Papers

Hyperspectral single image super-resolution (SISR) aims to enhance spatial resolution while preserving the rich spectral information of hyperspectral images. Most existing methods rely on supervised learning with high-resolution ground truth data, which is often unavailable in practice. To overcome this limitation, we propose an unsupervised learning approach based on synthetic abundance data. The hyperspectral image is first decomposed into endmembers and abundance maps through hyperspectral unmixing. A neural network is then trained to super-resolve these maps using data generated with the dead leaves model, which replicates the statistical properties of real abundances. The final super-resolution hyperspectral image is reconstructed by recombining the super-resolved abundance maps with the endmembers. Experimental results demonstrate the effectiveness of our method and the relevance of synthetic data for training.

For low-semantic sensor signals from human activity recognition (HAR), contrastive learning (CL) is essential to implement novel applications or generic models without manual annotation, which is a high-performance self-supervised learning (SSL) method. However, CL relies heavily on data augmentation for pairwise comparisons. Especially for low semantic data in the HAR area, conducting good performance augmentation strategies in pretext tasks still rely on manual attempts lacking generalizability and flexibility. To reduce the augmentation burden, we propose an end-to-end auto-augmentation contrastive learning (AutoCL) method for wearable-based HAR. AutoCL is based on a Siamese network architecture that shares the parameters of the backbone and with a generator embedded to learn auto-augmentation. AutoCL trains the generator based on the representation in the latent space to overcome the disturbances caused by noise and redundant information in raw sensor data. The architecture empirical study indicates the effectiveness of this design. Furthermore, we propose a stop-gradient design and correlation reduction strategy in AutoCL to enhance encoder representation learning. Extensive experiments based on four wide-used HAR datasets demonstrate that the proposed AutoCL method significantly improves recognition accuracy compared with other SOTA methods.

We investigate the role of scatter reducing agents in a continuous wave (CW) near infrared (NIR)reflectance mode imaging setting. We use food-grade dye Tartrazine as a scatter reducing agent to enhance depth sensitivity and weak-absorber detectability in CW diffuse reflectance measurements. We found that reflectance signal was enhanced when the dye was applied on chicken breast phantom. However, we saw reduced reflectance sensitivity when the dye was uniformly dissolved in intralipid phantom which is a commonly used for NIR imaging studies. This shows that the gradient of refractive index modulation created as the dye diffuses from the top layer allows increased reflectance signal sensitivity of optical photons. However, when the scatter reduction is uniform throughout the phantom (like in intralipid phantom), the improved reflectance sensitivity was not observed. Our study points to significant redistribution of photons with scatter modulation with Tartrazine dye. We show significant improvement in sensitivity to signals with reflectance imaging. To elucidate the underlying mechanism of dye induced scatter reduction in tissue, analytical diffusion models and Monte Carlo simulations were employed. Modeling results show the impact of refractive index gradient created due to dye diffusion in enhancing reflectance sensitivity. These findings demonstrate that dye induced scatter reduction provides a practical, low-complexity approach to improving depth sensitivity in CW diffuse reflectance measurements and extend the functional capabilities of CW-NIRS systems for deep-tissue sensing applications. Our preliminary studies shows up to five fold enhancement in signal sensitivity for signals between two and three cm depth.

Metric temporal logic (MTL) provides a formal framework for defining time-dependent mission requirements on autonomous vehicles. However, optimizing control decisions subject to these constraints is often computationally expensive. This article presents a method that uses reachability analysis to implicitly express the set of states satisfying an MTL specification and then optimizes to find a motion plan. The hybrid zonotope set representation is used to efficiently and conveniently encode MTL specifications into reachable sets. A numerical benchmark highlights the proposed method's computational advantages as compared to existing methods in the literature. Further numerical examples and an experimental application demonstrate the ability to address time-varying environments, region-dependent disturbances, and multi-agent coordination.

Synchronization over the special Euclidean group SE(3) aims to recover absolute poses from noisy pairwise relative transformations and is a core primitive in robotics and 3D vision. Standard approaches often require multi-step heuristic procedures to recover valid poses, which are difficult to analyze and typically lack theoretical guarantees. This paper adopts a dual quaternion representation and formulates SE(3) synchronization directly over the unit dual quaternion. A two-stage algorithm is developed: A spectral initializer computed via the power method on a Hermitian dual quaternion measurement matrix, followed by a dual quaternion generalized power method (DQGPM) that enforces feasibility through per-iteration projection. The estimation error bounds are established for spectral estimators, and DQGPM is shown to admit a finite-iteration error bound and achieves linear error contraction up to an explicit noise-dependent threshold. Experiments on synthetic benchmarks and real-world multi-scan point-set registration demonstrate that the proposed pipeline improves both accuracy and efficiency over representative matrix-based methods.

