Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Electrical Engineering and Systems Science

eess Watch Electrical Engineering and Systems Science

Friday 21 November

Image and Video Processing · Cross-listed from cs.CV

Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites

Lingyan Ruan, Bin Chen and Taehyun Rhee

Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur levels significantly affect the visual fidelity of mixed reality compositions. Existing pipelines often rely on camera parameters (e.g., focal length, focus distance, aperture size) and scene depth to compute the circle of confusion (CoC) for realistic lens blur rendering. However, such information is often unavailable to ordinary users, limiting the accessibility and generalizability of these methods. In this work, we propose a novel compositing approach that directly estimates the CoC map from RGB images, bypassing the need for scene depth or camera metadata. The CoC values for virtual objects are inferred through a linear relationship between its signed CoC map and depth, and realistic lens blur is rendered using a neural reblurring network. Our method provides flexible and practical solution for real-world applications. Experimental results demonstrate that our method achieves high-fidelity compositing with realistic defocus effects, outperforming state-of-the-art techniques in both qualitative and quantitative evaluations.

Read the full abstract

Signal Processing

Self-Localizing MIMO Beam Mapping with Continuously Evolving Channel Memory

Wangqian Chen, Junting Chen and Shuguang Cui

Machine learning has greatly advanced data-driven channel modeling and resource optimization. However, most existing methods require accurately location-labeled datasets, which are costly to collect and maintain in dynamic environments. This paper develops a self-localizing multiple-input multiple-output (MIMO) beam map framework that constructs a hierarchical wireless memory from highly sparse channel state information (CSI) measurements without explicit location labels. To reduce acquisition and processing overhead, we use beamdomain received signal strength (RSS) as compact inputs and theoretically show that they enable asymptotically unbiased spatial signature estimation. A dual-scale extractor captures intrasnapshot angular dependencies and inter-sample correlations for incomplete observations, and a hybrid temporal encoder is designed to consolidate recent CSI into stable short-term context for physical anchor inference. The inferred anchors spatially index a physically structured radio map embedding that stores long-term channel knowledge, which conditions a diffusion decoder for location-consistent full CSI reconstruction. Such a radio map embedding provides a persistent wireless knowledge representation that can be continuously updated and reused without full CSI acquisition. Experiments show that the proposed framework improves physical-anchor recovery accuracy by over 30% under sparse measurements and achieves more than 20% channel-capacity gain in non-line-of-sight (NLOS) beam tracking over Kalman-filter-based methods.

Read the full abstract

Systems and Control

Feature Partitioning and Semantic Equalization for Intrinsic Robustness in Semantic Communication under Packet Loss

Xiao Yang, Shuai Ma, Yong Liang et al. (+1 more)

Semantic communication can improve transmission efficiency by focusing on task-relevant information. However, under packet-based communication protocols, any error typically results in the loss of an entire packet, making semantic communication particularly vulnerable to packet loss. Since high-dimensional semantic features must be partitioned into one-dimensional transmission units during packetization. A critical open question is how to partition semantic features to maximize robustness. To address this, we systematically investigate the performance of two mainstream architectures, Transformer and Convolutional neural networks (CNN), under various feature partitioning schemes. The results show that the Transformer architecture exhibits inherent robustness to packet loss when partitioned along the channel dimension. In contrast, the CNN-based baseline exhibits imbalanced channel utilization, causing severe degradation once dominant channels are lost. To enhance the CNN resilience, we propose a lightweight Semantic Equalization Mechanism (SEM) that balances channel contributions and prevents a few channels from dominating. SEM consists of two parallel approaches: a Dynamic Scale module that adaptively adjusts channel importance, and a Broadcast module that facilitates information interaction among channels. Experimental results demonstrate that CNN equipped with SEM achieve graceful degradation under packet loss (retaining about 85% of lossless PSNR at 40% packet loss), comparable to that of Transformer models. Our findings indicate that, under an appropriate partitioning strategy, maintaining a balanced semantic representation is a fundamental condition for achieving intrinsic robustness against packet loss. These insights may also extend to other modalities such as video and support practical semantic communication design.

Read the full abstract

All authors Xiao Yang, Shuai Ma, Yong Liang, Guangming Shi

Systems and Control

State-Derivative Feedback Control for Damping Low-Frequency Oscillations in Bulk Power Systems

MST Rumi Akter, Anamitra Pal and Rajasekhar Anguluri

Low-frequency oscillations remain a major challenge in bulk power systems with high renewable penetration, long lines, and large loads. Existing damping strategies based on power modulation of high voltage DC (HVDC) or energy storage, are often limited by fixed control architectures, leaving some modes poorly damped. This paper introduces a state-derivative feedback (SDF) damping controller that uses both frequency and its rate of change as feedback signals. Incorporating state derivatives enhances modal damping and accelerates frequency recovery, enabling HVDC and energy storage to effectively stabilize the grid. We evaluate the SDF controller on two- and three-area systems and compare performance with a frequency difference-based damping scheme. Results show that the SDF control reproduces state-feedback performance while providing good damping of both inter- and intra-area oscillations compared to the frequency-difference method, highlighting its potential as a practical solution for stabilizing power-electronics-rich grids.

