Peer Revenue Impact factor: volatile

Papers

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

Electrical Engineering and Systems Science

eess Watch Electrical Engineering and Systems Science

Saturday 1 August

Systems and Control · Cross-listed from cs.RO

Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization

Daojie Peng, Fulong Ma, Bingtao Wang et al. (+2 more)

Deploying billion-parameter Vision-Language-Action (VLA) policies on mobile robots creates a systems conflict: semantic reasoning benefits from cloud GPUs, whereas closed-loop control must respond locally despite network delay and jitter. Existing hierarchical and asynchronous policies improve throughput, but their slow-path representations can still arrive stale or require explicit scheduling and delay cues. We introduce CloudEdgeVLA, a cloud-edge policy that treats temporal misalignment as a representation-learning problem. A cloud VLA encodes delayed observations into slowly varying task features, while a lightweight edge head combines the latest available cloud feature with current local vision. During training, current and randomly delayed frames are paired with the same current action target in fresh and stale paths. This objective encourages the cloud representation to preserve task-level information while the edge path supplies state-sensitive corrections, driving emergent specialization. Across four LIBERO suites, CloudEdgeVLA retains 63.8-78.0% success with a 40-step uniform-delay window, whereas VLASH reaches at most 6.4% and the evaluated single-path baselines at most 3.0%. By removing blocking synchronization from the control loop, the design offers a practical route to scalable VLA deployment in which cloud models can grow while edge computation remains lightweight and responsive.
Read the full abstract

All authors Daojie Peng, Fulong Ma, Bingtao Wang, Sheng Wang, Jun Ma

Audio and Speech Processing · Cross-listed from cs.CL

The Learning Objective Governs Perceptual Narrowing: A Cross-Lingual, Layer-Wise, Ten-Seed Study of Self-Supervised Speech Encoders

Sejin Yoo

Perceptual narrowing—the developmental loss of non-native phoneme discrimination in the first year of life \citep{werker1984}—is a canonical developmental finding, yet what learning objective produces it remains open. We train a \(\sim\)7\,M-parameter Transformer encoder on child-directed and read speech and evaluate phoneme ABX in English, French, and Mandarin over ten seeds, the seed as the unit of replication. Six results. (1)~The objective sets the direction of cross-lingual transfer: reconstruction (masked mel-prediction) degrades non-native discrimination, prediction (frame-contrastive) improves it—a same-encoder, same-data gap of \(+0.051\) in first-layer Mandarin ABX (\(p=3\times10^{-8}\)), unanimous in sign across twenty runs. (2)~That decline combines a large arm-intrinsic difficulty gradient with a smaller language-specialization effect (matched vs.\ mismatched \(+0.022\), \(p=10^{-4}\), all four layers). (3)~Against a language-symmetric raw-mel floor, reconstruction pushes the first layer below the discriminability of its input; prediction pushes it above. (4)~Read speech gives a \(3.6\times\) steeper non-native decline than child-directed speech. (5)~The customary three-seed budget cannot see this reliably: an effect unambiguous at ten seeds is called significant by as few as 70% of three-seed subsets. (6)~Six objective configurations—sharpening, compression, consolidation, their composition, and word-level semantic grounding in two forms—fail to produce the full developmental signature (native improves and non-native declines): a single objective moves both languages the same way because it acts on a shared representation. We conclude that the objective, not the architecture, is the first-order determinant of narrowing-shaped representational change.
Read the full abstract

Image and Video Processing

Streamable Neural Video Compression: A Mixed Precision Approach for Cross-Platform Deployment

Kasidis Arunruangsirilert, Heming Sun and Jiro Katto

Neural Video Codecs (NVCs) offer unprecedented rate-distortion performance, making them highly attractive for bandwidth-constrained environments like 5G cellular networks and emerging satellite direct-to-cell (D2C) links. However, deploying NVCs in real-world streaming applications is severely hindered by cross-platform floating-point non-determinism, which causes arithmetic entropy coders to desynchronize and crash across different GPU architectures. While recent integer-based quantization methods address this, they incur either massive degradation in compression efficiency (INT8) or severe computational bottlenecks by bypassing hardware acceleration (INT16). In this paper, we propose a streamable, client-server NVC architecture featuring a novel Mixed Precision (FP16/FP32) strategy. By strategically executing P-frames in hardware-accelerated FP16 for real-time throughput, while forcing I-frames and periodic feature-adapter resets to IEEE-754 compliant FP32, we guarantee deterministic synchronization at critical boundaries. Through extensive cross-encode/decode evaluations across 12 GPUs spanning four architectural generations, we demonstrate that our approach successfully eliminates intra-generation fragmentation and substantially broadens cross-die interoperability, achieving seamless cross-generation decodability for recent architectures at 1080p. Crucially, this is achieved with a negligible impact on compression efficiency. Furthermore, we evaluate the system's end-to-end latency across diverse real-world networks, including Wi-Fi 6, 5G NR (FDD/TDD), and Starlink D2C, proving the practical viability of streamable learned video compression while highlighting unique challenges in Non-Terrestrial Networks.
Read the full abstract

Signal Processing

Multi-Dimensional Entropy for Vibration Data Quality Control in Wind Turbines: Properties, Deployment, and Industrial Implications

Deshui Li, Xiao-Ming Yuan, Zishun Wang et al. (+1 more)