The rapid advances in text-to-speech (TTS) technologies have made audio deepfakes increasingly realistic and accessible, raising significant security and trust concerns. While existing research has largely focused on detecting single-speaker audio deepfakes, real-world malicious applications with multi-speaker conversational settings is also emerging as a major underexplored threat. To address this gap, we propose a conceptual taxonomy of multi-speaker conversational audio deepfakes, distinguishing between partial manipulations (one or multiple speakers altered) and full manipulations (entire conversations synthesized). As a first step, we introduce a new Multi-speaker Conversational Audio Deepfakes Dataset (MsCADD) of 2,830 audio clips containing real and fully synthetic two-speaker conversations, generated using VITS and SoundStorm-based NotebookLM models to simulate natural dialogue with variations in speaker gender, and conversational spontaneity. MsCADD is limited to text-to-speech (TTS) types of deepfake. We benchmark three neural baseline models; LFCC-LCNN, RawNet2, and Wav2Vec 2.0 on this dataset and report performance in terms of F1 score, accuracy, true positive rate (TPR), and true negative rate (TNR). Results show that these baseline models provided a useful benchmark, however, the results also highlight that there is a significant gap in multi-speaker deepfake research in reliably detecting synthetic voices under varied conversational dynamics. Our dataset and benchmarks provide a foundation for future research on deepfake detection in conversational scenarios, which is a highly underexplored area of research but also a major area of threat to trustworthy information in audio settings. The MsCADD dataset is publicly available to support reproducibility and benchmarking by the research community.

Near infrared diffuse optical imaging can be performed in reflectance and transmission mode and relies on physical models along with measurements to extract information on changes in chromophore concentration. Continuous-wave near-infrared diffuse optical imaging relies on accurate differential pathlength factors (DPFs) for quantitative chromophore estimation. Existing DPF definitions inherit formulation-dependent limitations that can introduce large errors in modified Beer–Lambert law analyses. These errors are significantly higher at smaller source-detector separations in a reflectance mode of measurement. This minimizes their applicability in situations where large area detection is used and also when signal depth is varying. Using Monte Carlo simulations, we derive two distance- and property-dependent DPF models one ideal and one experimentally practical and benchmark them against standard formulations. The proposed models achieve errors below 10 percent across broad optical conditions, whereas conventional DPFs can exceed 100 percent error. The theoretical predictions are further validated using controlled phantom experiments, demonstrating improved quantitative accuracy in CW-NIR imaging.

Speech Language Models (SpeechLMs) are increasingly deployed for streaming speech generation, where audio playback must start quickly and never stall. Serving them requires running two very different model components on the same system. An autoregressive LLM backbone emits audio tokens, and a codec converts chunks of those tokens into waveforms. Existing systems run the two as separately scheduled stages, and therefore either serialize them, let them interfere, or strand capacity by placing them on separate devices. We observe that overlapping the backbone and the codec on separate parts of the GPU raises throughput. Although this increases codec latency, most chunks can tolerate it, as long as it neither lies on the critical path of time-to-first-audio (TTFA) nor causes a playback stall. Based on this insight, we present VoxServe, a SpeechLM serving system that allocates GPU resources according to the urgency of chunks. VoxServe executes work on three asynchronous lanes. The LM lane runs the backbone on a large partition of the GPU's streaming multiprocessors, the background codec lane runs on a small partition beside it, and the urgent lane uses the whole GPU. The scheduler queues each request to the LM lane and routes every chunk the backbone completes by its urgency. A request's first chunk and chunks close to their playback deadline go to the urgent lane, and the rest are batched on the background lane. On Qwen3-TTS, VoxServe sustains 1.5x the request rate of the best existing system at a 200ms TTFA target without playback stalls. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.

