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 22 May

Signal Processing

Broad learning system with robust adaptive kernel

Haiquan Zhao, Jinhui Hu and Xin Lua

For the performance degradation problem of broad learning system (BLS) in non-Gaussian noise environment, the variant of BLS based on M-estimator shows good robust performance. However, in most cases, the determination of the optimal loss function is often very time-consuming due to the lack of prior knowledge of the sample data. Therefore, this paper constructs a variant of BLS based on adaptive robust kernel (AR-BLS) to improve the generalization performance of the model in non-Gaussian noise environment. Adaptive robust kernel function is a general loss function that includes many common M-estimator paradigms. By alternately optimizing model weights and adaptive robust kernel parameters, AR-BLS realizes the adaptive adjustment of model robustness under different outlier noise distributions without human intervention. In addition, the iterative convergence of AR-BLS algorithm is proved based on Zangwill's global convergence theorem. Simulation experiments on multiple public datasets and actual application scenarios verify the effectiveness of the proposed method.
Read the full abstract

Signal Processing

System Design Framework for Distributed Space Antennas Using Electromagnetic Formation Flight

Seang Shim, Yuta Takahashi, Naoto Usami et al. (+1 more)

Distributed space antennas using electromagnetic formation flight (EMFF) are a promising architecture for large-aperture, long-life space communication systems. Their system design, however, is governed by coupled constraints on antenna performance, satellite mass, power generation, coil geometry, and formation-keeping power. This paper proposes a system-level design framework for EMFF-based distributed space antennas. It links phased-array requirements with satellite and formation-system sizing for a static grid under a fixed total system mass. Before system-level optimization, distributed-control simulations are used to derive a control index that quantifies the formation-maintenance requirement. This index is integrated into an optimization problem with a user-defined objective and sizing, power, coil, and sidelobe-envelope constraints. Parametric case studies examine the margin magnetic moment, prescribed transmit power, and large inter-satellite spacing. Results show that increasing system mass improves footprint reduction or effective isotropic radiated power only while satellite-level design headroom remains. In direct-to-device cases with 0.15-m spacing, generated power and coil-geometry constraints dominate the feasible aperture. In the 0.30-m large-spacing case, the required coil burden can exceed satellite-level mass, size, and power capacities, making the design infeasible despite favorable communication performance. Higher-fidelity simulations of representative designs evaluate formation maintenance under nonlinear $J_2$ dynamics and antenna gain with mutual coupling, further supporting the framework's usefulness for preliminary design. The proposed framework enables the design and evaluation of feasible static grid-based EMFF distributed antennas under coupled antenna, satellite, and control constraints.
Read the full abstract

All authors Seang Shim, Yuta Takahashi, Naoto Usami, Shin-ichiro Sakai

Signal Processing

ComHymba: Low-Complexity Domain-Informed Foundation Model for Wireless Communications

Bowen Yang, Wei Chen, Jiaming Cheng et al. (+1 more)

Wireless foundation models are a promising route to unify channel reconstruction, sensing, and beam management in future wireless communication systems, but existing designs often inherit LLM-style Transformers with quadratic token complexity and weak integration of propagation priors. This paper proposes ComHymba, a domain-informed wireless foundation model built on an asymmetric masked autoencoder for large-scale self-supervised pre-training on Channel State Information (CSI). ComHymba introduces (i) 3D spatio-temporal-frequency patchification with rotary positional embedding, (ii) domain-informed masking strategies that emulate realistic CSI sparsity and fading patterns, and (iii) a decoupled amplitude–phase weighted objective tailored to channel statistics. Architecturally, we employ Hymba blocks that fuse windowed self-attention with state space models (SSMs), enabling linear-time modeling with respect to the overall channel input size. Experiments on eight downstream tasks spanning channel state information reconstruction, environmental sensing, and beam management show consistent accuracy gains over strong task-specific baselines, together with up to a $3.3\times$ inference speedup versus Transformer backbones. Overall, ComHymba provides a scalable and efficient backbone for AI-native physical-layer intelligence.
Read the full abstract

All authors Bowen Yang, Wei Chen, Jiaming Cheng, Bo Ai

Audio and Speech Processing

StepAudio 2.5 Technical Report

Bin Lin, Bo Zhao, Boyong Wu et al. (+98 more)

Unified audio-language modeling has emerged as a prominent trend in modern speech systems, promising to bring the reasoning capabilities of large language models to auditory tasks. However, existing unified foundations often struggle to match the depth of specialized systems across automatic speech recognition (ASR), text-to-speech synthesis (TTS), and realtime spoken interaction. Bridging this gap remains an open challenge. This report presents StepAudio 2.5, a unified audio-language foundation model that matches or exceeds specialized systems across all three capabilities. Rather than treating these tasks as architecturally distinct, we operate on the premise that once text and audio share a multimodal representational space, task specialization becomes a matter of operational regimes: data construction, optimization targets, and decoding constraints. Guided by this insight, we advance the post-training paradigm from standard supervised learning to task-tailored Reinforcement Learning from Human Feedback (RLHF), using it as the primary mechanism to define complex optimization targets. We leverage this RLHF-centric alignment, alongside specialized decoding, to shape a shared backbone into three distinct operational modes. Concretely, the ASR branch advances transcription efficiency via verifiable multi-token decoding; the TTS branch achieves controllable, expressive synthesis through preference-based RLHF and context-rich supervision; and the Realtime branch realizes low-latency, persona-consistent dialogue via generative reward modeling within an RLHF framework. On standard benchmarks, StepAudio 2.5 achieves state-of-the-art results across ASR, TTS, and Realtime, demonstrating that a singular audio-language foundation can successfully internalize the distinct deployment objectives of speech understanding, generation, and live interaction.
Read the full abstract