Erroneous vibration signals caused by sensor malfunction, shutdown transients, and abnormal acquisition conditions can degrade the reliability of automated industrial monitoring pipelines. This paper presents a deployment-oriented analysis of Multi-Dimensional Entropy (MDE) for vibration data quality control in wind turbines, focusing on computational efficiency, model-agnostic capability, physical interpretability, and robustness. Experiments on 57,643 labeled industrial vibration records from 12 wind farms and 14 turbine units, covering main bearings, gearboxes, and generators, together with cross-platform deployment validation and cross-turbine generalization tests on 4,152 unseen records from 3 additional wind farms, show that MDE provides a stable and discriminative feature representation across different classifiers and heterogeneous operating conditions while maintaining low computational and memory requirements. These results demonstrate that MDE can serve as a lightweight and deployment-ready feature layer for vibration data quality control, thereby improving the reliability of industrial monitoring pipelines and reducing the risk of error propagation into downstream diagnostic and prognostic tasks in wind energy applications.
Read the full abstract

All authors Deshui Li, Xiao-Ming Yuan, Zishun Wang, Min Zhang

Systems and Control

SPIRAL-PO: Symbolic Identification of Partially Observed Nonlinear Dynamics with Application to Rotating Machinery

Mohammad A. Ayoubi and Sina Piramoon

Many engineering systems have states that cannot be directly measured-tilt angles in rotating machines, internal flow variables, aeroelastic modes-yet these hidden states couple into the measured outputs. This paper addresses identifying the governing equations from such partial observations. We present SPIRA-PO (Symbolic Physics-Informed Residual Augmentation Loop-Partially Observed), a framework that treats hidden-state effects not as nuisances to be eliminated but as structured, physically interpretable signatures in the observable equations of motion. From a minimal physics seed in measured coordinates, the method fits a multi-output residual network to the projection residual, projects the learned structure onto a physics-constrained candidate library, and admits terms through a sequential statistical gating protocol. We give sufficient conditions for unique recovery of the hidden-coupling coefficients, a matching impossibility result showing that insufficiently rich excitation makes recovery impossible for any estimator, and a closed-form sample-complexity bound. These guarantees concern the projected hidden-coupling coefficients, not the hidden trajectory itself, which is reconstructed separately by a state estimator. The framework is demonstrated on a vertical flexible rotor with Duffing supports, where only the lateral displacements are measured while the tilt angles remain hidden. A constant-speed run is provably unidentifiable, whereas a speed sweep restores identifiability; from noisy coast-down data, SPIRAL-PO recovers the gyroscopic coupling, the Duffing nonlinearity, and the translation-tilt cross-coupling, each with a standard error and t-statistic. An Extended Kalman Filter built on the validated model then reconstructs the hidden tilt trajectory from observed displacements alone.
Read the full abstract

Audio and Speech Processing

Anomalous Sound Detection Meets Noise-Aware Self-Supervised Learning

Takuya Fujimura, Gordon Wichern, Yoshiki Masuyama et al. (+5 more)

In this paper, we introduce noise-aware self-supervised learning (NA-SSL) models for noise-aware anomalous sound detection (NA-ASD). NA-ASD is an ASD task with two-channel audio recordings, where one microphone is located close to the target machine and the other is located farther away to capture noise. For this task, we simulate two-channel recordings using diverse audio datasets and train NA-SSL models to extract clean SSL representations of the close-microphone signal by using the far-microphone recording dominated by background noise as auxiliary information. The NA-SSL models are then used as frontends in the standard ASD framework. Our experimental evaluation on the DCASE 2026 Challenge Task 2 development dataset demonstrates the effectiveness of the NA-SSL framework across three base SSL models (BEATs, EAT, and Dasheng), both with and without discriminative fine-tuning. Furthermore, the challenge results proved the effectiveness of the proposed approach, where the NA-BEATs system won the challenge by a large margin, achieving an official score of 70.24%, while the second-place system achieved 65.46%.
Read the full abstract

All authors Takuya Fujimura, Gordon Wichern, Yoshiki Masuyama, Christoph Boeddeker, Kohei Saijo, Julius Richter, Takahiro Edo, Jonathan Le Roux

Signal Processing

LOCUS-DT: Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins

Haozhe Lei, Roberto Bomfin, Marwa Chafii et al. (+1 more)

Accurate indoor localization is essential for emerging applications in robotic navigation and search and rescue. While classical methods typically focus on single-point estimates, complex indoor environments with heavy blockage and multipath propagation often lead to multimodal likelihood surfaces where a single estimate is insufficient. This paper proposes LOCUS-DT (Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins), a framework that treats snapshot localization as posterior inference over the transmitter location. By leveraging a ray-tracing-based digital twin (DT) of the known environment, LOCUS-DT generates synthetic multipath profiles for candidate locations and compares them against the measured channel profile. Central to our approach is a novel learned scoring function designed to compare a fixed number of dominant specular paths, providing robustness against errors in both the DT environment model and the physical channel estimation. Importantly, LOCUS-DT is trained over an ensemble of environments to ensure generalization to unseen layouts. We evaluate the system using a Sionna-based ray-tracing backend, demonstrating that LOCUS-DT captures the sharp, multimodal posterior structures inherent in indoor settings more accurately than standard Gaussian or Gaussian-mixture benchmarks.
Read the full abstract

All authors Haozhe Lei, Roberto Bomfin, Marwa Chafii, Sundeep Rangan

Signal Processing · Cross-listed from cs.RO

Embodied Passive Aeroacoustic Perception Enables Relative Sensing and Pursuit Between Aerial Robots

Yanbaihui Liu, Ravi Prakash, Li-Yu Lo et al. (+2 more)