Magnetic Resonance Imaging (MRI) is a crucial imaging modality for viewing internal body structures. This research work analyses the performance of popular GAN models for accurate and precise MRI reconstruction by enhancing image quality and improving diagnostic accuracy. Three GAN architectures considered in this study are Vanilla GAN, Deep Convolutional GAN (DCGAN), and Wasserstein GAN (WGAN). They were trained and evaluated using knee, brain, and cardiac MRI datasets to assess their generalizability across body regions. While the Vanilla GAN operates on the fundamentals of the adversarial network setup, DCGAN advances image synthesis by securing the convolutional layers, giving a superior appearance to the prevalent spatial features. Training instability is resolved in WGAN through the Wasserstein distance to minimize an unstable regime, therefore, ensuring stable convergence and high-quality images. The GAN models were trained and tested using 1000 MR images of an anonymized knee, 805 images of Heart, 90 images of Brain MRI dataset. The Structural Similarity Index (SSIM) for Vanilla GAN is 0.84, DCGAN is 0.97, and WGAN is 0.99. The Peak Signal to Noise Ratio (PSNR) for Vanilla GAN is 26, DCGAN is 49.3, and WGAN is 43.5. The results were further statistically validated. This study shows that DCGAN and WGAN-based frameworks are promising in MR image reconstruction because of good image quality and superior accuracy. With the first cross-organ benchmark of baseline GANs under a common preprocessing pipeline, this work provides a reproducible benchmark for future hybrid GANs and clinical MRI applications.

This paper introduces a hybrid two-stage registration framework for reconstructing three-dimensional (3D) kidney anatomy from macroscopic slices, using CT-derived models as the geometric reference standard. The approach addresses the data-scarcity and high-distortion challenges typical of macroscopic imaging, where fully learning-based registration (e.g., VoxelMorph) often fails to generalize due to limited training diversity and large nonrigid deformations that exceed the capture range of unconstrained convolutional filters. In the proposed pipeline, the Optimal Cross-section Matching (OCM) algorithm first performs constrained global alignment: translation, rotation, and uniform scaling to establish anatomically consistent slice initialization. Next, a lightweight deep-learning refinement network, inspired by VoxelMorph, predicts residual local deformations between consecutive slices. The core novelty of this architecture lies in its hierarchical decomposition of the registration manifold. This hybrid OCM+DL design integrates explicit geometric priors with the flexible learning capacity of neural networks, ensuring stable optimization and plausible deformation fields even with few training examples. Experiments on an original dataset of 40 kidneys demonstrated better results compared to single-stage baselines. The pipeline maintains physical calibration via Hough-based grid detection and employs Bezier-based contour smoothing for robust meshing and volume estimation. Although validated on kidney data, the proposed framework generalizes to other soft-tissue organs reconstructed from optical or photographic cross-sections. By decoupling interpretable global optimization from data-efficient deep refinement, the method advances the precision, reproducibility, and anatomical realism of multimodal 3D reconstructions for surgical planning, morphological assessment, and medical education.

Smallholder cacao producers often rely on outdated farming techniques and face significant challenges from pests and diseases, unlike larger plantations with more resources and expertise. In the Philippines, cacao farmers have limited access to data, information, and good agricultural practices. This study addresses these issues by developing a mobile application for cacao disease identification and management that functions offline, enabling use in remote areas where farms are mostly located. The core of the system is a deep learning model trained to identify cacao diseases accurately. The trained model is integrated into the mobile app to support farmers in field diagnosis. The disease identification model achieved a validation accuracy of 96.93% while the model for detecting cacao black pod infection levels achieved 79.49% validation accuracy. Field testing of the application showed an agreement rate of 84.2% compared with expert cacao technician assessments. This approach empowers smallholder farmers by providing accessible, technology-enabled tools to improve cacao crop health and productivity.

This work focuses on assessing the information-theoretic limits of scene parameter estimation in plenoptic imaging systems. A general framework to compute lower bounds on the parameter estimation error from noisy plenoptic observations is presented, with a particular focus on passive indirect imaging problems, where the observations do not contain line-of-sight information about the parameter(s) of interest. Using computer graphics rendering software to synthesize the often-complicated dependence among parameter(s) of interest and observations, i.e. the forward model, the proposed framework evaluates the Hammersley-Chapman-Robbins bound to establish lower bounds on the variance of any unbiased estimator of the unknown parameters. The effects of inexact rendering of the true forward model on the computed lower bounds are also analyzed, both theoretically and via simulations. Experimental evaluations compare the computed lower bounds with the performance of the Maximum Likelihood Estimator on a canonical object localization problem, showing that the lower bounds computed via the framework proposed here are indicative of the true underlying fundamental limits in several nominally representative scenarios.