All authors Bin Lin, Bo Zhao, Boyong Wu, Chao Yan, Chen Wu, Cheng Yi, Chengyuan Yao, Daijiao Liu, Fei Tian, Feng Tian, Haiyang Sun, Haoyang Zhang, Jiangjie Zhen, Jinglan Gong, Jun Chen, Li Xie, Peilin Li, Peng Yang, Pengfei Tan, Qingjian Lin, Runze Li, Shenghua Hu, Siyi Zhou, Wenwen Qu, Xiangyu Li, Xiangyu Tony Zhang, Xuerui Yang, Yang Yang, Yechang Huang, Yu Fu, Yuchu Luo, Yuxin Li, Yuxin Zhang, Zhengyan Sheng, Brian Li, Chang Zeng, Changlin Zhang, Chen Geng, Chenghao Dong, Chengli Feng, Dan Zhou, Danni Wan, Di Chen, Die Zhang, Dongqing Pang, Guanglong Yang, Guoqiang Hu, Huangxi Zhu, Jianzheng Gao, Jinghua Liang, Jinmei Wan, Junjie Yuan, Kang An, Lei Lei, Limin Zhong, Lun Cai, Mengqiang Ren, Min Xu, Mingliang Li, Mingxiao Li, Na Wang, Qiang Tong, Qiaoling Huang, Qingfu Du, Rui Wang, Shengchen Zhou, Shi Qiu, Shihao Peng, Shiliang Yang, Siqi Tu, Tianjiao Deng, Ting Xu, Tong Wang, WeiMing Niu, Wuxun Xie, Xianwei Zhang, Xianyu Feng, Xiaojia Liu, Xing Chen, Xiongbin Wu, Yan Wu, Yang Li, Yi Liu, Yifan Zhang, Yile Liu, Yongshen Long, Yu Luo, Yuanhao Ding, Yuhao Wang, Yuhe Yin, Yunfang Xu, Yuxiang Yang, Zhiguo Huang, Zhiyue Wu, Zichao Li, Zichao Zhou, Daxin Jiang, Future Li, Gang Yu, Xiangyu Zhang, Yibo Zhu

Signal Processing

Communication Security and Sensing Privacy in FMCW-Based ISAC Through Signal Modulation

Murat Temiz and Christos Masouros

This study proposes a novel radar-centric signaling design and architecture for secure integrated sensing and communication (ISAC) systems. The proposed framework is designed to provide robust physical layer security for data transmission while simultaneously enhancing sensing privacy. It employs index modulation and phase coding over frequency-modulated continuous-wave radar (FMCW) chirps, where index modulation (IM) provides an outer layer of data security, and we explicitly design the phase coding (PC) to perturb the resulting signal's ambiguity function (AF) to enhance sensing privacy. This design reduces the risk of unauthorized surveillance by rendering target velocity estimation practically infeasible for unauthorized passive sensing hardware (i.e., a sensing eavesdropper, S-Eve) and significantly impairing its range estimation capabilities. Furthermore, this study also presents the transmitter and receiver architectures required for effective modulation and demodulation of the proposed ISAC signaling and for performing sensing at the legitimate sensing hardware. Simulation results show that the proposed approach achieves high data throughput while enhancing communication security and sensing privacy.
Read the full abstract

Signal Processing

Movable-Antenna-Enhanced ISAC: Optimal Antenna Trajectory and Beamforming Design

Yifei Wu, Dongfang Xu, Derrick Wing Kwan Ng et al. (+2 more)

Integrated sensing and communication (ISAC) is a key enabling technology for next-generation wireless networks. However, most existing ISAC systems rely on fixed-position antennas, which restrict performance when balancing sensing and communication objectives. Movable antenna (MA) technology introduces additional spatial degrees of freedom through antenna mobility, yet existing studies on MA-enabled ISAC schemes mainly consider static antenna repositioning and fail to fully exploit this capability. By leveraging spatio-temporal sampling enabled by antenna motion, optimized MA trajectories can synthesize large virtual aperture arrays, thereby improving angular resolution and reducing sensing ambiguity. To this end, this paper investigates a dynamic MA-enabled ISAC system and studies the joint design of MA trajectories and transmit beamforming. We formulate a joint trajectory and beamforming optimization problem to minimize sensing beampattern mismatch under communication quality-of-service constraints. A branch-and-bound-based algorithm is developed to obtain the globally optimal solution. Numerical results show that the proposed framework significantly outperforms baseline schemes with only one or two antenna repositioning steps, demonstrating its practical feasibility.
Read the full abstract

All authors Yifei Wu, Dongfang Xu, Derrick Wing Kwan Ng, Wolfgang Gerstacker, Robert Schober

Signal Processing · Cross-listed from stat.ME

Generalized Stochastic Approximation of the Log-Likelihood Ratio for Robust Sequential Change-Point Detection