Aerial robots generate structured aeroacoustic fields during flight, yet these signals have been underexplored as a source of onboard relative perception, particularly under the strong ego-acoustic interference generated during simultaneous flight in various outdoor conditions. We introduce embodied passive aeroacoustic perception, a sensing paradigm in which an aerial robot infers actionable relative-state information from the naturally generated sound of flight while operating within its own evolving aeroacoustic field. We present SonicFly, a passive aeroacoustic perception framework that enables one unmanned aerial vehicle to estimate and follow another using only the leader's intrinsic flight sound, without active acoustic signaling, inter-robot communication, GPS sharing, or external sensing infrastructure. The system uses a lightweight four-microphone array, rotorcraft-informed acoustic representations, a neural bearing-range estimator, and confidence-gated filtering for closed-loop flight. Through acoustic characterization, onboard localization, and outdoor pursuit experiments, we show that multirotor aeroacoustic signals contain sufficient information to support relative perception despite strong ego-acoustic interference, environmental variability, and changing flight geometry. During acoustic-only pursuit, SonicFly achieved a mean distance-maintenance error of 1.34 m across diverse outdoor trajectories and operating conditions. Analysis of the acoustic channel reveals design principles governing embodied passive aeroacoustic perception, including the roles of harmonic structure, spectral separability, and spatial acoustic cues in determining observability. Our results establish the feasibility of embodied passive aeroacoustic perception for aerial robots and suggest that naturally generated behavioral signals can serve as information for robotic perception and coordination.
Read the full abstract

All authors Yanbaihui Liu, Ravi Prakash, Li-Yu Lo, Nils Roede, Boyuan Chen

Systems and Control · Cross-listed from cs.IT

GNN-RSMA: An Interference Management Framework for a Large-Scale HAPS Network

Afsoon Alidadi Shamsabadi, Animesh Yadav and Halim Yanikomeroglu

Integrating non-terrestrial networks (NTN) with terrestrial infrastructure is a key enabler of next-generation wireless systems, providing ubiquitous connectivity while meeting stringent rate and latency requirements. In particular, high altitude platform stations (HAPS) can complement terrestrial networks and jointly form vertical heterogeneous networks (vHetNets), extending coverage while delivering high-capacity, reliable, and low-latency connectivity for user equipments (UEs) including ground users and uncrewed aerial vehicles (UAVs). However, the high altitude deployment of HAPS establishes strong line-of-sight (LoS) links to UEs, creating highly correlated channels among UEs. Moreover, the wide coverage footprint of HAPS enables it to serve a large number of UEs, forcing limited radio resources to be shared among many UEs and resulting in significant intra-resource block (RB) interference. To address this challenge, we propose an interference management scheme based on UE clustering and rate-splitting multiple access (RSMA). Specifically, the network is modeled as a heterogeneous graph, and a graph neural network (GNN) is developed to efficiently allocate the common and private RSMA powers, maximizing the minimum spectral efficiency (SE) in a fast and scalable manner. Simulation results demonstrate that the proposed GNN-RSMA interference management algorithm outperforms conventional multiple access schemes while achieving fairness and worst-user performance comparable to successive convex approximation (SCA)-based optimization at only a fraction of its computational cost.
Read the full abstract

Systems and Control

Discovering Explicit Magnetic Core Loss Equations via Learnable Symbolic Sparse Identification

Haoyu Wang, Jialin Zheng, Yihao Wu et al. (+2 more)

Explicit magnetic core loss equations with simple expressions and physical interpretability are significant tools in the design of high-frequency power magnetics. Traditional fits to empirical data like the Steinmetz Equation (SE) often struggle with accuracy, whereas modern machine learning approaches improve precision but deviate from physics. To fill this gap, this paper proposes a Learnable Symbolic Sparse Identification (LSSI) framework for data-driven equation discovery. Specifically, LSSI reformulates magnetic core loss equations for sinusoidal drives as a symbolic regression problem derived directly from experimental data. Building upon the SE, an expanded library of candidate functions are introduced and a sparse identification framework is implemented to select the dominant ones. More importantly, crucial parameters like exponents and coefficients of candidate functions are treated as learnable ones, simultaneously achieving equation simplicity and high expressiveness of the underlying fractional power laws. Experimental results demonstrate that LSSI achieves superior accuracy with a state-of-the-art $\mathbf{R^2}$ of $\mathbf{0.9999}$ and a MAPE of $\mathbf{1.04\%}$ through a highly compact explicit equation containing only $\mathbf{4}$ active terms. Furthermore, it drastically reduces the parameter count from $\mathbf{4417}$ in neural network methods to $\mathbf{15}$, showcasing exceptional compactness and efficiency. The LSSI framework thus provides a physically transparent and highly accurate solution suitable for complex modern magnetic characterization and design.
Read the full abstract

All authors Haoyu Wang, Jialin Zheng, Yihao Wu, Ziyang Xu, Alex Hanson

Systems and Control · Cross-listed from cs.RO

A Robotic System for Automated Manufacturing of Dielectric Elastomer Actuators

Van Remenar, Anatol Gogoj, Ang Li et al. (+4 more)

This letter presents an automated robotic manufacturing system for soft capacitors which operate as actuators and sensors. Emphasis is placed on the two processes that most directly govern device quality, dielectric layer formation by spin coating and carbon nanotube (CNT) electrode application by stamping. Twenty multilayer DEAs, each comprising 12 dielectric layers with a mean thickness of 55.37 +- 2.04 um and 11 alternating CNT electrodes, were fabricated reducing total process time by 14.2% and removing the operator from 56.1% of it.
Read the full abstract

All authors Van Remenar, Anatol Gogoj, Ang Li, Tomas Verardi, Matei Mandoiu, Victor Jimenez Santiago, Mihai Duduta

Signal Processing

Agent-Native Task-Oriented Communication with Joint Token Compression Coding and Modulation