Read the full abstract

Image and Video Processing · Cross-listed from cs.CV

Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models

Dailan He, Guanlin Feng, Xingtong Ge et al. (+6 more)

Group Relative Policy Optimization (GRPO) has shown promise in aligning image and video generative models with human preferences. However, applying it to modern flow matching models is challenging because of its deterministic sampling paradigm. Current methods address this issue by converting Ordinary Differential Equations (ODEs) to Stochastic Differential Equations (SDEs), which introduce stochasticity. However, this SDE-based GRPO suffers from issues of inefficient credit assignment and incompatibility with high-order solvers for fewer-step sampling. In this paper, we first reinterpret existing SDE-based GRPO methods from a distance optimization perspective, revealing their underlying mechanism as a form of contrastive learning. Based on this insight, we propose Neighbor GRPO, a novel alignment algorithm that completely bypasses the need for SDEs. Neighbor GRPO generates a diverse set of candidate trajectories by perturbing the initial noise conditions of the ODE and optimizes the model using a softmax distance-based surrogate leaping policy. We establish a theoretical connection between this distance-based objective and policy gradient optimization, rigorously integrating our approach into the GRPO framework. Our method fully preserves the advantages of deterministic ODE sampling, including efficiency and compatibility with high-order solvers. We further introduce symmetric anchor sampling for computational efficiency and group-wise quasi-norm reweighting to address reward flattening. Extensive experiments demonstrate that Neighbor GRPO significantly outperforms SDE-based counterparts in terms of training cost, convergence speed, and generation quality.

Read the full abstract

All authors Dailan He, Guanlin Feng, Xingtong Ge, Yazhe Niu, Yi Zhang, Bingqi Ma, Guanglu Song, Yu Liu, Hongsheng Li

Image and Video Processing · Cross-listed from cs.NI

ARC: Consistent, Low-Latency Delivery via Receiver-Side Scheduling

Michael Luby

Applications such as cloud gaming, video streaming, telemetry, ML inference, and data transfer provide a better experience when data is released at the receiver with timing reflecting how the data enters the sender. In practice, network delay variation and recovery dynamics at the receiver distort this timing even when transports deliver all packets correctly, producing visible jitter, stalls, and unstable playback. Many such applications operate best when delivery preserves this timing behavior and its implied order; out-of-order or irregular delivery can significantly degrade performance even when all data eventually arrives. We present a lightweight receiver-side release scheduling protocol, Adaptive Release Control (ARC), that restores this timing at the receiver. ARC releases recovered data in a manner that follows the sender's timing, maintaining ordering and limiting reordering when necessary while producing smooth delivery with minimal added latency given network conditions. It operates entirely on the receiver clock and requires no feedback, synchronization, or changes to the underlying transport. As an example, we integrate ARC into LT3, a network-layer system currently deployed as a software overlay that forwards traffic without altering the transport protocols it carries, where ARC functions as an independent module that regulates release timing for forwarded data. Evaluating LT3 with ARC on a cloud-gaming workload shows that the protocol removes virtually all large jitter excursions and yields release intervals that closely match the sender's timing, translating into improved perceptual smoothness. Broader latency improvements arise from the behavior of the full LT3 system. The benefits of ARC extend to transport protocols carried over LT3, including TCP, QUIC, WebRTC, UDP, and RTP, as preserving sender timing improves their behavior across a wide range of conditions.

Read the full abstract

Systems and Control

When Motion Learns to Listen: Diffusion-Prior Lyapunov Actor-Critic Framework with LLM Guidance for Stable and Robust AUV Control in Underwater Tasks

Jingzehua Xu, Weiyi Liu, Weihang Zhang et al. (+4 more)

Autonomous Underwater Vehicles (AUVs) are indispensable for marine exploration; yet, their control is hindered by nonlinear hydrodynamics, time-varying disturbances, and localization uncertainty. Traditional controllers provide only limited adaptability, while Reinforcement Learning (RL), though promising, suffers from sample inefficiency, weak long-term planning, and lacks stability guarantees, leading to unreliable behavior. To address these challenges, we propose a diffusion-prior Lyapunov actor-critic framework that unifies exploration, stability, and semantic adaptability. Specifically, a diffusion model generates smooth, multimodal, and disturbance-resilient candidate actions; a Lyapunov critic further imposes dual constraints that ensure stability; and a Large Language Model (LLM)-driven outer loop adaptively selects and refines Lyapunov functions based on task semantics and training feedback. This "generation-filtering-optimization" mechanism not only enhances sample efficiency and planning capability but also aligns stability guarantees with diverse mission requirements in the multi-objective optimization task. Extensive simulations under complex ocean dynamics demonstrate that the proposed framework achieves more accurate trajectory tracking, higher task completion rates, improved energy efficiency, faster convergence, and improved robustness compared with conventional RL and diffusion-augmented baselines.