The rapid growth in video consumption has introduced significant challenges to modern streaming architectures. Over-the-Top (OTT) video delivery now predominantly relies on Adaptive Bitrate (ABR) streaming, which dynamically adjusts bitrate and resolution based on client-side constraints such as display capabilities and network bandwidth. This pipeline typically involves downsampling the original high-resolution content, encoding and transmitting it, followed by decoding and upsampling on the client side. Traditionally, these processing stages have been optimized in isolation, leading to suboptimal end-to-end rate-distortion (R-D) performance. The advent of deep learning has spurred interest in jointly optimizing the ABR pipeline using learned resampling methods. However, training such systems end-to-end remains challenging due to the non-differentiable nature of standard video codecs, which obstructs gradient-based optimization. Recent works have addressed this issue using differentiable proxy models, based either on deep neural networks or hybrid coding schemes with differentiable components such as soft quantization, to approximate the codec behavior. While differentiable proxy codecs have enabled progress in compression-aware learning, they remain approximations that may not fully capture the behavior of standard, non-differentiable codecs. To our knowledge, there is no prior evidence demonstrating the inefficiencies of using standard codecs during training. In this work, we introduce a novel framework that enables end-to-end training with real, non-differentiable codecs by leveraging data-driven surrogate gradients derived from actual compression errors. It facilitates the alignment between training objectives and deployment performance. Experimental results show a 5.19% improvement in BD-BR (PSNR) compared to codec-agnostic training approaches, consistently across the entire rate-distortion convex hull spanning multiple downsampling ratios.

Researchers have shown a growing interest in Audio-driven Talking Head Generation. The primary challenge in talking head generation is achieving audio-visual coherence between the lips and the audio, known as lip synchronization. This paper proposes a generic method, LPIPS-AttnWav2Lip, for reconstructing face images of any speaker based on audio. We used the U-Net architecture based on residual CBAM to better encode and fuse audio and visual modal information. Additionally, the semantic alignment module extends the receptive field of the generator network to obtain the spatial and channel information of the visual features efficiently; and match statistical information of visual features with audio latent vector to achieve the adjustment and injection of the audio content information to the visual information. To achieve exact lip synchronization and to generate realistic high-quality images, our approach adopts LPIPS Loss, which simulates human judgment of image quality and reduces instability possibility during the training process. The proposed method achieves outstanding performance in terms of lip synchronization accuracy and visual quality as demonstrated by subjective and objective evaluation results. The code for the paper is available at the following link: https://github.com/FelixChan9527/LPIPS-AttnWav2Lip

This paper presents SurfelSoup, an end-to-end learned surface-based framework for point cloud geometry compression, with surface-structured primitives for representation. It proposes a probabilistic surface representation, pSurfel, which models local point occupancies using a bounded generalized Gaussian distribution. In addition, the pSurfels are organized into an octree-like hierarchy, pSurfelTree, with a Tree Decision module that adaptively terminates the tree subdivision for rate-distortion optimal Surfel granularity selection. This formulation avoids redundant point-wise compression in smooth regions and produces compact yet smooth surface reconstructions. Experimental results under the MPEG common test condition show consistent gain on geometry compression over voxel-based baselines and MPEG standard G-PCC-GesTM-TriSoup, while providing visually superior reconstructions with smooth and coherent surface structures.

Limited-angle computed tomography (LACT) offers the advantages of reduced radiation dose and shortened scanning time. Traditional reconstruction algorithms exhibit various inherent limitations in LACT. Currently, most deep learning-based LACT reconstruction methods focus on multi-domain fusion or the introduction of generic priors, failing to fully align with the core imaging characteristics of LACT-such as the directionality of artifacts and directional loss of structural information, which are caused by the absence of projection angles in certain directions. Inspired by the theory of visible and invisible singularities, taking into account the aforementioned core imaging characteristics of LACT, we propose a Visible Singularities Guided Correlation network for LACT reconstruction (VSGC). The design philosophy of VSGC consists of two core steps: First, extract VS edge features from LACT images and focus the model's attention on these VS. Second, establish correlations between the VS edge features and other regions of the image. Additionally, a multi-scale loss function with anisotropic constraint is employed to constrain the model to converge in multiple aspects. Finally, qualitative and quantitative validations are conducted on both simulated and real datasets to verify the effectiveness and feasibility of the proposed design. Particularly, in comparison with alternative methods, VSGC delivers more prominent performance in small angular ranges, with the PSNR improvement of 2.45 dB and the SSIM enhancement of 1.5%. The code is publicly available at https://github.com/yqx7150/VSGC.

Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an optimal control problem; however, solving the resulting trajectory optimisation is computationally and memory intensive, requiring differentiation through the flow dynamics or adjoint solves. We propose MPC-Flow, a model predictive control framework that formulates inverse problem solving with flow-based generative models as a sequence of control sub-problems, enabling practical optimal control-based guidance at inference time. We provide theoretical analysis linking MPC-Flow to the underlying optimal control objective and show how different algorithmic choices yield a spectrum of guidance algorithms, including regimes that avoid backpropagation through the generative model trajectory. We evaluate MPC-Flow on benchmark image restoration tasks, spanning linear and non-linear settings such as in-painting, deblurring, and super-resolution, and demonstrate strong performance and scalability to massive state-of-the-art architectures via training-free guidance of FLUX.2 (32B) in a quantised setting on consumer hardware.

Diffusion models have been increasingly used as strong generative priors for solving inverse problems such as super-resolution in medical imaging. However, these approaches typically utilize a diffusion prior trained at a single scale, ignoring the hierarchical scale structure of image data. In this work, we propose to decompose images into Laplacian pyramid scales and train separate diffusion priors for each frequency band. We then develop an algorithm to perform super-resolution that utilizes these priors to progressively refine reconstructions across different scales. Evaluated on brain, knee, and prostate MRI data, our approach both improves perceptual quality over baselines and reduces inference time through smaller coarse-scale networks. Our framework unifies multiscale reconstruction and diffusion priors for medical image super-resolution.

We present a deep neural network approach for encoding microphone array signals into Ambisonics that generalizes to arbitrary microphone array configurations with fixed microphone count but varying locations and frequency-dependent directional characteristics. Unlike previous methods that rely only on array geometry as metadata, our approach uses directional array transfer functions, enabling accurate characterization of real-world arrays. The proposed architecture employs separate encoders for audio and directional responses, combining them through cross-attention mechanisms to generate array-independent spatial audio representations. We evaluate the method on simulated data in two settings: a mobile phone with complex body scattering, and a free-field condition, both with varying numbers of sound sources in reverberant environments. Evaluations demonstrate that our approach outperforms both conventional digital signal processing-based methods and existing deep neural network solutions. Furthermore, using array transfer functions instead of geometry as metadata input improves accuracy on realistic arrays.

This article develops a control method for linear time-invariant systems subject to time-varying and a priori unknown cost functions, that satisfies state and input constraints, and is robust to exogenous disturbances. To this end, we combine the online convex optimization framework with a reference governor and a constraint tightening approach. The proposed framework guarantees recursive feasibility and robust constraint satisfaction. Its closed-loop performance is studied in terms of its dynamic regret, which is bounded linearly by the variation of the cost functions and the magnitude of the disturbances. The proposed method is illustrated by a numerical case study of a tracking control problem.

We study Sparse Signal Recovery (SSR) methods for multichannel imaging with compressed {forward and backward} operators that preserve reconstruction accuracy. We propose a Compressed Block-Convolutional (C-BC) measurement model based on a low-rank Convolutional Neural Network (CNN) decomposition that is analytically initialized from a low-rank factorization of physics-derived forward/backward operators in time delay-based measurements. We use Orthogonal Matching Pursuit (OMP) to select a compact set of basis filters from the analytic model and compute linear mixing coefficients to approximate the full model. We consider the Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) network as a representative example for which the C-BC-LISTA extension is presented. In simulated multichannel ultrasound imaging across multiple Signal-to-Noise Ratios (SNRs), C-BC-LISTA requires substantially fewer parameters and smaller model size than other state-of-the-art (SOTA) methods while improving reconstruction accuracy. In ablations over OMP, Singular Value Decomposition (SVD)-based, and random initializations, OMP-initialized structured compression performs best, yielding the most efficient training and the best performance.

Ray tracing is increasingly utilized in wireless system simulations to estimate channel paths. In large-scale simulations with complex environments, ray tracing at high resolution can be computationally demanding. To reduce the computation, this paper presents a novel method for conducting ray tracing at a coarse set of reference points and interpolating the channels at other locations. The key insight is to interpolate the images of reflected points. In addition to the computational savings, the method directly captures the spherical nature of each wavefront enabling fast and accurate computation of channels using line-of-sight MIMO and other wide aperture techniques. Through empirical validation and comparison with exhaustive ray tracing, we demonstrate the efficacy and practicality of our approach in achieving high-fidelity channel predictions with reduced computational resources.

