Peer Revenue Play credits. Real papers.

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 10 October

Systems and Control · Cross-listed from cs.RO

Trust Modeling and Estimation in Human-Autonomy Interactions

Daniel A. Williams, Airlie Chapman, Daniel R. Little et al. (+1 more)

Advances in the control of autonomous systems have accompanied an expansion in the potential applications for autonomous robotic systems. The success of applications involving humans depends on the quality of interaction between the autonomous system and the human supervisor, which is particularly affected by the degree of trust that the supervisor places in the autonomous system. Absent from the literature are models of supervisor trust dynamics that can accommodate asymmetric responses to autonomous system performance and the intermittent nature of supervisor-autonomous system communication. This paper focuses on formulating an estimated model of supervisor trust that incorporates both of these features by employing a switched linear system structure with event-triggered sampling of the model input and output. Trust response data collected in a user study with 51 participants were then used identify parameters for a switched linear model-based observer of supervisor trust.
Read the full abstract

All authors Daniel A. Williams, Airlie Chapman, Daniel R. Little, Chris Manzie

Systems and Control

Traffic-Aware Eco-Driving Control in CAVs via Learning-based Terminal Cost Model

Mehmet Fatih Ozkan, Dennis Kibalama, Jacob Paugh et al. (+2 more)

Connected and Automated Vehicles (CAVs) offer significant potential for improving energy efficiency and lowering vehicle emissions through eco-driving technologies. Control algorithms in CAVs leverage look-ahead route information and Vehicle-to-Everything (V2X) communication to optimize vehicle performance. However, existing eco-driving strategies often neglect macroscopic traffic effects, such as upstream traffic jams, that occur outside the optimization horizon but significantly impact vehicle energy efficiency. This work presents a novel Neural Network (NN)-based methodology to approximate the terminal cost within a model predictive control (MPC) problem framework, explicitly incorporating upstream traffic dynamics. By incorporating traffic jams into the optimization process, the proposed traffic-aware approach yields more energy-efficient speed trajectories compared to traffic-agnostic methods, with minimal impact on travel time. The framework is scalable for real-time implementation while effectively addressing uncertainties from dynamic traffic conditions and macroscopic traffic events.
Read the full abstract

All authors Mehmet Fatih Ozkan, Dennis Kibalama, Jacob Paugh, Marcello Canova, Stephanie Stockar

Image and Video Processing

SAM2-3dMed: Empowering SAM2 for 3D Medical Image Segmentation

Yeqing Yang, Le Xu and Lixia Tian

Accurate segmentation of 3D medical images is critical for clinical applications like disease assessment and treatment planning. While the Segment Anything Model 2 (SAM2) has shown remarkable success in video object segmentation by leveraging temporal cues, its direct application to 3D medical images faces two fundamental domain gaps: 1) the bidirectional anatomical continuity between slices contrasts sharply with the unidirectional temporal flow in videos, and 2) precise boundary delineation, crucial for morphological analysis, is often underexplored in video tasks. To bridge these gaps, we propose SAM2-3dMed, an adaptation of SAM2 for 3D medical imaging. Our framework introduces two key innovations: 1) a Slice Relative Position Prediction (SRPP) module explicitly models bidirectional inter-slice dependencies by guiding SAM2 to predict the relative positions of different slices in a self-supervised manner; 2) a Boundary Detection (BD) module enhances segmentation accuracy along critical organ and tissue boundaries. Extensive experiments on three diverse medical datasets (the Lung, Spleen, and Pancreas in the Medical Segmentation Decathlon (MSD) dataset) demonstrate that SAM2-3dMed significantly outperforms state-of-the-art methods, achieving superior performance in segmentation overlap and boundary precision. Our approach not only advances 3D medical image segmentation performance but also offers a general paradigm for adapting video-centric foundation models to spatial volumetric data.
Read the full abstract

Systems and Control · Cross-listed from cs.RO

Direct Data-Driven Predictive Control for a Three-dimensional Cable-Driven Soft Robotic Arm

Cheng Ouyang, Moeen Ul Islam, Dong Chen et al. (+3 more)

Soft robots offer significant advantages in safety and adaptability, yet achieving precise and dynamic control remains a major challenge due to their inherently complex and nonlinear dynamics. Recently, Data-enabled Predictive Control (DeePC) has emerged as a promising model-free approach that bypasses explicit system identification by directly leveraging input-output data. While DeePC has shown success in other domains, its application to soft robots remains underexplored, particularly for three-dimensional (3D) soft robotic systems. This paper addresses this gap by developing and experimentally validating an effective DeePC framework on a 3D, cable-driven soft arm. Specifically, we design and fabricate a soft robotic arm with a thick tubing backbone for stability, a dense silicone body with large cavities for strength and flexibility, and rigid endcaps for secure termination. Using this platform, we implement DeePC with singular value decomposition (SVD)-based dimension reduction for two key control tasks: fixed-point regulation and trajectory tracking in 3D space. Comparative experiments with a baseline model-based controller demonstrate DeePC's superior accuracy, robustness, and adaptability, highlighting its potential as a practical solution for dynamic control of soft robots.
Read the full abstract