Read the full abstract

All authors Jingzehua Xu, Weiyi Liu, Weihang Zhang, Zhuofan Xi, Guanwen Xie, Shuai Zhang, Yi Li

Systems and Control · Cross-listed from cs.RO

Single-Pixel Tactile Skin via Compressive Sampling

Ariel Slepyan, Laura Xing, Rudy Zhang et al. (+1 more)

Development of large-area, high-speed electronic skins is a grand challenge for robotics, prosthetics, and human-machine interfaces, but is fundamentally limited by wiring complexity and data bottlenecks. Here, we introduce Single-Pixel Tactile Skin (SPTS), a paradigm that uses compressive sampling to reconstruct rich tactile information from an entire sensor array via a single output channel. This is achieved through a direct circuit-level implementation where each sensing element, equipped with a miniature microcontroller, contributes a dynamically weighted analog signal to a global sum, performing distributed compressed sensing in hardware. Our flexible, daisy-chainable design simplifies wiring to a few input lines and one output, and significantly reduces measurement requirements compared to raster scanning methods. We demonstrate the system's performance by achieving object classification at an effective 3500 FPS and by capturing transient dynamics, resolving an 8 ms projectile impact into 23 frames. A key feature is the support for adaptive reconstruction, where sensing fidelity scales with measurement time. This allows for rapid contact localization using as little as 7% of total data, followed by progressive refinement to a high-fidelity image - a capability critical for responsive robotic systems. This work offers an efficient pathway towards large-scale tactile intelligence for robotics and human-machine interfaces.

Read the full abstract

All authors Ariel Slepyan, Laura Xing, Rudy Zhang, Nitish Thakor

Signal Processing

State-of-charge estimation of lithium-ion batteries using a tree seed and genetic algorithm-optimized generalized mixture minimum error entropy-based square root cubature Kalman filter

Haiquan Zhao, Xiong Yin and Jinhui Hu

The cubature Kalman filter based on minimum error entropy (MEE-CKF) offers accurate and robust performance in state of charge (SOC) estimation. However, due to the inflexibility of the minimum error entropy (MEE), this algorithm demonstrates limited robustness when confronted with more complex noise environments. To address these limitations, this paper proposes a generalized mixture minimum error entropy-based (GMMEE) square-root cubature Kalman filter (GMMEE-SRCKF). The square-root algorithm ensures improved numerical stability and avoids covariance degeneration, while the GMMEE criterion with two flexible kernels adapts effectively to non-Gaussian noise. Moreover, a hybrid tree seed and genetic algorithm (TSGA) is introduced to optimize the kernel parameters automatically. Experimental results confirm that the TSGA-optimized GMMEE-SRCKF outperforms existing robust filters, achieving the root mean square error (RMSE) of less than 0.5%.

Read the full abstract

Signal Processing · Cross-listed from physics.med-ph

Double-Profile Intersection (DoPIo) Ultrasound: Pointwise Shear Elasticity Estimation using Paired Confocal Displacement Profiles

Keita Yokoyama, Murad Hossain, Sabiq Muhtadi et al. (+1 more)

Current acoustic radiation force (ARF) based methods for quantifying tissue elasticity primarily rely on shear wave propagation. However, their spatial resolution is limited by the need for spatial averaging, and their accuracy is affected by shear wave guidance, out of plane reflections, and geometric dispersion, which reduce their applicability in mechanically complex tissues. This study introduces a novel technique called Double Profile Intersection (DoPIo) ultrasound, which enables pointwise estimation of shear elastic modulus within the region of ARF excitation by leveraging the scatterer shearing rate. This rate is inferred by tracking ARF induced displacement using two tracking beams with different lateral widths. The wider beam captures scatterers located outside the ARF excitation region that begin to displace as shearing propagates. The time at which the two resulting displacement profiles intersect is mapped to shear elastic modulus using an empirically derived model based on finite element simulations. In silico, DoPIo estimated shear elastic modulus with a median error of -0.02 kPa and a median absolute deviation of 1.98 kPa in elastic materials up to 35 kPa. Experimental validation in vitro and ex vivo demonstrated that DoPIo reliably distinguished softer regions from stiffer ones, and its modulus estimates remained consistent across varying ARF push amplitudes, provided sufficient displacement estimation signal to noise ratio. DoPIo offers a feasible approach for high resolution, on axis shear elasticity estimation and holds promise as a quantitative biomarker that is independent of ARF amplitude.