The deployment of medium-range battery electric aircraft is a promising pathway to improve the environmental footprint of air mobility. Yet such a deployment would be accompanied by significant electric power requirements at airports due to aircraft charging. Given the growing prevalence of electric vehicles and their bi-directional charging capabilities–so-called vehicle-to-grid (V2G)–we study energy buffer capabilities of parked electric vehicles to alleviate pressure on grid connections. To this end, we present energy management strategies for airports providing cost-optimal apron and landside V2G charge scheduling. Specifically, we first formulate the optimal energy management problem of joint aircraft charging and landside V2G coordination as a linear program, whereby we use partial differential equations to model the aggregated charging dynamics of the electric vehicle fleet. Second, we consider a shuttle flight network with a single hub of a large Dutch airline, real-world grid prices, and synthetic parking garage occupancy data to test our framework. Our results show that V2G at even a single airport can indeed reduce energy costs to charge the aircraft fleet: Compared to a baseline scenario without V2G, the proposed concept yields cost savings of up to 32%, depending on the schedule and amount of participating vehicles, and has other potential beneficial effects on the local power grid, e.g., the reduction of potential power peaks.

We propose VL-DUN, a principled framework for joint All-in-One Medical Image Restoration and Segmentation (AiOMIRS) that bridges the gap between low-level signal recovery and high-level semantic understanding. While standard pipelines treat these tasks in isolation, our core insight is that they are fundamentally synergistic: restoration provides clean anatomical structures to improve segmentation, while semantic priors regularize the restoration process. VL-DUN resolves the sub-optimality of sequential processing through two primary innovations. (1) We formulate AiOMIRS as a unified optimization problem, deriving an interpretable joint unfolding mechanism where restoration and segmentation are mathematically coupled for mutual refinement. (2) We introduce a frequency-aware Mamba mechanism to capture long-range dependencies for global segmentation while preserving the high-frequency textures necessary for restoration. This allows for efficient global context modeling with linear complexity, effectively mitigating the spectral bias of standard architectures. As a pioneering work in the AiOMIRS task, VL-DUN establishes a new state-of-the-art across multi-modal benchmarks, improving PSNR by 0.92 dB and the Dice coefficient by 9.76%. Our results demonstrate that joint collaborative learning offers a superior, more robust solution for complex clinical workflows compared to isolated task processing. The codes are provided in https://github.com/cipi666/VLDUN.

Upper Mid-Band (FR3, 7-24 GHz) receivers for 6G must operate over wide bandwidths in dense spectral environments, making them particularly vulnerable to strong adjacent-band interference and front-end nonlinearities. While conventional linear receivers can suppress spectrally separated interferers under ideal hardware assumptions, receiver saturation and finite-resolution quantization cause nonlinear spectral leakage that severely degrades performance in practical wideband radios. We study the recovery of a desired signal from nonlinear receiver observations corrupted by a high-power out-of-band interferer. The receiver front-end is modeled as a smooth, memoryless nonlinearity followed by additive noise and optional quantization. To mitigate these nonlinear and quantization-induced distortions, we propose a learned multi-layer Vector Approximate Message Passing (LMLVAMP) algorithm that incorporates spectral priors with neural network based denoising. Simulation results demonstrate significant performance gains over conventional methods, particularly in high-interference regimes representative of FR3 coexistence scenarios.

Modulo imaging enables high dynamic range (HDR) acquisition by cyclically wrapping saturated intensities, but accurate reconstruction remains challenging due to ambiguities between natural image edges and artificial wrap discontinuities. This work proposes a learning-based HDR restoration framework that incorporates two key strategies: (i) a scale-equivariant regularization that enforces consistency under exposure variations, and (ii) a feature lifting input design combining the raw modulo image, wrapped finite differences, and a closed-form initialization. Together, these components enhance the network's ability to distinguish true structure from wrapping artifacts, yielding state-of-the-art performance across perceptual and linear HDR quality metrics.