Serhii Zabolotnii

Generalized stochastic approximation replaces the log-likelihood ratio of a sequential change-point problem by an affine function of a fixed feature dictionary, whose coefficients solve a normal system in the dictionary's moments under the pre- and post-change laws. The increment is a rescaled orthogonal projection of the bounded score, and the information it carries is bounded by the triangular discrimination between the laws. The dictionary decides what is detectable: a symmetry shared by both laws annihilates a whole parity at every order, and one further column raises the information by an explicit bordered-metric increment. A single efficiency factor, at most one, governs all three procedures the increment drives – cumulative-sum, Shiryaev-Roberts and Shiryaev – through false-alarm and delay bounds valid at every threshold. Estimated coefficients are consistent and asymptotically normal. A Monte-Carlo study measures the factor against the delay ratio it predicts, and locates the order at which the dictionary stops paying.
Read the full abstract

2605.23419 · 22 May · v4: scope narrowed to the theory. The benchmark study of v1-v3 is withdrawn: a scoring error counted a run with no alarm as a detection, inflating the proposed method only. Theory and proofs stand. The normal system is now normalised F = C_0+C_1, halving J(s) and doubling theta_0 – units, not a correction of Theorem 2. Full account on page 1. 29 pages

Abstract PDF $STOC ×2$SYMM ×1

Signal Processing

Energy-Efficient THz Sensing with Hybrid THz/VLC Communication Under Human Blockage Effects

Hanshita Prabhakar, Neetu R.R. and Vivek Ashok Bohara

This paper presents an energy-efficient indoor system integrating \ac{THz} with \ac{VLC}. \ac{THz} communication offers ultra-high-capacity links but is limited by severe path loss, atmospheric absorption, and susceptibility to blockages. In contrast, \ac{VLC} provides robust, wide indoor coverage with illumination support, thereby enabling reliable, high-speed hybrid connectivity. To leverage their respective strengths, we propose a hybrid framework that integrates \ac{$THz_s-AP$} with hybrid \ac{$THz_c/VLC_c-AP$}, enabling reliable coverage and enhancing the \ac{EE} from an \ac{ISAC} perspective. We first perform optimal power allocation between the \ac{$THz_s-AP$} and \ac{$THz_c-AP$} to optimized the set of users served by the \ac{$THz_c-AP$} link, considering monostatic sensing performance metrics such as \ac{$P_d$}, \ac{$FA_p$} and \ac{$SC_p$} under the impact of human blockages are evaluated. Subsequently, the overall network power consumption is minimized via a mixed-integer linear programming (MILP) optimization that optimally selects the active \ac{$VLC_c-APs$} and assigns transmit powers. Furthermore, extensive performance evaluations are conducted to analyze key metrics, including average energy efficiency, average spectral efficiency, average sensing rate, and average communication rate. Simulation results demonstrate that, under \ac{THz} sensing, most users are connected to the \ac{$THz_c-AP$} in the absence of blockages, whereas in the presence of blockages, the majority are served by the \ac{$VLC_c-APs$}. Overall, all users maintain reliable coverage with high \ac{EE}.
Read the full abstract

Signal Processing

Stochastic Geometry Analysis of Uplink CUMA-Enabled Cellular Networks

Chenguang Rao, Kai-Kit Wong, Xusheng Zhu et al. (+3 more)

Uplink cellular networks are interference-dominated but interference channel state information (CSI) is rarely available at scale. The emerging fluid antenna system (FAS) concept, which provides additional spatial degrees of freedom through multi-port reconfiguration, offers a promising alternative to CSI-intensive multi-antenna processing. Building on this concept, compact ultra-massive arrays (CUMA) exploit large-scale port selection with low implementation complexity. In each uplink transmission, CUMA activates a subset of ports based on only the desired-link CSI and combines the selected ports via simple superposition, yielding coherent enhancement of the desired user signal, while inter-cell interference aggregates largely non-coherently due to the random superposition effect. Consequently, CUMA is well suited to multi-cell uplink scenarios where CSI is limited. In this paper, we analyze uplink CUMA in multi-cell cellular networks using a stochastic geometry framework. We derive a tight approximate expression for the signal-to-interference ratio (SIR) coverage probability, and further characterize the average user rate and cell sum-rate. The analysis quantifies how key design parameters impact performance and reveals the scaling behavior with network densification. Simulation results validate the accuracy of the derived expressions and show that uplink CUMA achieves competitive, and often superior, performance relative to conventional schemes under practical CSI constraints, highlighting its potential as a low-complexity, hardware-efficient uplink solution for future large-scale cellular networks.
Read the full abstract

All authors Chenguang Rao, Kai-Kit Wong, Xusheng Zhu, Hanjiang Hong, Chan-Byoung Chae, Ross Murch

Systems and Control

A Distributed Framework for Data-Driven Safe Coordination in Leader-Follower Networks

Mirhan Urkmez, Maryam Sharifi and Shahab Heshmati-Alamdari

This paper addresses connectivity preservation in leader-follower multi-agent systems with unknown control-affine dynamics and local state information. We introduce the distributed data-driven zeroing control barrier function (3D-ZCBF) framework, which ensures the controlled invariance of safety sets by identifying derivative bounds from input-state data without requiring explicit models of high-dimensional agent dynamics. In this work, we derive the explicit, decoupled safety conditions necessary to maintain connectivity for leader-leader, and follower-follower pairings. These individual constraints, along with the leader-follower conditions, are aggregated into explicit system-wide conditions that formally guarantee the preservation of the entire communication network. Furthermore, we provide a quantitative analysis demonstrating how the size of the collected data set and the accuracy of the learned Jacobian bounds impact the feasibility of the safety certificates. The proposed conditions are implemented via a projection-based controller, and simulations confirm that these explicit 3D-ZCBF requirements effectively maintain system-level connectivity using only local, two-hop information.
Read the full abstract