Read the full abstract

All authors Keita Yokoyama, Murad Hossain, Sabiq Muhtadi, Caterina Gallippi

Image and Video Processing

Avoiding Quality Saturation in UGC Compression Using Denoised References

Xin Xiong, Samuel Fernández-Menduiña, Eduardo Pavez et al. (+3 more)

Video-sharing platforms must re-encode large volumes of noisy user-generated content (UGC) to meet streaming demands. However, conventional codecs, which aim to minimize the mean squared error (MSE) between the compressed and input videos, can cause quality saturation (QS) when applied to UGC, i.e., increasing the bitrate preserves input artifacts without improving visual quality. A direct approach to solve this problem is to detect QS by repeatedly evaluating a non-reference metric (NRM) on videos compressed with multiple codec parameters, which is inefficient. In this paper, we re-frame UGC compression and QS detection from the lens of noisy source coding theory: rather than using a NRM, we compute the MSE with respect to the denoised UGC, which serves as an alternative reference (D-MSE). Unlike MSE measured between the UGC input and the compressed UGC, D-MSE saturates at non-zero values as bitrates increase, a phenomenon we term distortion saturation (DS). Since D-MSE can be computed at the block level in the transform domain, we can efficiently detect D-MSE without coding and decoding with various parameters. We propose two methods for DS detection: distortion saturation detection (DSD), which relies on an input-dependent threshold derived from the D-MSE of the input UGC, and rate-distortion saturation detection (RDSD), which estimates the Lagrangian at the saturation point using a low-complexity compression method. Both methods work as a pre-processing step that can help standard-compliant codecs avoid QS in UGC compression. Experiments with AVC show that preventing encoding in the saturation region, i.e., avoiding encoding at QPs that result in QS according to our methods, achieves BD-rate savings of 8%-20% across multiple different NRMs, compared to a naïve baseline that encodes at the given input QP while ignoring QS.

Read the full abstract

All authors Xin Xiong, Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega, Neil Birkbeck, Balu Adsumilli

Thursday 20 November

Systems and Control · Cross-listed from cs.LG

AI-based framework to predict animal and pen feed intake in feedlot beef cattle

Alex S. C. Maia, John B. Hall, Hugo F. M. Milan et al. (+1 more)

Advances in technology are transforming sustainable cattle farming practices, with electronic feeding systems generating big longitudinal datasets on individual animal feed intake, offering the possibility for autonomous precision livestock systems. However, the literature still lacks a methodology that fully leverages these longitudinal big data to accurately predict feed intake accounting for environmental conditions. To fill this gap, we developed an AI-based framework to accurately predict feed intake of individual animals and pen-level aggregation. Data from 19 experiments (>16.5M samples; 2013-2024) conducted at Nancy M. Cummings Research Extension & Education Center (Carmen, ID) feedlot facility and environmental data from AgriMet Network weather stations were used to develop two novel environmental indices: InComfort-Index, based solely on meteorological variables, showed good predictive capability for thermal comfort but had limited ability to predict feed intake; EASI-Index, a hybrid index integrating environmental variables with feed intake behavior, performed well in predicting feed intake but was less effective for thermal comfort. Together with the environmental indices, machine learning models were trained and the best-performing machine learning model (XGBoost) accuracy was RMSE of 1.38 kg/day for animal-level and only 0.14 kg/(day-animal) at pen-level. This approach provides a robust AI-based framework for predicting feed intake in individual animals and pens, with potential applications in precision management of feedlot cattle, through feed waste reduction, resource optimization, and climate-adaptive livestock management.

Read the full abstract

All authors Alex S. C. Maia, John B. Hall, Hugo F. M. Milan, Izabelle A. M. A. Teixeira

Image and Video Processing

Reconfigurable, large-format D-ToF/photon-counting SPAD image sensors with embedded FPGA for scene adaptability

Tommaso Milanese, Baris Can Efe, Claudio Bruschini et al. (+2 more)

CMOS-compatible single-photon avalanche diodes (SPADs) have emerged in many systems as the solution of choice for cameras with photon-number resolution and photon counting capabilities. Being natively digital optical interfaces, SPADs are naturally drawn to in situ logic processing and event-driven computation; they are usually coupled to discrete FPGAs to enable reconfigurability. In this work, we propose to bring the FPGA on-chip, in direct contact with the SPADs at pixel or cluster level. To demonstrate the suitability of this approach, we created an architecture for processing timestamps and photon counts using programmable weighted sums based on an efficient use of look-up tables. The outputs are processed hierarchically, similarly to what is done in FPGAs, reducing power consumption and simplifying I/Os. Finally, we show how artificial neural networks can be designed and reprogrammed by using look-up tables in an efficient way.

Read the full abstract

All authors Tommaso Milanese, Baris Can Efe, Claudio Bruschini, Nobukazu Teranishi, Edoardo Charbon

Signal Processing · Cross-listed from cs.SD

Is Phase Really Needed for Weakly-Supervised Dereverberation ?

Marius Rodrigues, Louis Bahrman, Roland Badeau et al. (+1 more)

In unsupervised or weakly-supervised approaches for speech dereverberation, the target clean (dry) signals are considered to be unknown during training. In that context, evaluating to what extent information can be retrieved from the sole knowledge of reverberant (wet) speech becomes critical. This work investigates the role of the reverberant (wet) phase in the time-frequency domain. Based on Statistical Wave Field Theory, we show that late reverberation perturbs phase components with white, uniformly distributed noise, except at low frequencies. Consequently, the wet phase carries limited useful information and is not essential for weakly supervised dereverberation. To validate this finding, we train dereverberation models under a recent weak supervision framework and demonstrate that performance can be significantly improved by excluding the reverberant phase from the loss function.