Zhuoran Xiao, Yihang Huang, Tianyu Jiao et al. (+2 more)

As large foundation models empower agents to become pervasive across industries and emerge as central actors in intelligent systems, a fundamental rethinking of communication paradigms toward AI-native, agent-centric designs in the post-Shannon era becomes inevitable. One essential shift is that tokens, which are the minimal semantic units natively processed by large language models (LLMs), should replace bits as the fundamental unit of communication. However, existing works in the LLMs field assume lossless token transmission over high-speed wired links and largely neglect the air-interface overhead and channel distortions inherent in wireless environments, lacking a native design for wireless token communication systems. To bridge this gap, we propose an innovative design for a token transmitter-receiver architecture that facilitates task-oriented token transmission. Specifically, we propose JTCM (Joint Token Coding and Modulation), an AI-native semantic communication framework that jointly optimizes token representation, channel coding, and modulation to maximize downstream task performance directly. Correspondingly, we propose a two-stage training scheme. In the first stage, the token encoder-decoder pair is pre-trained to enable semantic-preserving compression and reconstruction. In the second stage, it is fine-tuned end-to-end with a multi-modal foundation model under specific downstream tasks to achieve task-aware optimization. Extensive experiments demonstrate that JTCM significantly reduces transmission overhead while enhancing task accuracy and robustness compared to state-of-the-art baselines in bandwidth- and SNR-constrained wireless channels.
Read the full abstract

All authors Zhuoran Xiao, Yihang Huang, Tianyu Jiao, Xiaohua Xu, Yin Xu

Friday 31 July

Image and Video Processing

Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models

Hongxin Xu, Jianping Mei, Can Wang et al. (+1 more)

Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image from the stego. Existing diffusion-based CIS methods can generate natural-looking stego images but preserve substantial visual similarity to the secret image. This resemblance risks exposing structural and semantic cues, giving rise to security vulnerabilities that cannot be evaluated solely via recovery fidelity. Achieving substantial visual dissimilarity between the secret and stego images without compromising stego quality and recovery fidelity remains challenging. To address this issue, we propose InvCISD, an invertible diffusion framework that couples the latent representations of the secret and an irrelevant reference image with an invertible network called LIMNet. We first train LIMNet in diffusion latent space, followed by end-to-end fine-tuning of the entire network, i.e., LIMNet integrated diffusion inversion and generation modules. Experiments demonstrate that the proposed method substantially reduces secret-stego visual similarity, improves stego quality, and retains satisfactory secret reconstruction quality. Our further investigation shows that all evaluated methods are highly detectable by the CIS-oriented steganalysis model, indicating that resistance against targeted steganalysis constitutes a critical direction for future CIS research.
Read the full abstract

All authors Hongxin Xu, Jianping Mei, Can Wang, Defang Chen

Signal Processing

VSWR-Resilient Mm-Wave and Cm-Wave PAs for Large-Scale Phased Arrays

Chenhao Chu, Masoud Pashaeifar, Filippo Svelto et al. (+1 more)

Large-scale mm-Wave and cm-Wave phased arrays have become central to wireless communication and sensing systems, including terrestrial 5G/6G links and base stations, non-terrestrial networks (NTNs), satellite communication (SATCOM), radar, and relay applications. In dense arrays, power amplifiers (PAs) and antenna array interact with each other: array radiation depends on the amplitude/phase of PA output signals, while the load impedance experienced by each PA varies with frequency, scan angle, and element position. This active antenna impedance, described as voltage standing wave ratio (VSWR) variation, arises mainly from antenna inter-element mutual coupling and is shaped by package/interconnect parasitics. Each PA can deviate from its optimum large-signal operating condition, degrading output power, power gain, power-added efficiency, AM-AM/AM-PM, and reliability margin. These variations further affect array EIRP consistency, EVM headroom, link budget, thermal density, and beamforming calibration, complicating PA design for wideband, wide-scan-angle arrays. This review introduces the origins of antenna VSWR and antenna-PA interactions connecting the antenna reflection coefficient $\Gamma_{\mathrm{ant}}$ and PA output matching $S_{22}$ to delivered-power and transmitted-phase variation through the $S_{22}\Gamma_{\mathrm{ant}}$ dependence. Reverse-coupled excitation and reverse intermodulation distortion (RIMD) are discussed. This motivates PA designs that achieve simultaneous output and loadline matching (SOLM), enabling a small output reflection coefficient $|S_{22}|$ without significantly compromising large-signal performance. Recent mm-Wave and cm-Wave VSWR-resilient integrated PA techniques and demonstrations are reviewed. Finally, challenges and opportunities for compact, load-insensitive, energy-efficient, high-power-density, and calibration-scalable integrated PAs are discussed.
Read the full abstract

All authors Chenhao Chu, Masoud Pashaeifar, Filippo Svelto, Hua Wang

Systems and Control · Cross-listed from cs.RO

Belief-Space Perception Routing under Coupled Sensor Faults and Compute Contention

Sparsh Roy, Vihan Aggarwal and Davin Yin

A robot that has to see and react on a fixed clock runs into two problems at once. Its cameras degrade in rain, mud, fog, and darkness. And the single onboard processor it runs on is shared with planning and control, so the compute left over for perception moves around from second to second. Most systems model the two separately. We present a perception router that tracks probabilistic estimates of sensor-fault state and compute- contention state, couples them with a noisy-OR term, and uses the coupled estimate to pick one of four detector configurations (YOLO11x/n at 1280 or 640 px) so that the frame finishes before its deadline. Where the two stressors co-occur, the coupled policy cuts the deadline-miss rate by 1.1 to 9.4 percentage points against a policy that treats them independently. The interval excludes zero in five of six conditions, the pooled effect over 10 sequences and 6 conditions has sign-test p = 0.001, and every uncoupled control and the fault-free trajectory sit at exactly 0.0 pp. Routing costs tens of microseconds per frame. We then asked whether the coupling the method exploits arises on its own. Across eight real RADIATE adverse-weather sequences and three workload proxies independent of the fault signal, after Benjamini-Hochberg correction and a replication run, none of 24 tests found it. We report that null and scope the routing result as a proof of mechanism. Whether such coupling occurs in the field is still open, and the released evaluation pipeline lets a deployment settle it on its own traces.
Read the full abstract