Systems and Control

Physics-informed sparse identification-based tube model predictive control for aerial vehicles

Tayyab Manzoor, Yasir Ali, Yuanqing Xia et al. (+2 more)

Autonomous aerial vehicles necessitate control strategies that balance computational efficiency with robust performance in dynamic operational environments. This paper proposes a model predictive control (MPC) framework for aerial platforms that leverages physics-informed machine learning (PIML) to achieve an optimal balance between computational tractability and robust performance. At the core of the proposed approach lies a sparse, control-affine model identified via the PIML method, which provides a parsimonious yet interpretable representation of the system dynamics by embedding first-principles knowledge and learning residual uncertainties from operational data. This model is incorporated within a robust MPC scheme that adopts a high-order Runge-Kutta discretization to ensure prediction accuracy and an adaptive tube-based mechanism to guarantee constraint satisfaction under uncertainty. The online adaptation of the tube, directly informed by the residual error of the PIML model, ensures robust stability without introducing excessive conservatism. Rigorous theoretical proofs are provided to establish recursive feasibility and stability. Numerical simulations and experiments on a quadrotor demonstrate that our method significantly reduces computational load compared to nonlinear MPC and robust MPC using a first-principles high-fidelity model, while outperforming PID, nonlinear MPC, neural-network-based MPC, and fixed-tube robust MPC in tracking performance and robustness, showcasing the practical efficiency of the proposed PIML-based control synthesis for resource-constrained aerial systems.
Read the full abstract

All authors Tayyab Manzoor, Yasir Ali, Yuanqing Xia, Lijie You, Yan Wang

Systems and Control

From Visual to Digital: Coordination Scheduling and Its Effect on Safety and Efficiency in UAM Corridors

Akihiro Fujita, Sasinee Pruekprasert, Katsuhiro Nishinari et al. (+1 more)

This paper explores scalable coordination strategies for urban air mobility (UAM) corridors by comparing two representative approaches. The first, inspired by visual flight rules (VFR), is a local coordination strategy relying on spatial information available to each vehicle. The second, conceptually aligned with digital flight rules (DFR), is a global coordination strategy based on shared estimated times of arrival (ETAs) at constrained waypoints (CWPs). To support this comparison, we introduce a lightweight disturbance-avoidance mechanism that enables vehicles to adjust their ETAs in response to forecasted disruptions using shared information. We evaluate these approaches through numerical simulations under varying disturbance levels, comparing the locally reactive VFR-style scheme with the globally coordinated DFR-style scheme. Results show that VFR achieves high throughput in low-traffic scenarios but becomes increasingly prone to collisions at higher traffic densities unless conservative separation is enforced, which reduces traffic efficiency. In contrast, DFR maintains more consistent safety performance and traffic efficiency, even under moderate ETA update propagation delays. These findings highlight the advantages of DFR-style global coordination in managing high-density air traffic control (ATC) operations within UAM corridors.
Read the full abstract

All authors Akihiro Fujita, Sasinee Pruekprasert, Katsuhiro Nishinari, Shinji Nakadai

Systems and Control

Safety-Assured Arrival Scheduling in Sequential UAM Corridor Sections under Speed and Separation Constraints

Sasinee Pruekprasert, Shinji Nakadai and Katsuhiro Nishinari

This paper presents a safety-assured arrival-scheduling framework for Urban Air Mobility (UAM) corridor operations. We propose an analytical method to compute a sufficient ETA gap at Constrained Waypoints (CWPs) that guarantees longitudinal separation along sequential corridor sections with heterogeneous speed limits. The resulting ETA-gap condition depends on section-specific speed bounds and the required separation distance, providing an efficiently computable rule suitable for integration into future digital ETA-scheduling and air traffic management systems. We show that the computed ETA gap ensures safe separation across all corridor sections under prescribed section travel times and speed limits. Numerical simulations for a decreasing-speed corridor confirm that vehicles coordinated with the proposed mechanism adjust their speeds to maintain the required spacing, avoid potential collisions, and support improved traffic flow compared with unscheduled operations.
Read the full abstract

Image and Video Processing

Efficient Learned Image Compression without Entropy Coding

Hao Cao, Wenqi Guo, Zhijin Qin et al. (+1 more)

Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present Entropy-Coding Free Learned Image Compression (EF-LIC), a multi-rate framework that generates compact representation by removing statistical and correlation redundancy with low coding latency. First, we introduce unconstrained vector quantization and prove that its index distribution approaches the maximum-entropy bound, yielding minimal statistical redundancy. Second, we propose a context-conditioned autoregressive transform that directly reparameterizes the latents to reduce inter-dependency. Theoretical analysis shows that EF-LIC can remove correlation redundancy as effectively as typical LIC with entropy coding, leading to comparable compression performance. Experiments show EF-LIC achieves up to 67.86% bitrate reduction over MS-ILLM on Kodak with LPIPS. Ablation studies further show EF-LIC matches the compression performance of its entropy-coding based variant while achieving over $3\times$ faster encoding and $5\times$ faster decoding.
Read the full abstract

All authors Hao Cao, Wenqi Guo, Zhijin Qin, Jungong Han

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

SpinFlow: A Physics-Informed Spin Field Framework for Traffic Phase Inference and Transition Detection

Haopeng Deng, Fucheng Zheng and Xinhai Xia

Active traffic management (ATM) is frequently hindered by traditional macroscopic models and rigid empirical thresholds that fail to capture metastable phase precursors, resulting in delayed, reactive interventions. To address this, we propose SpinFlow, a physics-informed spin-field framework unifying Kerner's three-phase theory with statistical physics for continuous macroscopic traffic phase inference. Inspired by the Heisenberg model, SpinFlow parametrizes spatially varying phase weights via a latent spin vector and a competitive-equilibrium mapping, allowing synchronized flow to emerge naturally. A physics-regularized Expectation-Maximization algorithm inverts this latent structure from high-resolution trajectories, jointly optimizing the spin field while softly enforcing mass conservation and spatial smoothness. We introduce the Phase Equilibrium Degree (PED) to quantify structural alignment and topologically localize phase-transition points. Across four real-world trajectory datasets, SpinFlow achieves $R_{q}^{2}$ up to 0.940, PED drops of 94.9-100%, and interpretable phase maps that outperform three heterogeneous baselines on forward accuracy, physics consistency, and bottleneck localization. SpinFlow pinpoints congestion nucleation without prior network topology, yielding a data-driven, physics-consistent trigger for ATM.
Read the full abstract

Audio and Speech Processing

Evaluating the Temporal Detection Capability of Integrated Gradients Applied on Sound Classifier

Martynas Dumpis and Tuomas Virtanen

Gradient-based attribution methods can highlight input regions important for neural network predictions, but their effectiveness for temporal sound event detection in audio classification has not been systematically evaluated. This paper assesses whether integrated gradients (IG) can temporally detect sound events when applied to a classifier trained without temporal supervision. We use synthetic polyphonic audio with ground truth timestamps to measure alignment between IG attributions and event boundaries. On a 10-class domestic sound dataset, IG achieves mean Intersection over Union (IoU) of 0.39, frame-level F1 of 0.52, and Pointing Game accuracy of 82.6%. For comparison, a framewise CNN trained with weak supervision (FW-WS, clip-level training labels) achieves 0.42 IoU, 0.55 F1, and 97.3% PG, while a strongly supervised variant (FW-SS, frame-level training labels) reaches 0.45 IoU, 0.58 F1, and 97.9% PG. Overall, these results suggest that post-hoc IG captures meaningful temporal activity patterns of sound events, with localization performance approaching models that explicitly produce frame-level predictions. All methods substantially outperform random and energy-based baselines.
Read the full abstract

Image and Video Processing

Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring

Shaoqing Duan, Haofei Song, Xintian Mao et al. (+2 more)

Defocus deblurring in pathological microscopy remains challenging due to the spatially varying and locally discontinuous nature of optical blur induced by a position-dependent integral imaging process. Existing deep learning methods, constrained by shift-invariance assumptions and limited interpretability, are not well suited to such heterogeneous blur patterns. Neural operators provide a principled alternative by modeling defocus formation directly as an integral operator, offering a new perspective on defocus deblurring. However, most existing neural operator architectures for low-level vision rely on globally parameterized kernels that assume smoothness and stationarity, limiting their ability to model heterogeneous and locally discontinuous blur patterns. To address this limitation, we propose the Discontinuous Galerkin Neural Operator (DGNO), which parameterizes the integral kernel using a discontinuous Galerkin formulation with element-local volume operators and interface numerical fluxes. DGNO provides a principled combination of locality, heterogeneity modeling, and global coherence while preserving the underlying physics of optical image formation. Extensive and insightful experiments demonstrate that DGNO surpasses state-of-the-arts, delivering sharper reconstructions, robust handling of spatially varying blur, and scalable high-resolution performance. The code will be released at https://github.com/DeepMed-Lab-ECNU/Single-Image-Deblur.
Read the full abstract

All authors Shaoqing Duan, Haofei Song, Xintian Mao, Qingli Li, Yan Wang

Systems and Control · Cross-listed from cs.RO

6G Communication Networks Enabling Embodied Agents: Architecture and Prototype

Lipeng Dai, Luping Xiang and Kun Yang

Embodied agents, which couple intelligent decision-making with physical actuation in the real world, impose far more stringent and heterogeneous communication requirements than purely software-based agents. While 6G promises sub-millisecond latency, ultra-high reliability, native intelligence, and integrated sensing, systematic studies on how to exploit these capabilities for embodied agent communication remain limited. This article investigates 6G-enabled communication systems for embodied agents from both conceptual and engineering perspectives. First, we review the concept, embodiment value of embodied agents, and clarify their distinctions from disembodied agents. Then, we analyse the symbiotic relationship between embodied agents and 6G networks. We highlight how key 6G enablers can support the stringent requirements of human-robot interaction. Furthermore, we demonstrate the proactive role of embodied agents in bolstering communication networks through coverage extension, environmental sensing, and physical world understanding. Building on these insights, we propose a hierarchical communication architecture for human-robot remote interaction, comprising a human-intent perception layer, an open radio access network (O-RAN)-based transport layer, an intelligent intermediary layer, and an embodiment layer. To validate its feasibility, we implement an end-to-end prototype that integrates a haptic device, an industrial robotic arm, an intermediary platform, and a 5G O-RAN testbed. Experimental results demonstrate millisecond-level latency and stable closed-loop operation, confirming the practicality of the proposed architecture and providing a reference for future 6G-embodied agent research and industrial deployments.
Read the full abstract

Audio and Speech Processing

UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment

Yuanyuan Wang, Dongchao Yang, Yayue Deng et al. (+4 more)

Evaluating speech generation still relies heavily on human judgments, such as Mean Opinion Score (MOS), which are expensive, subjective, and difficult to reproduce at scale. While a few recent studies have begun to explore AudioLLM-based judge models, existing efforts typically target only a narrow set of scenarios (e.g., utterance-level quality or single-turn dialogue) and provide limited coverage of diverse speech generation tasks and evaluation dimensions. In this work, we propose UniSRM, a unified speech reward model that can support multi-dimensional, interpretable reward signals with reliable reasoning. To support training and evaluation, we introduce UniSRM-Data and UniSRM-Bench, covering speech evaluation tasks from utterance-level quality to context-level coherence. Based on this dataset, we present the unified speech reward model, UniSRM, with a two-stage pipeline that enables reasoning-based fine-grained assessment. Furthermore, we introduce Reasoning-Consistent Rewards to improve the reliability of the reasoning process. Experiments show that UniSRM delivers more reliable and human-aligned judgments across a broad range of speech evaluation tasks, offering a practical foundation for scalable and unified evaluation of speech quality.
Read the full abstract

All authors Yuanyuan Wang, Dongchao Yang, Yayue Deng, Zhiyong Wu, Yiwen Guo, Helen Meng, Xixin Wu

Systems and Control · Cross-listed from cs.RO

Signal Temporal Logic Motion Planning via Graphs of Convex Sets

Yu Chen, Ancheng Hou, Mingyang Feng et al. (+2 more)

This paper investigates continuous-time motion planning under Signal Temporal Logic (STL) specifications. The goal is to generate smooth robot trajectories that satisfy high-level logical and timing requirements while respecting low-level motion constraints. To this end, we propose an efficient framework that combines timed-automata reasoning with graphs of convex sets (GCS). An STL specification is first represented by a timed automaton, which is then coupled with a convex decomposition of the configuration space to form a joint transition system encoding both task progress and region occupancy. Based on this joint transition system, the STL motion-planning problem is reformulated as a shortest-path problem over a GCS, whose solution induces a smooth Bézier-spline trajectory satisfying the STL specification, smoothness requirements, and velocity bounds. We establish the soundness of the proposed formulation and analyze its computational complexity, showing that, once the timed automaton and convex decomposition are fixed, the convex relaxation scales polynomially with the configuration-space dimension and the Bézier degree. We further develop a compact timed-automaton construction for an expressive STL fragment using dedicated templates and Boolean composition. Numerical experiments on low-dimensional benchmarks, a $3$-D quadrotor, a $30$-DoF humanoid, and a hardware experiment on a UR-3 robot arm demonstrate that the proposed method efficiently solves complex STL motion-planning problems and produces smooth executable trajectories.
Read the full abstract

All authors Yu Chen, Ancheng Hou, Mingyang Feng, Xiao Yu, Xiang Yin

Systems and Control

Experimental Evaluation of Data Upload Efficiency and Guiding Challenges for a Vehicular-to-Road System Using 60-GHz mmWave Ultra-Spots

Phuc Duc Nguyen, Kazuhiro Maruyama, Keitarou Kondou et al. (+1 more)

Maximizing data uploading efficiency in a vehicular-to-road data uploading system using millimeter-wave communication is a challenging issue, as the wireless zone is often critically narrow, and vehicles can easily fail to pass through it without the aid of an autonomous guiding system. Variations in driving routes, speeds, approach angles, and distances to the ultra-spot can significantly affect data transmission performance, leading to either efficient or suboptimal results. This study presents a comprehensive analysis based on 75 experimental cases to identify the optimal travel trajectory and conditions that allow the vehicle to pass through the ultra-spot and enhance data transmission effectively. Experimental results show that with an optimal travel trajectory, appropriate movement speed, antenna placement, and prior estimation of the ultra-spot area, the amount of transferred data can be improved by 6 to 8 times.
Read the full abstract

All authors Phuc Duc Nguyen, Kazuhiro Maruyama, Keitarou Kondou, Yozo Shoji

Signal Processing

Fundamental Bounds and Efficient Estimation for Dead-Time-Constrained Event Detection, with Application to Single-Photon Lidar

Frederic J. N. Jorgensen and Steven G. Johnson

We develop an asymptotic statistical theory for parameter estimation from a class of non-i.i.d. periodic binary event-detection processes subject to nonparalyzable dead time and gating, which we call "dead-time event detection" (DED) processes. Such processes arise in single-photon lidar, fluorescence lifetime imaging, X-ray astronomy, and particle or radiation flux measurements in nuclear physics, where each detection renders the radiation/particle detector inactive for a recovery interval. Our theory quantifies how dead time and gating affect the fundamental lower bounds of estimation and identifies practical estimators that attain these bounds. First, we identify a sufficient statistic, showing in particular that activation counts can carry statistically useful information discarded by conventional histogramming hardware. We then prove local asymptotic normality and derive the corresponding Fisher-information rate, thereby obtaining fundamental lower bounds for estimation from DED processes. We prove that the maximum likelihood estimator (MLE), widely used in DED applications, attains these lower bounds. Since computing the MLE typically requires solving a nonconvex optimization problem, we also propose Le Cam one-step estimators, which attain the same asymptotic bounds with only a single local correction rather than iterative optimization. We illustrate the validity of our asymptotic theory and the practical usefulness of one-step estimators through the example of single-photon lidar in both simulations and real-data experiments.
Read the full abstract

Image and Video Processing

GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences

Pengfei Song, Fangjin Liu, Wenwen Zeng et al. (+5 more)

Contemporary glioma diagnosis integrates molecular features with histopathology to guide clinical decision-making. However, in clinical settings, divergent imaging protocols result in incomplete MRI sequences, leading to two primary challenges: forcing existing frameworks to discard a large portion of clinical data during training and consequently limiting their clinical applicability. To address these limitations, we propose GMENet, a Generative Mixture of Experts Network for multi-center glioma diagnosis with incomplete imaging sequences. Firstly, we design a Cross-attention-based Gated Generation Module that synthesizes missing sequence features from available sequences via cross-attention and dynamic gating mechanisms, incorporating a cycle-consistency loss to preserve semantic integrity. Secondly, we introduce a Dynamically Weighted Experts Fusion Module that performs mixture-of-experts interaction and confidence-aware fusion over original and synthesized dual-sequence features for multi-task prediction. We evaluate GMENet on a multi-center cohort of 1,241 subjects from four in-house datasets and two public repositories. Experiments show that GMENet expands clinically usable training data by 97%, relative to complete-sequence-only data. Furthermore, it consistently outperforms state-of-the-art methods trained on complete data, demonstrating improved robustness under cross-center distribution shifts.
Read the full abstract

All authors Pengfei Song, Fangjin Liu, Wenwen Zeng, Yonghuang Wu, Chengqian Zhao, Feiyu Yin, Xuan Xie, Jinhua Yu

Signal Processing

Physics-Informed Digital Twins for Channel Estimation and Traffic Prediction of Non-Terrestrial Networks

Xinyu Huang, Yixiao Zhang, Xue Qin et al. (+4 more)

In non-terrestrial networks (NTN), high-speed satellite orbital motion, limited pilot signaling resources, and spatiotemporally heterogeneous traffic make accurate channel and traffic state characterization particularly challenging. In this paper, we propose a physics-informed digital twin (DT) framework for channel estimation and traffic prediction. Particularly, it formulates channel state information (CSI) reconstruction as a controllable generative process guided by physical-prior tensors. Through a physics-aware attention mechanism, it effectively reconstructs the real-time full-resolution CSI from highly sparse and outdated pilots. Then, we develop an orbit-adaptive spatiotemporal graph neural network for traffic prediction. By leveraging a dual-stream attention mechanism to capture intra- and inter-plane spatial dependencies and a gated recurrent unit to model temporal evolution, the neural network effectively predicts stochastic traffic residuals, which are integrated with the deterministic physical traffic baseline to form the complete traffic state. To evaluate the proposed DT framework, we establish a high-fidelity NTN DT simulation platform based on real-world Starlink ephemeris, global population, and ERA5 weather data. Experimental results demonstrate that our framework significantly outperforms state-of-the-art baselines in both CSI reconstruction and traffic prediction accuracy.
Read the full abstract

All authors Xinyu Huang, Yixiao Zhang, Xue Qin, Mingcheng He, Junling Li, Weihua Zhuang, Xuemin Shen

Systems and Control

Convex Hybrid Modeling: An Operator-Based Approach

Wentao Tang

While machine learning can accurately model process systems, models for decision making should also be structurally simple and physically interpretable. In process control, for example, (nearly) linear models are favored than nonlinear ones, promoting the use of operator theory, which “universally” represents a nonlinear system by a nonparametric operator. On the other hand, interpretability requires by a “non-universal”, parametric nonlinear model family satisfying first principles; these constraints tend to complicate the learning procedure. This paper considers hybrid modeling by formulating convex learning problems that account for interpretability systematically and give surrogate models efficiently. Three settings are discussed – (i) regularization around a particular “reference model”, (ii) restriction on an “interpretable subspace”, and more generally, (iii) restriction on a “interpretable manifold” that is nonlinearly parameterized. In the more general setting, by introducing an operator-theoretic technique to re-parameterize models in the “lifted” parameters (“canonical features”, potentially infinite-dimensional), the system is regarded as a kernel-based mixture of interpretable models. Application to both static and dynamic models are exemplified in numerical studies.
Read the full abstract

Signal Processing

Self-Calibration DOA Estimation for Movable Antenna Systems with Antenna Position Errors

Chengzhi Ye, Ruoyu Zhang, Wen Wu et al. (+1 more)

In this letter, we investigate the direction-of-arrival (DOA) estimation problem for wireless sensing with movable antenna (MA) systems in the presence of unknown antenna position errors (APE). To achieve robust wireless sensing, we transform the DOA estimation problem with APE into an optimization problem via the orthogonality between the steering vector and the noise subspace. Then we propose an alternating optimization (AO)-based self-calibration estimation, which consists of two stages and iteratively estimates the APE and DOA. Specifically, in the first stage, by fixing the APE, the problem reduces to the classical DOA estimation problem, which is solved using the multiple signal classification (MUSIC) algorithm. In the second stage, we fix the DOA to estimate the APE. By applying the Lagrange multiplier technique to the subproblem, we obtain a closed-form expression for the APE estimation. Simulation results demonstrate the superior DOA estimation performance of the proposed self-calibration algorithm for MA systems compared to the existing approaches.
Read the full abstract

All authors Chengzhi Ye, Ruoyu Zhang, Wen Wu, Byonghyo Shim

Image and Video Processing

STAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding

Jiahe Meng, Weiming Zeng, Yueyang Li et al. (+5 more)

Electroencephalography (EEG) visual decoding remains challenging due to the modality gap between low-SNR neural signals and highly structured vision–language spaces, making direct cross-modal alignment unstable. To address this, we propose STAMBRIDGE, a versatile two-stage framework that sequentially tackles feature conditioning and cross-modal alignment. First, we introduce a Spectral-Temporal Amplitude-aware Modulation (STAM) to extract well-conditioned EEG representations. By replacing hard frequency masking with amplitude-derived soft channel weighting and multi-scale temporal convolutions, STAM explicitly preserves frequency-aware transients while reducing the risk of time-domain ringing artifacts. Building upon these robust neural features, we further introduce a model-agnostic Mid-Feature Semantic Bridge (MFSB) that constructs a regularized intermediate space through directed cross-modal interactions, enabling staged distillation and more stable semantic alignment. Experiments on the THINGS-EEG benchmark show competitive 200-way zero-shot retrieval performance, with 34.50% Top-1 and 65.95% Top-5 accuracy. In addition, embeddings learned by STAMBRIDGE produce semantically coherent image reconstructions with a diffusion model, demonstrating robust EEG-to-vision semantic alignment. The code is available at: https://github.com/thabeatmjh/STAMBRIDGE.
Read the full abstract

All authors Jiahe Meng, Weiming Zeng, Yueyang Li, Bo Chai, Hongjie Yan, Zhiguo Zhang, Wai Ting Siok, Nizhuan Wang

Systems and Control

Deception and Counter Deception in Adversarial Graph Traversal Game

Violetta Rostobaya, James Berneburg and Daigo Shishika

We study deception in adversarial graph traversal, where a mobile agent seeks to reach a goal with minimum cost while an adversary alters edge costs to increase the total traversal cost. Unlike prior works that assume fixed observer-deceiver roles, we model this problem with two-sided incomplete information in which both players possess private information and update beliefs from observed actions. To solve the resulting indefinite-horizon game, we develop an adaptation of the Extensive-Form Double Oracle (XDO) algorithm. While the standard XDO algorithm is designed for finite games, the proposed adaptation ensures bounded computation despite endogenous game termination. We show that the proposed algorithm terminates in finite time and returns an epsilon-Nash equilibrium. Finally, we use Value of Information to characterize the deceptive and counter-deceptive behaviors that emerge from equilibrium strategies.
Read the full abstract

Signal Processing

Deep-Learning-Aided Successive Cancellation List Flip Decoding for Polar Codes

Fu-Siang Liang, Shan Lu and Yeong-Luh Ueng

Polar codes are the first error-correcting code proven to achieve channel capacity based on infinite code length. The Successive Cancellation List Flip (SCLF) decoding algorithm was proposed by flipping an erroneous bit during the next decoding attempt. To identify the erroneous bits, the Log-Likelihood Ratio (LLR) is used to indicate the reliability of each decision bit. To improve the accuracy of the erroneous bit prediction, we propose deep-learning-aided (DL-aided) SCLF decoding algorithms. We first offer a stacked LSTM network that contains new features to train our models, which are able to improve the accuracy of the prediction of positions of erroneous bits. Then we separately train the stacked LSTM models to predict the position of both the first and second erroneous bits and whether to continue flipping. As a result, the DL-aided SCLF decoding algorithms based on the proposed stacked LSTM \mbox{flip-1} model, stacked LSTM \mbox{flip-2} model, and the stacked LSTM \mbox{continue-flipping} check (CFC) model are able to provide a better performance at a lower number of average decoding attempts when compared to other state-of-the-art decoding algorithms.
Read the full abstract

Thursday 21 May

Signal Processing

CLSP-REQA: A Real-Time Quality-Aware Closed-Loop Seizure Prediction Framework with Mamba-BiLSTM and Confidence-Gated Intervention

Mufeng Chen, Qi Wu, Bingchao Huang et al. (+4 more)

Reliable seizure prediction is a prerequisite for closed-loop neurostimulation therapy, yet existing methods rarely account for the variability in EEG signal quality encountered in real-world deployment, and the overwhelming majority adopt non-strict evaluation protocols that overestimate generalisation performance. We propose CLSP-REQA (Closed-Loop Seizure Prediction with Real-time EEG Quality Assessment), a unified framework that embeds a lightweight signal quality estimator directly within the prediction pipeline. A Real-time EEG Quality Assessment (REQA) module runs in parallel with a Mamba-BiLSTM backbone, producing a scalar quality score q in [0,1] that modulates output confidence through a tiered non-linear fusion function (ECLO). Under strict cross-patient evaluation on the CHB-MIT Scalp EEG Database (n = 23 subjects, 198 seizures), CLSP-REQA achieves an AUC-ROC of 0.7426 +- 0.0199, outperforming the unadapted cross-patient baseline of 0.69 reported by Jemal et al., using only 16 EEG channels compared to 23 in prior work, and without requiring any target-patient data or domain adaptation. On the SIENA Scalp EEG Database (n = 14 subjects, 47 seizures), CLSP-REQA achieves AUC 0.7012 +- 0.0249, substantially surpassing the best domain-adapted cross-patient result of 0.61 on the same dataset, demonstrating strong cross-dataset generalisation. The framework outputs a structured four-tuple (p, q, c, Phi_SHAP) directly compatible with closed-loop neurostimulator interfaces.
Read the full abstract

All authors Mufeng Chen, Qi Wu, Bingchao Huang, Xiwen Lai, Zekai Chen, Xinge Ouyang, Quansheng Ren