Read the full abstract

All authors Marius Rodrigues, Louis Bahrman, Roland Badeau, Gaël Richard

Image and Video Processing

MRI Super-Resolution with Deep Learning: A Comprehensive Survey

Mohammad Khateri, Serge Vasylechko, Morteza Ghahremani et al. (+9 more)

High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR) presents a promising computational approach to overcome these challenges by generating HR images from more affordable low-resolution (LR) scans, potentially improving diagnostic accuracy and efficiency without requiring additional hardware. This survey reviews recent advances in MRI SR techniques, with a focus on deep learning (DL) approaches. It examines DL-based MRI SR methods from the perspectives of computer vision, computational imaging, inverse problems, and MR physics, covering theoretical foundations, architectural designs, learning strategies, benchmark datasets, and performance metrics. We propose a systematic taxonomy to categorize these methods and present an in-depth study of both established and emerging SR techniques applicable to MRI, considering unique challenges in clinical and research contexts. We also highlight open challenges and directions that the community needs to address. Additionally, we provide a collection of essential open-access resources, tools, and tutorials, available on our GitHub: https://github.com/mkhateri/Awesome-MRI-Super-Resolution. IEEE keywords: MRI, Super-Resolution, Deep Learning, Computational Imaging, Inverse Problem, Survey.

Read the full abstract

All authors Mohammad Khateri, Serge Vasylechko, Morteza Ghahremani, Liam Timms, Deniz Kocanaogullari, Simon K. Warfield, Camilo Jaimes, Davood Karimi, Alejandra Sierra, Jussi Tohka, Sila Kurugol, Onur Afacan

Systems and Control

The PV performance ratio paradox: annual data from large-scale, real-world PV systems show negligible meteorological and technical impact and points to dominant human factors

Hugo FM Milan, Aline Q Alves, Thatiane AT Souza et al. (+4 more)

Performance ratio (PR) is a established measure of efficiency of photovoltaic (PV) systems. While previous research demonstrated the effects of meteorological and technical variables on PR, a gap persists in the literature on which variables strongly influence PR in large-scale, real-world, heterogeneous PV systems. This paper aims to fill this gap, applying data-driven models to PV systems located in Rondônia State, Brazil, to identify which variables strongly influence annual PR, and, hence, should be the target for optimization. Surprisingly, only negligible effects were found between meteorological and technical variables on annual PR, indicating that human-factors (such as installation, monitoring, and maintenance quality) might have a stronger effect. These findings indicates that, to improve performance of PV systems, policy makers could focus on creating educational programs to teach PV installers and technicians how to properly install, monitor, and maintain modern PV systems. Through estimating the probability density functions of PR, its peak value was found as 78.85% (mean 77.52%, 95% confidence interval of 76.12% to 78.84%, and 95% prediction interval of 58.83% to 92.70%). A map of annual final yield was developed for Rondônia State and can be used by entrepreneurs to quickly and cheaply estimate energy production.

Read the full abstract

All authors Hugo FM Milan, Aline Q Alves, Thatiane AT Souza, Juliana M Galo, Alex SC Maia, Moisés AP Borges, Ciro J Egoavil

Signal Processing

Line-of-Sight Probability in Macrocells: Framework, Statistical Models, and Parametrization from Massive Real World Datasets in the USA

Bassel Abou Ali Modad, Xin Yu, Yao-Yi Chiang et al. (+1 more)

Accurate modeling of line-of-sight (LOS) probability is crucial for wireless channel description and coverage planning. The presence of a LOS impacts other channel characteristics such as pathloss, fading depth, delay- and angular spread, etc.. Existing models, although useful, are based on very limited datasets. In this paper, we establish a framework to produce high accuracy LOS models from geospatial data in different environments, and apply it to create a LOS model for macrocells, using datasets of the United States (US) on a nationalscale, using more than 13, 000 locations of real-world macrocells. Based on this we create a new, fully parameterized model that better describes macrocell deployments in the US than the 3GPP model. We furthermore demonstrate that for improved accuracy the LOS probability should be modeled on a per cell basis, and the model parameters treated as random variables; we provide a full description and parameterization of this novel approach and by simulations show that it better predicts the inter-cell interference at the cell-edge than an average-based model.

Read the full abstract

All authors Bassel Abou Ali Modad, Xin Yu, Yao-Yi Chiang, Andreas F. Molisch

Systems and Control

Experimental Multi-site Testbed for Advanced Control and Optimization of Hybrid Energy Systems

Arash Omidi, Tanmay Mishra and Mads R. Almassalkhi

This paper presents a hybrid energy system (HES) experimental testbed developed at the University of Vermont, featuring a dual-site architecture that integrates on-campus laboratory facility with an off-campus solar and meteorological station. This supports the prototyping and validation of advanced HES control and optimization strategies. The platform integrates hardware-in-the-loop (HIL) simulations with a reconfigurable set of kVA-scale assets.A unified monitoring and communication architecture supports real-time data acquisition, model validation, and control implementation. The capabilities of the testbed are demonstrated through an HIL experiment in which a battery systems participate in solar PV smoothing.