Reliable control of myoelectric prostheses is often hindered by high inter-subject variability and the clinical impracticality of high-density sensor arrays. This study proposes a deep learning framework for accurate gesture recognition using only two surface electromyography (sEMG) channels. The method employs a Convolutional Sparse Autoencoder (CSAE) to extract temporal feature representations directly from raw signals, eliminating the need for heuristic feature engineering. On a 6-class gesture set, our model achieved a multi-subject F1-score of 94.3% $\pm$ 0.3%. To address subject-specific differences, we present a few-shot transfer learning protocol that improved performance on unseen subjects from a baseline of 35.1% $\pm$ 3.1% to 92.3% $\pm$ 0.9% with minimal calibration data. Furthermore, the system supports functional extensibility through an incremental learning strategy, allowing for expansion to a 10-class set with a 90.0% $\pm$ 0.2% F1-score without full model retraining. By combining high precision with minimal computational and sensor overhead, this framework provides a scalable and efficient approach for the next generation of affordable and adaptive prosthetic systems.

Speech contains both acoustic and linguistic patterns that reflect cognitive decline, and therefore models describing only one domain cannot fully capture such complexity. This study investigates how early fusion (EF) of speech and its corresponding transcription text embeddings, with attention to encoder layer depth, can improve cognitive status classification. Using a DementiaBank-derived collection of recordings (1,629 speakers; cognitively normal controls$\unicode{x2013}$CN, Mild Cognitive Impairment$\unicode{x2013}$MCI, and Alzheimer's Disease and Related Dementias$\unicode{x2013}$ADRD), we extracted frame-aligned embeddings from different internal layers of wav2vec 2.0 or Whisper combined with DistilBERT or RoBERTa. Unimodal, EF and late fusion (LF) models were trained with a transformer classifier, optimized, and then evaluated across 10 seeds. Performance consistently peaked in mid encoder layers ($\sim$8$\unicode{x2013}$10), with the single best F1 at Whisper + RoBERTa layer 9 and the best log loss at Whisper + DistilBERT layer 10. Acoustic-only models consistently outperformed text-only variants. EF boosts discrimination for genuinely acoustic embeddings, whereas LF improves probability calibration. Layer choice critically shapes clinical multimodal synergy.

Fluid antenna systems (FAS) have recently emerged as a promising paradigm for achieving spatially reconfigurable, compact, and energy-efficient wireless communications in beyond fifth-generation (B5G) and sixth-generation (6G) networks. By dynamically repositioning a liquid-based radiating element within a confined physical structure, FAS can exploit spatial diversity without relying on multiple fixed antenna elements. This spatial mobility provides a new degree of freedom for mitigating channel fading and interference, while maintaining low hardware complexity and power consumption. However, the performance of FAS in realistic deployments is strongly affected by channel uncertainty, hardware nonidealities, and mechanical constraints, all of which can substantially deviate from idealized analytical assumptions. This paper presents a comprehensive survey of the operation and design of FAS under such practical considerations. Key aspects include the characterization of spatio-temporal channel uncertainty, analysis of hardware and mechanical impairments such as RF nonlinearity, port coupling, and fluid response delay, as well as the exploration of robust design and learning-based control strategies to enhance system reliability. Finally, open research directions are identified, aiming to guide future developments toward robust, adaptive, and cross-domain FAS design for next-generation wireless networks.

As intelligent sensing expands into high-privacy environments such as restrooms and changing rooms, the field faces a critical privacy-security paradox. Traditional RGB surveillance raises significant concerns regarding visual recording and storage, while existing privacy-preserving methods-ranging from physical desensitization to traditional cryptographic or obfuscation techniques-often compromise semantic understanding capabilities or fail to guarantee mathematical irreversibility against reconstruction attacks. To address these challenges, this study presents a novel privacy-preserving perception technology based on the AI Flow theoretical framework and an edge-cloud collaborative architecture. The proposed methodology integrates source desensitization with irreversible feature mapping. Leveraging Information Bottleneck theory, the edge device performs millisecond-level processing to transform raw imagery into abstract feature vectors via non-linear mapping and stochastic noise injection. This process constructs a unidirectional information flow that strips identity-sensitive attributes, rendering the reconstruction of original images impossible. Subsequently, the cloud platform utilizes multimodal family models to perform joint inference solely on these abstract vectors to detect abnormal behaviors. This approach fundamentally severs the path to privacy leakage at the architectural level, achieving a breakthrough from video surveillance to de-identified behavior perception and offering a robust solution for risk management in high-sensitivity public spaces.