Systems and Control · Cross-listed from cs.LG

Neural Operator Learning for Collision-Aware Trajectory Planning of Spacecraft Swarms

Sidhdharth D. Sikka, Suyi Gao, Zehui Lu et al. (+2 more)

Satellite constellations require orbital transfers that are both fuel efficient and collision avoidant. Yet, the computational cost of optimization methods traditionally used to plan their trajectories scales poorly with both the number of satellites as well as the number of obstacles to avoid, due to the pairwise safety constraints. In this work, we introduce a permutation-equivariant neural operator for trajectory planning of spacecraft swarms. This neural operator maps distributions of spacecraft initial states, target states, and obstacle initial states to trajectories which avoid collision and conserve fuel. This neural operator output is then paired with a batched Gauss-Newton finish to enforce exact orbital dynamics, and further reduce fuel use. The operator is self-supervised, trained without optimal trajectory labels. When trained on ten spacecraft, the proposed method generalized zero-shot to swarms of 1,000 spacecraft and 11,000 obstacles. The generated trajectories matched a per-agent optimal control solver's accuracy while retaining collision avoidance. Operator learning grounded in physics may offer a fast, scalable alternative to trajectory optimization in the increasingly crowded orbits of the future.
Read the full abstract

All authors Sidhdharth D. Sikka, Suyi Gao, Zehui Lu, Rongjie Lai, Shaoshuai Mou

Systems and Control · Cross-listed from cs.RO

Towards General Language-Conditioned Latent Safety Filters

Ihab Tabbara, Yuxuan Yang and Hussein Sibai

Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural language. Safe deployment, however, requires adapting not only to new tasks but also to varying safety requirements across users, environments, and applications. Existing safety filters remain largely constraint-specific and thus must be redesigned or relearned when safety requirements change. In this paper, we investigate language-conditioned safety filtering, in which a Hamilton-Jacobi safety actor and critic are conditioned on language-specified constraints. We evaluate this formulation across pick-and-place, table-wiping, and block-stacking tasks in the vision-based setting, examining its ability to enforce language-specified constraints and transfer to unseen constraint instances within the evaluated constraint families. Our experiments provide evidence that language-conditioned safety filters reduce constraint violations and exhibit partial transfer to unseen constraint instances.
Read the full abstract

Image and Video Processing

Fused electrical impedance tomography using an electromagnetically tracked handheld probe for oral cancer margin assessment: reconstruction methods and phantom validation

Sophie A Lloyd, Ehsan Nasiri, Allaire F Doussan et al. (+2 more)

Objective: Positive margins in oral squamous cell carcinoma (OSCC) resection are common and significantly impact patient outcomes. Electrical impedance tomography (EIT) can be used to intraoperatively distinguish cancer from healthy tissue. The objective of this study was to develop and identify a fused EIT approach to accurately reconstruct a tumor boundary using multiple impedance measurements recorded with a handheld electrical impedance probe. Approach: Simulations and noise analyses were used to investigate the best reconstruction method for fused EIT, and a measured phantom experiment was conducted to evaluate the EIT reconstructions. Main results: Fused approaches successfully and accurately recovered the conductivity boundary location from multiple probe sites, increasing boundary localization to within 0.5 mm of the true boundary for both simulated and experimental results. Simulations and noise analysis revealed that all reconstruction methods maintain strong classification accuracy with added noise on a half-plane boundary scenario and fused difference EIT is the most robust to all types of added noise, due to the high data redundancy in the reconstruction formulation. Significance: The measured multi-site probe experiments represent important steps in the development of an approach that can combine EIT from multiple locations to increase boundary localization accuracy. Overall, this result is a step towards a clinically deployable impedance imaging approach to scanning the entire tumor boundary, which could significantly help to improve surgical outcomes for OSCC.
Read the full abstract

All authors Sophie A Lloyd, Ehsan Nasiri, Allaire F Doussan, Ryan J Halter, Ethan K Murphy

Image and Video Processing

Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation

Xuan Cuong Ngo

Recent radiology-adapted vision-language models have achieved strong performance on standard report generation benchmarks, yet their robustness and generalization remain constrained by imperfect alignment and correlation between visual and textual features. Existing methods connect image and text either implicitly through autoregressive report supervision or explicitly through contrastive learning. However, autoregressive supervision alone is insufficient to establish reliable image-text alignment, while contrastive learning can push apart unpaired reports that describe related pathologies simply because they are not paired with the same image. This is problematic in radiology, where different reports may share compatible pathology semantics rather than being true negatives. As a result, the learned representation may fail to organize images and reports around shared pathology concepts, causing the decoder to rely on pretrained language priors and generate clinically plausible reports that are not fully supported by radiographic evidence. To address this issue, we propose PALM, a pathology-aware alignment framework for radiology report generation. Instead of directly matching each image-report pair while separating all others, PALM aligns visual and textual features through shared pathology prototypes. These prototypes provide a clinically meaningful bridge between radiographic evidence and textual findings, allowing cases with similar pathology semantics to move toward common concepts without separating compatible cases. In addition, we introduce Masked Evidence Modeling to strengthen the image encoder sensitivity to local radiographic evidence by learning semantic changes caused by masked image regions. Experiments on MIMIC-CXR, IU X-Ray, and MIMIC-ABN show that PALM consistently improves both report generation and abnormality-focused robustness.
Read the full abstract