Read the full abstract

Systems and Control

Design, Fabrication, and Measurement of a Hemispherical Multi-Layer Band-Pass Frequency Selective Surface

Ali Tehranian, Jordan Budhu, Casey Perkowski et al. (+4 more)

A hemispherical multilayer wide-band (7-13 GHz) band-pass frequency selective surface (FSS) is reported. A new design technique based on a Goldberg discretization and unit cell scaling technique is introduced to accommodate the curved profile of the FSS. The FSS is additively manufactured by sequentially printing dielectric layers and metallic patterns until 3 patterned silver-ink surfaces are integrated within a 4.5 mm (${\lambda_0}/6$ at 10 GHz) thick ABS hemispherical radome. The diameter and the height of the realized hemispherical FSS are around $5{\lambda_0}$ and $3{\lambda_0}$ respectively. Measurements demonstrate a roughly 1.7 dB insertion loss in the passband and 15-20 dB rejection in the stop-band. Additionally, a new postprocessing technique is used to suppress the effects of edge diffraction in the measured transmission spectrum. The design process, manufacturing technique, and measurement postprocessing represent novel advancements enabling future conformal frequency selective surfaces.

Read the full abstract

All authors Ali Tehranian, Jordan Budhu, Casey Perkowski, Lance Sookdeo, Kenneth H. Church, Garrett Harris, Carl Pfeiffer

Systems and Control · Cross-listed from cs.CR

RampoNN: A Reachability-Guided System Falsification for Efficient Cyber-Kinetic Vulnerability Detection

Kohei Tsujio, Mohammad Abdullah Al Faruque and Yasser Shoukry

Detecting kinetic vulnerabilities in Cyber-Physical Systems (CPS), vulnerabilities in control code that can precipitate hazardous physical consequences, is a critical challenge. This task is complicated by the need to analyze the intricate coupling between complex software behavior and the system's physical dynamics. Furthermore, the periodic execution of control code in CPS applications creates a combinatorial explosion of execution paths that must be analyzed over time, far exceeding the scope of traditional single-run code analysis. This paper introduces RampoNN, a novel framework that systematically identifies kinetic vulnerabilities given the control code, a physical system model, and a Signal Temporal Logic (STL) specification of safe behavior. RampoNN first analyzes the control code to map the control signals that can be generated under various execution branches. It then employs a neural network to abstract the physical system's behavior. To overcome the poor scaling and loose over-approximations of standard neural network reachability, RampoNN uniquely utilizes Deep Bernstein neural networks, which are equipped with customized reachability algorithms that yield orders of magnitude tighter bounds. This high-precision reachability analysis allows RampoNN to rapidly prune large sets of guaranteed-safe behaviors and rank the remaining traces by their potential to violate the specification. The results of this analysis are then used to effectively guide a falsification engine, focusing its search on the most promising system behaviors to find actual vulnerabilities. We evaluated our approach on a PLC-controlled water tank system and a switched PID controller for an automotive engine. The results demonstrate that RampoNN leads to acceleration of the process of finding kinetic vulnerabilities by up to 98.27% and superior scalability compared to other state-of-the-art methods.

Read the full abstract

Audio and Speech Processing

Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation

Wei-Cheng Tseng, Xuanru Zhou, Mingyue Huo et al. (+3 more)

Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales. We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation. To fill this gap, we present the first principled empirical study of ALP. We first introduce CaptionStew, a 10.7M caption dataset aggregating open-source audio-text corpora across multiple domains and captioning focuses. We then conduct the first comprehensive evaluation comparing contrastive and captioning objectives for learning audio representation across speech, music, and environmental sound tasks. Our results not only demonstrate that ALP yields competitive, transferable representations, but reveal critical trade-offs: contrastive learning offers superior data efficiency, while captioning exhibits better scalability. Furthermore, we find that the benefits of supervised initialization often diminish at larger scales, challenging common practices. By grounding these claims in empirical evidence, we establish a viable pathway toward general-purpose audio representation learning, guiding future research.

Read the full abstract

All authors Wei-Cheng Tseng, Xuanru Zhou, Mingyue Huo, Yiwen Shao, Hao Zhang, Dong Yu

Image and Video Processing · Cross-listed from cs.CV

Motion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions

Takuya Igaue, Catia Correia-Caeiro, Akito Yoshida et al. (+2 more)

Generating animal faces using generative AI techniques is challenging because the available training images are limited both in quantity and variation, particularly for facial expressions across individuals. In this study, we focus on macaque monkeys, widely studied in systems neuroscience and evolutionary research, and propose a method to generate their facial expressions using a style-based generative image model (i.e., StyleGAN2). To address data limitations, we implemented: 1) data augmentation by synthesizing new facial expression images using a motion transfer to animate still images with computer graphics, 2) sample selection based on the latent representation of macaque faces from an initially trained StyleGAN2 model to ensure the variation and uniform sampling in training dataset, and 3) loss function refinement to ensure the accurate reproduction of subtle movements, such as eye movements. Our results demonstrate that the proposed method enables the generation of diverse facial expressions for multiple macaque individuals, outperforming models trained solely on original still images. Additionally, we show that our model is effective for style-based image editing, where specific style parameters correspond to distinct facial movements. These findings underscore the model's potential for disentangling motion components as style parameters, providing a valuable tool for research on macaque facial expressions.