All authors Cheng Ouyang, Moeen Ul Islam, Dong Chen, Kaixiang Zhang, Zhaojian Li, Xiaobo Tan

Image and Video Processing

FS-RWKV: Leveraging Frequency Spatial-Aware RWKV for 3T-to-7T MRI Translation

Yingtie Lei, Zimeng Li, Chi-Man Pun et al. (+2 more)

Ultra-high-field 7T MRI offers enhanced spatial resolution and tissue contrast that enables the detection of subtle pathological changes in neurological disorders. However, the limited availability of 7T scanners restricts widespread clinical adoption due to substantial infrastructure costs and technical demands. Computational approaches for synthesizing 7T-quality images from accessible 3T acquisitions present a viable solution to this accessibility challenge. Existing CNN approaches suffer from limited spatial coverage, while Transformer models demand excessive computational overhead. RWKV architectures offer an efficient alternative for global feature modeling in medical image synthesis, combining linear computational complexity with strong long-range dependency capture. Building on this foundation, we propose Frequency Spatial-RWKV (FS-RWKV), an RWKV-based framework for 3T-to-7T MRI translation. To better address the challenges of anatomical detail preservation and global tissue contrast recovery, FS-RWKV incorporates two key modules: (1) Frequency-Spatial Omnidirectional Shift (FSO-Shift), which performs discrete wavelet decomposition followed by omnidirectional spatial shifting on the low-frequency branch to enhance global contextual representation while preserving high-frequency anatomical details; and (2) Structural Fidelity Enhancement Block (SFEB), a module that adaptively reinforces anatomical structure through frequency-aware feature fusion. Comprehensive experiments on UNC and BNU datasets demonstrate that FS-RWKV consistently outperforms existing CNN-, Transformer-, GAN-, and RWKV-based baselines across both T1w and T2w modalities, achieving superior anatomical fidelity and perceptual quality.
Read the full abstract

All authors Yingtie Lei, Zimeng Li, Chi-Man Pun, Yupeng Liu, Xuhang Chen

Image and Video Processing

Progressive Uncertainty-Guided Evidential U-KAN for Trustworthy Medical Image Segmentation

Zhen Yang, Yansong Ma and Lei Chen

Trustworthy medical image segmentation aims at deliver accurate and reliable results for clinical decision-making. Most existing methods adopt the evidence deep learning (EDL) paradigm due to its computational efficiency and theoretical robustness. However, the EDL-based methods often neglect leveraging uncertainty maps rich in attention cues to refine ambiguous boundary segmentation. To address this, we propose a progressive evidence uncertainty guided attention (PEUA) mechanism to guide the model to focus on the feature representation learning of hard regions. Unlike conventional approaches, PEUA progressively refines attention using uncertainty maps while employing low-rank learning to denoise attention weights, enhancing feature learning for challenging regions. Concurrently, standard EDL methods suppress evidence of incorrect class indiscriminately via Kullback-Leibler (KL) regularization, impairing the uncertainty assessment in ambiguous areas and consequently distorts the corresponding attention guidance. We thus introduce a semantic-preserving evidence learning (SAEL) strategy, integrating a semantic-smooth evidence generator and a fidelity-enhancing regularization term to retain critical semantics. Finally, by embedding PEUA and SAEL with the state-of-the-art U-KAN, we proposes Evidential U-KAN, a novel solution for trustworthy medical image segmentation. Extensive experiments on 4 datasets demonstrate superior accuracy and reliability over the competing methods. The code is available at \href{https://anonymous.4open.science/r/Evidence-U-KAN-BBE8}{github}.
Read the full abstract

Systems and Control · Cross-listed from physics.med-ph

A pilot cohort study of a microfluidic-based point-of-care bilirubin measurement system

Jean Pierre Ndabakuranye, Inge W.G. Last, Kay Weng Choy et al. (+6 more)

Objective The concentration of bilirubin in blood or serum is useful for assessing liver function as well as monitoring treatment. This study evaluates the clinical performance of a novel point-of-care (PoC) device for the detection of bilirubin in serum. The PoC device incorporates an integrated miniature optoelectronic sensing module and a microfluidic test cartridge. Methods Patients' serum total bilirubin concentrations, ranging from 2 {\mu}mol/L to 480 {\mu}mol/L, were measured using the PoC device and the standard laboratory method (n=20). Bland-Altman analysis and regression analysis using Passing-Bablok method were used to benchmark the PoC device against the standard laboratory measurements. The diagnostic capability of the PoC device in categorising the serum samples within clinically relevant bilirubin concentration thresholds of 200, 300, and 450 {\mu}mol/L was assessed using receiver operating characteristic (ROC) analysis. Results The mean difference between the PoC device and the standard laboratory method was -5.6 {\mu}mol/L, with a 95% confidence interval (CI) of -45.1 {\mu}mol/L to 33.9 {\mu}mol/L. The coefficient of determination (R2) was 0.986. The PoC device achieved a detection sensitivity of 90% and specificity of 97% in categorising bilirubin concentrations within bands used in clinical decision-making. Conclusions This study demonstrates that the proposed PoC device is capable of measuring bilirubin levels in patient samples with clinically acceptable accuracy.
Read the full abstract