Systems and Control · Cross-listed from astro-ph.IM

A Comparative Systems-Engineering Framework for RFI Coexistence in Radio Astronomy and Aviation Safety Systems

Simthembile Dlamini

Radio astronomy and aviation safety systems occupy opposite ends of the signal-power spectrum, yet both depend on the same finite resource and are increasingly squeezed by commercial broadband wireless services. The two fields protect their receivers using separately derived, apparently incommensurable criteria: the ITU-R RA.769 detrimental-interference threshold for radio telescopes, and the radar-altimeter interference thresholds established by RTCA Special Committee 239 for the 5G C-band coexistence problem. We introduce a single coexistence-margin framework, M(f,d) = Pth(f) - Prx(f,d), and show both criteria to be special cases of it. We apply this framework to two case studies, the Karoo Radio Quiet Zone surrounding MeerKAT and SKA-Mid, and the global 5G C-band/altimeter dispute, showing that, despite unrelated regulatory histories, both converged on the same three-lever solution: guard-band separation, bounded exclusion zones, and receiver-side filtering, governed by mandatory coordination rather than static exclusion. We then show that interference-excision, beamforming, and statistical-calibration pipelines developed for radio interferometry are closely analogous to, and in several cases directly reusable for, operations required by ADS-B validation, phased-array radar clutter rejection, and predictive-maintenance anomaly detection. The unifying framework, and the finding that two independently-arising regulatory histories converge on the same design pattern, is this papers central contribution: M(f,d) has not, to our knowledge, been proposed before as a common formalism spanning these two protection regimes, and the toolkit mapping distinguishes genuine reuse from looser analogy. The result is a reusable design pattern and shared skills/infrastructure pipeline, applicable wherever a narrowband receiver must coexist with a growing broadband commercial neighbour.
Read the full abstract

Signal Processing

Artificial Intelligence for Spatially Reconfigurable Antennas: Movable, Fluid, and Pinching Antenna Systems

Nguyen Cong Luong, Zeping Sui, Thai-Hoc Vu et al. (+10 more)

Recently, sixth-generation (6G) wireless networks have moved beyond fixed-array designs toward antenna architectures that can adapt their spatial configuration to specific environmental conditions. Movable antenna, fluid antenna, and pinching antenna systems represent this principle in different ways, but they share a common vision: exploiting spatial flexibility as an additional degree of freedom (DoF) to improve communication, sensing, security, and resource efficiency. These new techniques, however, also bring challenging problems, as antenna configuration must be jointly considered with channel acquisition, beamforming, mobility, and network resource management. Therefore, artificial intelligence (AI) has become an important tool for learning fast and adaptive control policies for these highly coupled systems. In this survey, we provide a unified review of AI for spatially reconfigurable antenna systems. We first introduce the basic principles of movable, fluid, and pinching antennas, which is followed by a summary of the latest AI-enabled designs according to their primary optimization objectives. Furthermore, we compare the roles of deep learning (DL), deep reinforcement learning (DRL), multi-agent reinforcement learning (MARL), graph learning, Transformers, large language models (LLMs), and structure-guided learning across different antenna architectures. Finally, we discuss open challenges and future directions toward scalable, robust, and hardware-aware intelligent reconfigurable antenna networks.
Read the full abstract

All authors Nguyen Cong Luong, Zeping Sui, Thai-Hoc Vu, Jie Cao, Bo Ma, Thuan Van Le, Xunyang Zhan, Nguyen Duc Hai, Min Xu, Qiushi Zhao, Dong In Kim, Yonghong Zeng, Shaohan Feng

Systems and Control

Dynamical principles of habituation across substrates and scales

Matthew Smart, Stanislav Y. Shvartsman and Martin Mönnigmann

Habituation is a basic form of learning in which a system's response to repeated stimulation progressively diminishes but eventually recovers when the stimulus is withheld. Long studied in animals, it has increasingly been observed in unicellular organisms and non-living devices such as electronic circuits and neuromorphic materials, suggesting underlying dynamical principles that recur across domains. This review asks what those principles are: given qualitative constraints imposed by habituation on a system's response, what is the minimal dynamical structure that satisfies them? We formalize the classical hallmarks of habituation as behavioral constraints on input–output behavior, show that linear time-invariant systems are structurally incompatible with these constraints, and construct nonlinear motifs—linear fading-memory dynamics composed with static nonlinearities—that exhibit the hallmarks across diverse settings. We relate these motifs to models of specific biological systems and to physical and algorithmic realizations, from analog circuits to transient computation in machine learning.
Read the full abstract

Systems and Control

The Anatomy of RF Chains: Metrics, Measures, and Operating Efficiency

Leonid Belostotski, Arjuna Madanayake, John Nielsen et al. (+6 more)