Read the full abstract

All authors Takuya Igaue, Catia Correia-Caeiro, Akito Yoshida, Takako Miyabe-Nishiwaki, Ryusuke Hayashi

Audio and Speech Processing

Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs

Wei-Cheng Tseng and David Harwath

Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader range of speech processing tasks. Building on this trend, we introduce Codec2Vec, the first speech representation learning framework that relies exclusively on discrete audio codec units. This approach offers several advantages, including improved data storage and transmission efficiency, faster training, and enhanced data privacy. We explore masked prediction with various training target derivation strategies to thoroughly understand the effectiveness of this framework. Evaluated on the SUPERB benchmark, Codec2Vec achieves competitive performance compared to continuous-input models while reducing storage requirements by up to 16.5x and training time by 2.3x, showcasing its scalability and efficiency.

Read the full abstract

Systems and Control · Cross-listed from cs.LG

Stabilizing Policy Gradient Methods via Reward Profiling

Shihab Ahmed, El Houcine Bergou, Aritra Dutta et al. (+1 more)

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from unreliable reward improvements and slow convergence, due to high variance in gradient estimations. In this paper, we propose a universal reward profiling framework that can be seamlessly integrated with any policy gradient algorithm, where we selectively update the policy based on high-confidence performance estimations. We theoretically justify that our technique will not slow down the convergence of the baseline policy gradient methods, but with high probability, will result in stable and monotonic improvements of their performance. Empirically, on eight continuous-control benchmarks (Box2D and MuJoCo/PyBullet), our profiling yields up to 1.5x faster convergence to near-optimal returns, up to 1.75x reduction in return variance on some setups. Our profiling approach offers a general, theoretically grounded path to more reliable and efficient policy learning in complex environments.

Read the full abstract

All authors Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang

Signal Processing

TFCDiff: Robust ECG Denoising via Time-Frequency Complementary Diffusion

Pengxin Li, Yimin Zhou, Jie Min et al. (+4 more)

Ambulatory electrocardiogram (ECG) readings are prone to mixed noise from physical activities, including baseline wander (BW), muscle artifact (MA), and electrode motion artifact (EM). Developing a method to remove such complex noise and reconstruct high-fidelity signals is clinically valuable for diagnostic accuracy. However, denoising of multi-beat ECG segments remains understudied and poses technical challenges. To address this, we propose Time-Frequency Complementary Diffusion (TFCDiff), a novel approach that operates in the Discrete Cosine Transform (DCT) domain and uses the DCT coefficients of noisy signals as conditioning input. To refine waveform details, we incorporate Temporal Feature Enhancement Mechanism (TFEM) to reinforce temporal representations and preserve key physiological information. Comparative experiments on a synthesized dataset demonstrate that TFCDiff achieves state-of-the-art performance across five evaluation metrics. Furthermore, TFCDiff shows superior generalization on the unseen SimEMG Database, outperforming all benchmark models. Notably, TFCDiff processes raw 10-second sequences and maintains robustness under flexible random mixed noise (fRMN), enabling plug-and-play deployment in wearable ECG monitors for high-motion scenarios. Source code is available at https://github.com/Miroircivil/TFCDiff.

Read the full abstract

All authors Pengxin Li, Yimin Zhou, Jie Min, Yirong Wang, Wei Liang, Qingling Xia, Wang Li

Image and Video Processing · Cross-listed from cs.CV

SurgSLOT: Segment Anything in Surgical Videos via Semantic Long-term Tracking

Haofeng Liu, Ziyue Wang, Sudhanshu Mishra et al. (+8 more)

Surgical scene understanding demands temporally consistent tracking of instruments and tissues. For clinical use, such tracking should generalize to new centers and procedure types, yet retraining for each of them is costly and not scalable. Interactive video object segmentation offers a way toward this generalization: the target is specified at inference by a first-frame visual prompt, so a model can generalize to unseen categories and new scenarios without retraining. However, training such a generalizable model demands spatio-temporal masklet annotations at a scale and procedural diversity that existing surgical benchmarks lack. We fill this gap with iSurg, the largest surgical segmentation benchmark to our knowledge, spanning six procedure types with over 170k frames, 410k object masks, and 2.4k masklets, including an in-house clinical dataset of four 30-minute videos. Yet tracking over such long videos remains challenging: the target needs to be re-identified among visually similar objects after long absences, while long-term memory has to judge whether each stored frame genuinely depicts the target, both demanding a stable object-level semantic identity. To this end, we propose SurgSLOT, a surgical segmentation generalist that segments any prompted target through two coupled modules built on this semantic identity: Temporal Semantic Learning learns it for re-identification, and Semantic-driven Long-term Memory reuses it to select reliable memory frames, suppressing identity drift over long procedures. On the SAM2 and SAM3 backbones, SurgSLOT reaches 81.0 and 82.8 Macro Average J&F under cross-dataset evaluation, surpassing their fine-tuned counterparts by 5.1 and 5.3 points and transferring zero-shot to an unseen procedure type and unseen object categories, with the SAM2 version running in real time at 68 FPS.