All authors Jean Pierre Ndabakuranye, Inge W.G. Last, Kay Weng Choy, Peter Thurgood, Jason C. Steel, Genia Burchall, Stella Stylianou, Khashayar Khoshmanesh, Arman Ahnood

Systems and Control

Cognitive Radio for Asymmetric Cellular Downlink with Multi-User MIMO

Omer Gokalp Serbetci, Lei Chu and Andreas F. Molisch

Cognitive radio (CR) is an important technique for improving spectral efficiency, letting a secondary system operate in a wireless spectrum when the primary system does not make use of it. While it has been widely explored over the past 25 years, many common assumptions are not aligned with the realities of 5G networks. In this paper, we consider the CR problem for the following setup: (i) infrastructure-based systems, where downlink transmissions might occur to receivers whose positions are not, or not exactly, known; (ii) multi-beam antennas at both primary and secondary base stations. We formulate a detailed protocol to determine when secondary transmissions into different beam directions can interfere with primary users at potential locations and create probability-based interference rules. We then analyze the "catastrophic interference" probability and the "missed transmission opportunity" probability, as well as the achievable throughput, as a function of the transmit powers of the primary and secondary base stations and the sensing window of the secondary base station. Results can serve to more realistically assess the spectral efficiency gains in 5G infrastructure-based cognitive systems.
Read the full abstract

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

VM-UNSSOR: Unsupervised Neural Speech Separation Enhanced by Higher-SNR Virtual Microphone Arrays

Shulin He and Zhong-Qiu Wang

Blind speech separation (BSS) aims to recover multiple speech sources from multi-channel, multi-speaker mixtures under unknown array geometry and room impulse responses. In unsupervised setup where clean target speech is not available for model training, UNSSOR proposes a mixture consistency (MC) loss for training deep neural networks (DNN) on over-determined training mixtures to realize unsupervised speech separation. However, when the number of microphones of the training mixtures decreases, the MC constraint weakens and the separation performance falls dramatically. To address this, we propose VM-UNSSOR, augmenting the observed training mixture signals recorded by a limited number of microphones with several higher-SNR virtual-microphone (VM) signals, which are obtained by applying linear spatial demixers (such as IVA and spatial clustering) to the observed training mixtures. As linear projections of the observed mixtures, the virtual-microphone signals can typically increase the SNR of each source and can be leveraged to compute extra MC losses to improve UNSSOR and address the frequency permutation problem in UNSSOR. On the SMS-WSJ dataset, in the over-determined six-microphone, two-speaker separation setup, VM-UNSSOR reaches 17.1 dB SI-SDR, while UNSSOR only obtains 14.7 dB; and in the determined two-microphone, two-speaker case, UNSSOR collapses to -2.7 dB SI-SDR, while VM-UNSSOR achieves 10.7 dB.
Read the full abstract

Systems and Control · Cross-listed from cs.IT

Observation Matrix Design for Densifying MIMO Channel Estimation via 2D Ice Filling

Zijian Zhang and Mingyao Cui

In recent years, densifying multiple-input multiple-output (MIMO) has attracted much attention from the communication community. Thanks to the subwavelength antenna spacing, the strong correlations among densifying antennas provide sufficient prior knowledge about channel state information (CSI). This inspires the careful design of observation matrices (e.g., transmit precoders and receive combiners), that exploits the CSI prior knowledge, to boost channel estimation performance. Aligned with this vision, this work proposes to jointly design the combiners and precoders by maximizing the mutual information between the received pilots and densifying MIMO channels. A two-dimensional ice-filling (2DIF) algorithm is proposed to efficiently accomplish this objective. The algorithm is motivated by the fact that the eigenspace of MIMO channel covariance can be decoupled into two sub-eigenspaces, which are associated with the correlations of transmitter antennas and receiver antennas, respectively. By properly setting the precoder and the combiner as the eigenvectors from these two sub-eigenspaces, the 2DIF promises to generate near-optimal observation matrices. Moreover, we further extend the 2DIF method to the popular hybrid combining systems, where a two-stage 2DIF (TS-2DIF) algorithm is developed to handle the analog combining circuits realized by phase shifters. Simulation results demonstrate that, compared to the state-of-the-art schemes, the proposed 2DIF and TS-2DIF methods can achieve superior channel estimation accuracy.
Read the full abstract