In 1958, Haus and Adler [1] introduced the concept of noise measure. Noise measure is a single quantitative metric that provides a comprehensive basis for comparing devices (individual circuits or outcomes of optimization iterations) in terms of their contribution to overall system noise by incorporating both noise factor and available power gain. Unlike noise factor alone, which reflects how much a device degrades the signal-to-noise ratio, noise measure captures the trade-off between noise and gain, making it a system-aware metric. This distinction is especially important when comparing devices in multistage systems, where both parameters jointly influence the overall system noise. Building on Haus and Adler's work, this article aims to advance RF system design by extending traditional device metrics, such as noise factor and noise measure, with new system-aware metrics: linearity, dynamic range, power efficiency, and waste measures. These new measures are interpretable, computable, and cascadable, making them well-suited for comparing the impact of individual devices or tracking the convergence of circuit design iterations on overall system-level performance. Additionally, a new metric–operating efficiency–is introduced, which unifies power efficiency, dynamic range, and data rate by incorporating signal statistics and variability in communication circuits and systems. Operating efficiency enables robust evaluation of devices under realistic and transient operating conditions, including interference, modulated signals, and adaptive modulation schemes.
Read the full abstract

All authors Leonid Belostotski, Arjuna Madanayake, John Nielsen, Mostafa Abdelhadi, Xingchen Liu, Xinquan Wang, Guanyue Qian, Sabit Ekin, Theodore S. Rappaport

Systems and Control

Physically Consistent SINDy (Sparse Identification of Nonlinear Dynamics) for Microgrid Identification and Real-Time Frequency Control

Mohan Du, Jiayi Lai, Rong-Peng Liu et al. (+1 more)

This paper proposes PC-SINDYc, a novel framework for the identification and frequency control of microgrids (MGs) with distributed energy resources. By leveraging physics-guided library construction, total least squares regression, and random sample consensus, the regression algorithm of PC-SINDYc robustly identifies the true frequency dynamics of MGs from phasor measurement unit (PMU) data, considering noise, delays, and constraint activations. Based on the identified model, the PC-SINDYc framework further incorporates a model predictive controller (MPC) for real-time frequency control. We prove that, under mild conditions, PC-SINDYc ensures asymptotic stability of the MG. Simulations on 4-bus and 13-bus MGs demonstrate that PC-SINDYc effectively controls MG's frequency across various disturbances unseen during the offline identification, outperforming PI controllers, conventional SINDYc, and state-of-the-art reinforcement learning methods.
Read the full abstract

All authors Mohan Du, Jiayi Lai, Rong-Peng Liu, Xiaozhe Wang

Systems and Control · Cross-listed from cs.RO

Motion Planning for Mobile Manipulators Navigating Doorways via Model Predictive Control

Kasra Sinaei, Kasun Weerakoon, Christopher Bradley et al. (+2 more)

Navigating doorways is a fundamental capability for mobile manipulators operating in human environments, requiring coordinated motion between the mobile base and manipulator arm. This paper presents a motion planning framework that generates dynamically feasible and collision-free trajectories for autonomously opening and traversing both push and pull doors. The proposed method formulates the robot and door as a coupled dynamical system within a nonlinear Model Predictive Control (MPC) optimization framework. Manipulation feasibility is enforced through a penalty-based constraint, avoiding explicit arm kinematic modeling in the planner. Simulations and a hardware experiment demonstrate that the approach successfully plans feasible trajectories for door traversal.
Read the full abstract

All authors Kasra Sinaei, Kasun Weerakoon, Christopher Bradley, Seyed Abolfazl Fakoorian, Donald Ebeigbe

Image and Video Processing

MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation

John Garcia Henao, Nicholas Bünger, Benedikt Herzog et al. (+11 more)

High-resolution 3D segmentation of hip and shoulder anatomy from CT and MRI is essential for surgical planning, yet frozen segmentation models often fail under domain shift. CNN-based expert models are fully automatic but lack adaptability, whereas promptable foundation models generalize better but require manual prompting. We present MedSAM2-Anatomy, a training-free inference-time optimization framework that improves frozen segmentation models without retraining or human interaction. A frozen expert model generates anatomical priors that are automatically converted into multiple prompt hypotheses for a frozen 3D foundation model. Candidate masks are fused while anatomically implausible priors are rejected. No model weights are updated and no manual prompts are required. TotalSegmentator and MedSAM2 are used as representative expert and foundation models, allowing the contribution of the inference policy to be isolated. Evaluation on the independent Balgrist-V0 CT and MRI cohorts shows that inference-time optimization increases median Dice from 0.71 to 0.92 on hip MRI and from 0.89 to 0.92 on shoulder CT, while reducing median HD95 on hip MRI from 22.0 mm to 5.0 mm. On public TotalSegmentator benchmarks, the expert model remains strongest, indicating that the optimal fusion strategy depends on the reliability of the expert prior. These results demonstrate that training-free inference-time optimization provides a practical strategy for improving frozen segmentation models without manual prompting.
Read the full abstract

All authors John Garcia Henao, Nicholas Bünger, Benedikt Herzog, Cindy Guerrero Toro, Benjamin Vella, Matthias Biner, Rico Brütsch, Carmen Castroviejo Fernandez, Felix Öttl, Norman Juchler, Armando Hoch, Bettina Hochreiter, Sven Hirsch, Sebastiano Caprara

Signal Processing

Normal-Anchored First-Order Model-Agnostic Meta-Learning based Whisper Fine-Tuning for Enhancing Fairness of Cleft Lip and Palate Speech Recognition

Susmita Bhattacharjee, Jagabandhu Mishra, H.S. Shekhawat et al. (+2 more)

Automatic speech recognition (ASR) for cleft lip and palate (CLP) speech is difficult because acoustic and articulatory patterns vary across severity levels. This variability reduces the performance of pretrained ASR systems, and conventional fine-tuning may not generalize well under low-resource, heterogeneous CLP conditions. This work proposes Normal-Anchored First-Order Model-Agnostic Meta-Learning (NA-FOMAML) for adapting Whisper to CLP speech. The method uses a first-order bilevel meta-learning framework in which normal speech is used in the inner loop as a stable support condition, while CLP severity groups are used in the outer loop to improve post-adaptation robustness. This design aims to reduce the performance gap between normal and pathological speech. Experiments are conducted on the NMCPC and AIISH datasets using four normal-anchored training configurations. Frozen encoder, full encoder, and selected Whisper encoder-layer tuning strategies are evaluated, including layers 0–5, 4–11, 6–11, and 8–11, with decoder and projection-head adaptation. Results show that outer-loop training with only normal speech is insufficient. For NMCPC, full encoder tuning with Normal to Normal+Mild+Moderate gives WERs of 4.40%, 5.53%, 16.14%, and 52.07% for normal, mild, moderate, and severe speech. For AIISH, full encoder tuning with Normal to Normal+Mild+Moderate+Severe gives WERs of 2.48%, 19.66%, 14.05%, and 57.50%. A transcription-based phoneme-category analysis shows that severe CLP speech has high error rates across fricatives, affricates, nasals, liquids, plosives, and vowels. Overall, NA-FOMAML improves cross-severity robustness, but severe speech still requires severity-aware sampling, phoneme-aware loss functions, and augmentation targeting pressure consonant and resonance-related distortions.
Read the full abstract

All authors Susmita Bhattacharjee, Jagabandhu Mishra, H.S. Shekhawat, Ravi Jasuja, S. R. Mahadeva Prasanna

Signal Processing

Generative Models for Modeling and Synthesizing MIMO Channels in Adverse Weather Conditions

Vignesh Nandakumar, Faraz Barati and Brian L. Evans

The push for broader coverage in future cellular networks depends on reliable service, yet this is increasingly harder to do as we encounter more instances of extreme weather conditions. In extreme weather conditions, we have difficulty evaluating coverage due to limited access to channel measurements. In this paper, we generate channel state information (CSI) in low and moderate weather conditions to synthesize realistic MIMO CSI under adverse weather conditions. Our primary contributions are to (1) synthesize MIMO channel datasets incorporating three weather types, each with three intensity levels, representative of practical 5G/6G scenarios; (2) train a diffusion model conditioned on weather using channel samples obtained through conventional pilot-based estimation under low and moderate weather intensities, and subsequently use it to generate channel realizations for severe weather conditions; and (3) evaluate the downlink Bit Error Rate (BER) and Outage Probability measures using the generated channels. The results show that diffusion-based generative models provide a scalable, data-driven alternative for channel modeling in harsh environments and can generalize to severe weather conditions using only low- and moderate-intensity training data.
Read the full abstract

Image and Video Processing

Automatic LV Localization and Short-Axis Plane Estimation from Arbitrary CMR Slice

Yi Yu, Yixuan Liu, Ziyu Zhang et al. (+4 more)

Accurate estimation of left ventricular (LV) orientation is essential for cardiac magnetic resonance (CMR) imaging and downstream analysis. Existing methods typically formulate orientation recognition as discrete view classification or rely on multi-slice geometric intersection, limiting their ability to model continuous 3D orientation and generalize across arbitrary slices. This work introduces a novel paradigm: Joint LV localization and 3D orientation estimation from a single CMR slice. To investigate this setting, representative orientation-aware detection frameworks are adapted to the CMR domain, and their limitations are analyzed. Upon that, we propose the Polar-Coupled Circular (PCC) embedding that provides a continuous and unambiguous orientation representation to address the limitations. Meanwhile, a scalable benchmark is constructed through automatic slice sampling from volumetric CMR segmentation datasets. Extensive experiments on four datasets demonstrate strong performance, achieving an average mIoU of 86.18% and an average angle deviation of 3.39{\deg}. This study establishes a new task setting for single-slice LV orientation modeling and provides a geometry-consistent framework for spatially informed CMR analysis. Code is available at https://github.com/yuyi1005/cmr-3d-ood.
Read the full abstract

All authors Yi Yu, Yixuan Liu, Ziyu Zhang, Parker Martin, Zhenyu Bu, Yuchi Han, Yuan Xue

Image and Video Processing

Two-Stage Teacher-Student Reliable Prior Learning for Robust Underwater Image Enhancement

Yifan Chen, Jiaming Liu, Ye Zheng et al. (+2 more)

Underwater image enhancement (UIE) aims to recover clear images from observations affected by wavelength-dependent absorption, scattering, and spatially nonuniform degradation. Although existing generative methods can handle complex degradations, severe information loss may lead to semantic drift in the restored results. To address this issue, we propose RPL-UIE, a two-stage teacher–student framework for reliable prior learning. In the teacher stage, the network learns reliable and complementary spatial priors characterizing appearance and photometric properties from paired degraded and reference images. In the student stage, the network takes only degraded images as input and learns to emulate the teacher's prior extraction capability, thereby providing more reliable restoration guidance for the enhancement process without requiring reference images at inference. To reduce the prior-learning discrepancy between the teacher and student models, we further develop Residual Prior Refinement Diffusion (RPRD) and Frequency-Aware Prior Residual Calibration (FPRC). RPRD uses the coarse priors as anchors and progressively predicts the necessary corrections in the residual space. FPRC retains stable low-frequency residual components and selectively modulates high-frequency detail residuals, producing calibrated priors to support high-quality reconstruction. Experiments on multiple UIE benchmarks demonstrate competitive restoration performance. Downstream underwater object detection and instance segmentation experiments further demonstrate the improved utility of enhanced images for visual perception, while tests on real-world data captured by a remotely operated vehicle (ROV) support the robustness and practical applicability of RPL-UIE.
Read the full abstract

All authors Yifan Chen, Jiaming Liu, Ye Zheng, Zhe Sun, Tao Chen