Read the full abstract

All authors Haofeng Liu, Ziyue Wang, Sudhanshu Mishra, Mingqi Gao, Guanyi Qin, Chang Han Low, Alex Y. W. Kong, Zhu Zhuo, Huazhu Fu, Joseph S. Ng, Yueming Jin

Signal Processing · Cross-listed from quant-ph

Variational Quantum Integrated Sensing and Communication

Ivana Nikoloska and Osvaldo Simeone

The integration of sensing and communication functionalities within a common system is one of the main innovation drivers for next-generation networks. In this paper, we introduce a quantum integrated sensing and communication (QISAC) protocol that leverages entanglement in quantum carriers of information to enable both superdense coding and quantum sensing. The proposed approach adaptively optimizes encoding and quantum measurement via variational circuit learning, while employing classical machine learning-based decoders and estimators to process the measurement outcomes. Numerical results for qudit systems demonstrate that the proposed QISAC protocol can achieve a flexible trade-off between classical communication rate and accuracy of parameter estimation.

Read the full abstract

Systems and Control · Cross-listed from cs.LO

Synthesis of Safety Specifications for Probabilistic Systems

Gaspard Ohlmann, Edwin Hamel-De le Court and Francesco Belardinelli

Ensuring that agents satisfy safety specifications can be crucial in safety-critical environments. While methods exist for controller synthesis with safe temporal specifications, most existing methods restrict safe temporal specifications to probabilistic-avoidance constraints. Formal methods typically offer more expressive ways to express safety in probabilistic systems, such as Probabilistic Computation Tree Logic (PCTL) formulas. Thus, in this paper, we develop a new approach that supports more general temporal properties expressed in PCTL. Our contribution is twofold. First, we develop a theoretical framework for the Synthesis of safe-PCTL specifications. We show how the reducing global specification satisfaction to local constraints, and define CPCTL, a fragment of safe-PCTL. We demonstrate how the expressiveness of CPCTL makes it a relevant fragment for the Synthesis Problem. Second, we leverage these results and propose a new Value Iteration-based algorithm to solve the synthesis problem for these more general temporal properties, and we prove the soundness and completeness of our method.

Read the full abstract

Systems and Control · Cross-listed from cs.CR

Auditable Ledger Snapshot for Non-Repudiable Cross-Blockchain Communication

Tirthankar Sengupta, Bishakh Chandra Ghosh, Sandip Chakraborty et al. (+1 more)

Blockchain interoperability is increasingly recognized as the centerpiece for robust interactions among decentralized services. Blockchain ledgers are generally tamper-proof and thus enforce non-repudiation for transactions recorded within the same network. However, such a guarantee does not hold for cross-blockchain transactions. When disruptions occur due to malicious activities or system failures within one blockchain network, foreign networks can take advantage by denying legitimate claims or mounting fraudulent liabilities against the defenseless network. In response, this paper introduces InterSnap, a novel blockchain snapshot archival methodology, for enabling auditability of crossblockchain transactions, enforcing non-repudiation. InterSnap introduces cross-chain transaction receipts that ensure their irrefutability. Snapshots of ledger data along with these receipts are utilized as non-repudiable proof of bilateral agreements among different networks. InterSnap enhances system resilience through a distributed snapshot generation process, need-based snapshot scheduling process, and archival storage and sharing via decentralized platforms. Through a prototype implementation based on Hyperledger Fabric, we conducted experiments using on-premise machines, AWS public cloud instances, as well as a private cloud infrastructure. We establish that InterSnap can recover from malicious attacks while preserving crosschain transaction receipts. Additionally, our proposed solution demonstrates adaptability to increasing loads while securely transferring snapshot archives with minimal overhead.

Read the full abstract

All authors Tirthankar Sengupta, Bishakh Chandra Ghosh, Sandip Chakraborty, Shamik Sural

Image and Video Processing · Cross-listed from cs.LG

Saving Foundation Flow-Matching Priors for Inverse Problems

Yuxiang Wan, Ryan Devera, Wenjie Zhang et al. (+1 more)

Foundation flow-matching (FM) models promise universal priors for solving inverse problems (IPs); yet today, they trail behind domain-specific and even untrained priors. How can we unlock their potential? We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. For evaluation, we consider both simple image restoration tasks and scientific IPs with a few similar samples – where the prohibitive cost of data collection and model training hinders the development of domain-specific generative models. Our superior experimental results confirm the effectiveness of FMPlug. Overall, FMPlug paves the way for making foundation FM models practical, reusable priors for IPs, especially scientific ones with few similar samples. More details are available at https://sun-umn.github.io/xm-plug/ .

Read the full abstract

All authors Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun