain observability issues related to scanning-while-moving sensors. A popular means of representing the trajectory in continuous time is via a Gaussian process (GP) prior, with the prior's mean and covariance functions generated by a linear time-varying (LTV) stochastic differential equation (SDE) driven by white noise. When the state comprises elements of Lie groups, previous works have resorted to a patchwork of local GPs each with a linear time-invariant SDE kernel, which while effective in practice, lacks theoretical elegance. Here we revisit the full LTV GP approach to continuous-time trajectory estimation, deriving a global GP prior on Lie groups via the Magnus expansion, which offers a more elegant and general solution. We provide a numerical comparison between the two approaches and discuss their relative merits.

Artificial muscles are essential for compliant musculoskeletal robotics but complicate control due to nonlinear multiphysics dynamics. Hydraulically amplified electrostatic (HASEL) actuators, a class of soft artificial muscles, offer high performance but exhibit memory effects and hysteresis. Here we present a data-driven reduction and control strategy grounded in spectral submanifold (SSM) theory. In the adiabatic regime, where inputs vary slowly relative to intrinsic transients, trajectories rapidly converge to a low-dimensional slow manifold. We learn an explicit input-to-output map on this manifold from forced-response trajectories alone, avoiding decay experiments that can trigger hysteresis. We deploy the SSM-based model for real-time control of an antagonistic HASEL-clutch joint. This approach yields a substantial reduction in tracking error compared to feedback-only and feedforward-only baselines under identical settings. This record-and-control workflow enables rapid characterization and high-performance control of soft muscles and muscle-driven joints without detailed physics-based modeling.