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

ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling

Yuxuan Jiang, Zehua Chen, Zeqian Ju et al. (+3 more)

Text-to-audio (TTA) generation with fine-grained control signals, e.g., precise timing control or intelligible speech content, has been explored in recent works. However, constrained by data scarcity, their generation performance at scale is still compromised. In this study, we recast controllable TTA generation as a multi-task learning problem and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on more fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a diffusion transformer (DiT) on large-scale text-audio pairs, achieving scalable TTA generation, and then incrementally integrate the timing and phoneme features with unified semantic representations, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio.
Read the full abstract

All authors Yuxuan Jiang, Zehua Chen, Zeqian Ju, Yusheng Dai, Weibei Dou, Jun Zhu

Thursday 9 October

Signal Processing

A Multiscale Approach for Enhancing Weak Signal Detection

Dixon Vimalajeewa, Ursula U. Muller and Brani Vidakovic

Stochastic resonance (SR), a phenomenon originally introduced in climate modeling, enhances signal detection by leveraging optimal noise levels within non-linear systems. Traditional SR techniques, mainly based on single-threshold detectors, are limited to signals whose behavior does not depend on time. Often large amounts of noise are needed to detect weak signals, which can distort complex signal characteristics. To address these limitations, this study explores multi-threshold systems and the application of SR in multiscale applications using wavelet transforms. In the multiscale domain signals can be analyzed at different levels of resolution to better understand the underlying dynamics. We propose a double-threshold detection system that integrates two single-threshold detectors to enhance weak signal detection. We evaluate it both in the original data domain and in the multiscale domain using simulated and real-world signals and compare its performance with existing methods. Experimental results demonstrate that, in the original data domain, the proposed double-threshold detector significantly improves weak signal detection compared to conventional single-threshold approaches. Its performance is further improved in the frequency domain, requiring lower noise levels while outperforming existing detection systems. This study advances SR-based detection methodologies by introducing a robust approach to weak signal identification, with potential applications in various disciplines.
Read the full abstract

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

Beyond Discrete Categories: Multi-Task Valence-Arousal Modeling for Pet Vocalization Analysis

Junyao Huang and Rumin Situ

Traditional pet emotion recognition from vocalizations, based on discrete classification, struggles with ambiguity and capturing intensity variations. We propose a continuous Valence-Arousal (VA) model that represents emotions in a two-dimensional space. Our method uses an automatic VA label generation algorithm, enabling large-scale annotation of 42,553 pet vocalization samples. A multi-task learning framework jointly trains VA regression with auxiliary tasks (emotion, body size, gender) to enhance prediction by improving feature learning. Our Audio Transformer model achieves a validation Valence Pearson correlation of r = 0.9024 and an Arousal r = 0.7155, effectively resolving confusion between discrete categories like "territorial" and "happy." This work introduces the first continuous VA framework for pet vocalization analysis, offering a more expressive representation for human-pet interaction, veterinary diagnostics, and behavioral training. The approach shows strong potential for deployment in consumer products like AI pet emotion translators.
Read the full abstract

Systems and Control · Cross-listed from math.OC

Optimal Control with Lyapunov Stability Guarantees for Space Applications

Abhijeet, Mohamed Naveed Gul Mohamed, Aayushman Sharma et al. (+1 more)

This paper investigates the infinite horizon optimal control problem (OCP) for space applications characterized by nonlinear dynamics. The proposed approach divides the problem into a finite horizon OCP with a regularized terminal cost, guiding the system towards a terminal set, and an infinite horizon linear regulation phase within this set. This strategy guarantees global asymptotic stability under specific assumptions. Our method maintains the system's fully nonlinear dynamics until it reaches the terminal set, where the system dynamics is linearized. As the terminal set converges to the origin, the difference in optimal cost incurred reduces to zero, guaranteeing an efficient and stable solution. The approach is tested through simulations on three problems: spacecraft attitude control, rendezvous maneuver, and soft landing. In spacecraft attitude control, we focus on achieving precise orientation and stabilization. For rendezvous maneuvers, we address the navigation of a chaser to meet a target spacecraft. For the soft landing problem, we ensure a controlled descent and touchdown on a planetary surface. We provide numerical results confirming the effectiveness of the proposed method in managing these nonlinear dynamics problems, offering robust solutions essential for successful space missions.
Read the full abstract

All authors Abhijeet, Mohamed Naveed Gul Mohamed, Aayushman Sharma, Suman Chakravorty

Systems and Control

Joint Detection, Channel Estimation and Interference Nulling for Terrestrial-Satellite Downlink Co-Existence in the Upper Mid-Band

Shizhen Jia, Mingjun Ying, Marco Mezzavilla et al. (+3 more)

The upper mid-band FR3 spectrum (7-24 GHz) has garnered significant interest for future cellular services. However, utilizing a large portion of this band requires careful interference coordination with incumbent satellite systems. This paper investigates interference from high-power terrestrial base stations (TN-BSs) to satellite downlink receivers. A central challenge is that the victim receivers, i.e., ground-based non-terrestrial user equipment (NTN-UEs) such as satellite customer premises equipment, must first be detected and their channels estimated before the TN-BS can effectively place nulls in their directions. We explore a potential solution where NTN-UEs periodically transmit preambles or beacon signals that TN-BSs can use for detection and channel estimation. The performance of this nulling approach is analyzed in a simplified scenario with a single victim, revealing the interplay between path loss and estimation quality in determining nulling performance. To further validate the method, we conduct a detailed multi-user site-specific ray-tracing (RT) simulation in a rural environment. The results show that the proposed nulling approach is effective under realistic parameters, even with high densities of victim units, although TN-BS may require a substantial number of antennas.
Read the full abstract

All authors Shizhen Jia, Mingjun Ying, Marco Mezzavilla, Doru Calin, Theodore S. Rappaport, Sundeep Rangan

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

Audible Networks: Deconstructing and Manipulating Sounds with Deep Non-Negative Autoencoders

Juan José Burred and Carmine-Emanuele Cella

We propose the use of Non-Negative Autoencoders (NAEs) for sound deconstruction and user-guided manipulation of sounds for creative purposes. NAEs offer a versatile and scalable extension of traditional Non-Negative Matrix Factorization (NMF)-based approaches for interpretable audio decomposition. By enforcing non-negativity constraints through projected gradient descent, we obtain decompositions where internal weights and activations can be directly interpreted as spectral shapes and temporal envelopes, and where components can themselves be listened to as individual sound events. In particular, multi-layer Deep NAE architectures enable hierarchical representations with an adjustable level of granularity, allowing sounds to be deconstructed at multiple levels of abstraction: from high-level note envelopes down to fine-grained spectral details. This framework enables a wide new range of expressive, controllable, and randomized sound transformations. We introduce novel manipulation operations including cross-component and cross-layer synthesis, hierarchical deconstructions, and several randomization strategies that control timbre and event density. Through visualizations and resynthesis of practical examples, we demonstrate how NAEs can serve as flexible and interpretable tools for object-based sound editing.
Read the full abstract

Signal Processing · Cross-listed from cs.IT

On Estimation of Angles of Arrival in Monostatic ISAC Without Instantaneous Transmit CSI

Ataher Sams, Simone Di Bari, Besma Smida et al. (+3 more)

This paper explores the fundamental limits of Integrated Sensing and Communication (ISAC) in a more realistic setting compared to previous literature when the Base Staion (BS) has only statistical CSI of the communication user rather than full CSI. We analyze a monostatic setting where the BS performs multi-target Angle of Arrival (AoA) estimation while simultaneously communicating with one of the targets. We assume that the BS has statistical CSI about all AoAs, with less uncertainty in the AoA of the communication receiver. The communication receiver is assumed to have perfect CSI. Utilizing a Bayesian Cramér-Rao Bound (BCRB) framework to characterize the fundamental limits of sensing under minimum mean square error (MMSE) criteria, we derive achievable BCRB-rate trade-off regions. Our approach introduces a number of transmission strategies that share power across sensing and communication beams over a coherence time. Our analysis reveals that beam allocation strategies leveraging the principal eigenvectors of the target-specific sensing matrices minimize individual AoA estimation errors, while strategies balancing sensing and communication directions optimize joint estimation performance at the cost of individual accuracy. We demonstrate that leveraging updated BCRB-based sensing information for the communication receiver, due to its lower channel uncertainty, enables significantly improved communication rates.
Read the full abstract

All authors Ataher Sams, Simone Di Bari, Besma Smida, Natasha Devroye, Daniela Tuninetti, Giorgio Taricco

Signal Processing

UAV-Assisted 3-D Localization for IoT Networks Using a Simple and Efficient TDOA-AOA Estimator

Mojtaba Amiri and Rouhollah Amiri

This letter proposes an algebraic solution for the problem of 3-D source localization utilizing the minimum number of measurements, i.e., one Time Difference of Arrival (TDOA) and one Angle of Arrival (AOA) pair. The proposed method employs a closed-form weighted least squares estimator and enables the positioning using a single ground station and a cooperative UAV relaying the signal. Analytical derivations and simulation results demonstrate effectiveness of the proposed approach, achieving near-optimal performance aligned with the Cramér-Rao Lower Bound (CRLB) under moderate Gaussian noise conditions.
Read the full abstract

Systems and Control · Cross-listed from cs.RO

Whole Body Model Predictive Control for Spin-Aware Quadrupedal Table Tennis

David Nguyen, Zulfiqar Zaidi, Kevin Karol et al. (+2 more)

Developing table tennis robots that mirror human speed, accuracy, and ability to predict and respond to the full range of ball spins remains a significant challenge for legged robots. To demonstrate these capabilities we present a system to play dynamic table tennis for quadrupedal robots that integrates high speed perception, trajectory prediction, and agile control. Our system uses external cameras for high-speed ball localization, physical models with learned residuals to infer spin and predict trajectories, and a novel model predictive control (MPC) formulation for agile full-body control. Notably, a continuous set of stroke strategies emerge automatically from different ball return objectives using this control paradigm. We demonstrate our system in the real world on a Spot quadruped, evaluate accuracy of each system component, and exhibit coordination through the system's ability to aim and return balls with varying spin types. As a further demonstration, the system is able to rally with human players.
Read the full abstract

All authors David Nguyen, Zulfiqar Zaidi, Kevin Karol, Jessica Hodgins, Zhaoming Xie

Signal Processing · Cross-listed from cs.NI

Curated Wireless Datasets for Aerial Network Research

Amir Hossein Fahim Raouf, Donggu Lee, Mushfiqur Rahman et al. (+18 more)

This Review consolidates publicly available aerial wireless measurement datasets collected using AERPAW. We organize signal-level, power-level, and KPI-level datasets under a unified taxonomy, harmonize metadata, and provide verified access with reproducible post-processing scripts. The curated catalog supports propagation modeling, machine learning, localization, and system-level evaluation for 5G-Advanced and emerging 6G aerial networks.
Read the full abstract

All authors Amir Hossein Fahim Raouf, Donggu Lee, Mushfiqur Rahman, Saad Masrur, Gautham Reddy, Cole Dickerson, Md Sharif Hossen, Sergio Vargas Villar, An{\i}l Gürses, Simran Singh, Sung Joon Maeng, Martins Ezuma, Christopher Roberts, Mohamed Rabeek Sarbudeen, Thomas J. Zajkowski, Magreth Mushi, Ozgur Ozdemir, Ram Asokan, Ismail Guvenc, Mihail L. Sichitiu, Rudra Dutta

Systems and Control · Cross-listed from cs.ET

When to Reason: Semantic Router for vLLM

Chen Wang, Xunzhuo Liu, Yuhan Liu et al. (+4 more)

Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also incurs significant costs in inference latency and token usage, with environmental and financial impacts, which are unnecessary for many simple prompts. We present a semantic router that classifies queries based on their reasoning requirements and selectively applies reasoning only when beneficial. Our approach achieves a 10.2 percentage point improvement in accuracy on the MMLU-Pro benchmark while reducing response latency by 47.1% and token consumption by 48.5% compared to direct inference with vLLM. These results demonstrate that semantic routing offers an effective mechanism for striking a balance between accuracy and efficiency in open-source LLM serving systems
Read the full abstract

All authors Chen Wang, Xunzhuo Liu, Yuhan Liu, Yue Zhu, Xiangxi Mo, Junchen Jiang, Huamin Chen

Image and Video Processing

Interlaced dynamic XCT reconstruction with spatio-temporal implicit neural representations

Mathias Boulanger and Ericmoore Jossou

In this work, we investigate the use of spatio-temporalImplicit Neural Representations (INRs) for dynamic X-ray computed tomography (XCT) reconstruction under interlaced acquisition schemes. The proposed approach combines ADMM-based optimization with INCODE, a conditioning framework incorporating prior knowledge, to enable efficient convergence. We evaluate our method under diverse acquisition scenarios, varying the severity of global undersampling, spatial complexity (quantified via spatial information), and noise levels. Across all settings, our model achieves strong performance and outperforms Time-Interlaced Model-Based Iterative Reconstruction (TIMBIR), a state-of-the-art model-based iterative method. In particular, we show that the inductive bias of the INR provides good robustness to moderate noise levels, and that introducing explicit noise modeling through a weighted least squares data fidelity term significantly improves performance in more challenging regimes. The final part of this work explores extensions toward a practical reconstruction framework. We demonstrate the modularity of our approach by explicitly modeling detector non-idealities, incorporating ring artifact correction directly within the reconstruction process. Additionally, we present a proof-of-concept 4D volumetric reconstruction by jointly optimizing over batched axial slices, an approach which opens up the possibilities for massive parallelization, a critical feature for processing large-scale datasets.
Read the full abstract

Image and Video Processing

AI-Driven Radiology Report Generation for Traumatic Brain Injuries

Riadh Bouslimi, Houda Trabelsi, Wahiba Ben Abdssalem Karaa et al. (+1 more)

Traumatic brain injuries present significant diagnostic challenges in emergency medicine, where the timely interpretation of medical images is crucial for patient outcomes. In this paper, we propose a novel AI-based approach for automatic radiology report generation tailored to cranial trauma cases. Our model integrates an AC-BiFPN with a Transformer architecture to capture and process complex medical imaging data such as CT and MRI scans. The AC-BiFPN extracts multi-scale features, enabling the detection of intricate anomalies like intracranial hemorrhages, while the Transformer generates coherent, contextually relevant diagnostic reports by modeling long-range dependencies. We evaluate the performance of our model on the RSNA Intracranial Hemorrhage Detection dataset, where it outperforms traditional CNN-based models in both diagnostic accuracy and report generation. This solution not only supports radiologists in high-pressure environments but also provides a powerful educational tool for trainee physicians, offering real-time feedback and enhancing their learning experience. Our findings demonstrate the potential of combining advanced feature extraction with transformer-based text generation to improve clinical decision-making in the diagnosis of traumatic brain injuries.
Read the full abstract

All authors Riadh Bouslimi, Houda Trabelsi, Wahiba Ben Abdssalem Karaa, Hana Hedhli

Systems and Control · Cross-listed from cs.RO

Reliability of Single-Level Equality-Constrained Inverse Optimal Control

Filip Bečanović, Kosta Jovanović and Vincent Bonnet

Inverse optimal control (IOC) allows the retrieval of optimal cost function weights, or behavioral parameters, from human motion. The literature on IOC uses methods that are either based on a slow bilevel process or a fast but noise-sensitive minimization of optimality condition violation. Assuming equality-constrained optimal control models of human motion, this article presents a faster but robust approach to solving IOC using a single-level reformulation of the bilevel method and yields equivalent results. Through numerical experiments in simulation, we analyze the robustness to noise of the proposed single-level reformulation to the bilevel IOC formulation with a human-like planar reaching task that is used across recent studies. The approach shows resilience to very large levels of noise and reduces the computation time of the IOC on this task by a factor of 15 when compared to a classical bilevel implementation.
Read the full abstract

Audio and Speech Processing

MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

Guobin Ma, Jixun Yao, Ziqian Ning et al. (+4 more)

Zero-shot voice conversion (VC) aims to transfer timbre from a source speaker to any unseen target speaker while preserving linguistic content. Growing application scenarios demand models with streaming inference capabilities. This has created a pressing need for models that are simultaneously fast, lightweight, and high-fidelity. However, existing streaming methods typically rely on either autoregressive (AR) or non-autoregressive (NAR) frameworks, which either require large parameter sizes to achieve strong performance or struggle to generalize to unseen speakers. In this study, we propose MeanVC, a lightweight and streaming zero-shot VC approach. MeanVC introduces a diffusion transformer with a chunk-wise autoregressive denoising strategy, combining the strengths of both AR and NAR paradigms for efficient streaming processing. By introducing mean flows, MeanVC regresses the average velocity field during training, enabling zero-shot VC with superior speech quality and speaker similarity in a single sampling step by directly mapping from the start to the endpoint of the flow trajectory. Additionally, we incorporate diffusion adversarial post-training to mitigate over-smoothing and further enhance speech quality. Experimental results demonstrate that MeanVC significantly outperforms existing zero-shot streaming VC systems, achieving superior conversion quality with higher efficiency and significantly fewer parameters. Audio demos and code are publicly available at https://aslp-lab.github.io/MeanVC.
Read the full abstract

All authors Guobin Ma, Jixun Yao, Ziqian Ning, Yuepeng Jiang, Lingxin Xiong, Lei Xie, Pengcheng Zhu

Audio and Speech Processing

DialoSpeech: Dual-Speaker Dialogue Generation with LLM and Flow Matching

Hanke Xie, Dake Guo, Chengyou Wang et al. (+8 more)

Recent advances in text-to-speech (TTS) synthesis, particularly those leveraging large language models (LLMs), have significantly improved expressiveness and naturalness. However, generating human-like, interactive dialogue speech remains challenging. Current systems face limitations due to the scarcity of dual-track data and difficulties in achieving naturalness, contextual coherence, and interactional dynamics, such as turn-taking, overlapping speech, and speaker consistency, in multi-turn conversations. To address these challenges, we propose DialoSpeech, a dual-track architecture combining a large language model with Chunked Flow Matching for expressive, human-like dialogue speech synthesis. DialoSpeech generates natural multi-turn conversations with coherent speaker turns and natural overlaps, supporting both Chinese and English and cross-lingual speech synthesis. We introduce a data processing pipeline to construct dual-track dialogue datasets, facilitating scalable training and experimental validation. Experiments show that our model outperforms baselines, offering a solution for generating human-like spoken dialogues. Audio samples are available at https://tiamojames.github.io/DialoSpeech
Read the full abstract

All authors Hanke Xie, Dake Guo, Chengyou Wang, Yue Li, Wenjie Tian, Xinfa Zhu, Xinsheng Wang, Xiulin Li, Guanqiong Miao, Bo Liu, Lei Xie

Systems and Control

Learning to Mitigate Post-Outage Load Surges: A Data-Driven Framework for Electrifying and Decarbonizing Grids

Wenlong Shi, Dingwei Wang, Liming Liu et al. (+1 more)

Electrification and decarbonization are transforming power system demand and recovery dynamics, yet their implications for post-outage load surges remain poorly understood. Here we analyze a metropolitan-scale heterogeneous dataset for Indianapolis comprising 30,046 feeder-level outages between 2020 and 2024, linked to smart meters and submetering, to quantify the causal impact of electric vehicles (EVs), heat pumps (HPs) and distributed energy resources (DERs) on restoration surges. Statistical analysis and causal forest inference demonstrate that rising penetrations of all three assets significantly increase surge ratios, with effects strongly modulated by restoration timing, outage duration and weather conditions. We develop a component-aware multi-task Transformer estimator that disaggregates EV, HP and DER contributions, and apply it to project historical outages under counterfactual 2035 adoption pathways. In a policy-aligned pathway, evening restorations emerge as the binding reliability constraint, with exceedance probabilities of 0.057 when 30% of system load is restored within the first 15 minutes. Mitigation measures, probabilistic EV restarts, short thermostat offsets and accelerated DER reconnection, reduce exceedance to 0.019 and eliminate it entirely when 20% or less of system load is restored. These results demonstrate that transition-era surges are asset-driven and causally linked to electrification and decarbonization, but can be effectively managed through integrated operational strategies.
Read the full abstract

All authors Wenlong Shi, Dingwei Wang, Liming Liu, Zhaoyu Wang

Systems and Control

Underground Power Distribution System Restoration Using Inverter Based Resources

Wenlong Shi, Hongyi Li and Zhaoyu Wang

Underground power distribution systems (PDSs) are increasingly deployed in urban areas. The integration of smart devices including smart switchgears, pad-mounted distribution transformers and inverter-based resources (IBRs) enhance system resilience, however simultaneously introducing unique challenges. The challenges include inrush currents caused by trapped charges in underground cables, ferroresonance in distribution transformers during energization, and three-phase load imbalance resulting from single-phase underground laterals. To address these issues, this paper proposes an underground PDS restoration framework using IBRs. Firstly, an underground cable energization model is developed to quantify inrush current by analyzing voltage differences across both switchgear terminals. Secondly, a distribution transformer energization model is proposed to evaluate ferroresonance using Q-factor constraints based on underground cable capacitance and damping resistance. Thirdly, a phase-swapping model is proposed to improve load balancing by dynamically reassigning lateral-phase connections through smart switchgears. The proposed models are further integrated into a mixed-integer nonlinear programming (MINLP) formulation to maximize the total weighted restored load while constraining inrush currents, ferroresonance, and phase imbalance. To address the nonlinearity induced by impedance matrix reordering during phase swapping, a permutation-based linearization technique is proposed. Finally, case studies on an underground PDS established based on IEEE 123-Node Test Feeder validate the effectiveness of the proposed strategy in improving uderground PDS restoration performance.
Read the full abstract

Systems and Control · Cross-listed from quant-ph

Quantum memory optimisation using finite-horizon, decoherence time and discounted mean-square performance criteria

Igor G. Vladimirov, Ian R. Petersen and Guodong Shi

This paper is concerned with open quantum memory systems for approximately retaining quantum information, such as initial dynamic variables or quantum states to be stored over a bounded time interval. In the Heisenberg picture of quantum dynamics, the deviation of the system variables from their initial values lends itself to closed-form computation in terms of tractable moment dynamics for open quantum harmonic oscillators and finite-level quantum systems governed by linear or quasi-linear Hudson-Parthasarathy quantum stochastic differential equations, respectively. This tractability is used in a recently proposed optimality criterion for varying the system parameters so as to maximise the memory decoherence time when the mean-square deviation achieves a given critical threshold. The memory decoherence time maximisation approach is extended beyond the previously considered low-threshold asymptotic approximation and to Schrödinger type mean-square deviation functionals for the reduced system state governed by the Lindblad master equation. We link this approach with the minimisation of the mean-square deviation functionals at a finite time horizon and with their discounted version which quantifies the averaged performance of the quantum system as a temporary memory under a Poisson flow of storage requests.
Read the full abstract

Systems and Control

CPU- and GPU-Based Parallelization of the Robust Reference Governor

Hamid R. Ossareh, William Shayne and Samuel Chevalier

Constraint management is a central challenge in modern control systems. A solution is the Reference Governor (RG), which is an add-on strategy to pre-stabilized feedback control systems to enforce state and input constraints by shaping the reference command. While robust formulations of RG exist for linear systems, their extension to nonlinear systems is often computationally intractable. This paper develops a scenario-based robust RG formulation for nonlinear systems and investigates its parallel implementation on multi-core CPUs and CUDA-enabled GPUs. We analyze the computational structure of the algorithm, identify parallelization opportunities, and implement the resulting schemes on modern parallel hardware. Benchmarking on a nonlinear hydrogen fuel cell model demonstrates order-of-magnitude speedups (by as much as three orders of magnitude) compared to sequential implementations.
Read the full abstract