Papers

Video-language models (VLMs) are reshaping video querying services, bringing unified solutions to complex perception and reasoning tasks. However, deploying large VLMs in real-world systems remains challenging due to their high resource demands, and remote-based deployment often results in unacceptable response delays. Although small, locally deployable VLMs offer faster responses, they unavoidably fall short in accuracy. To reconcile this trade-off, we propose QuickGrasp, a responsive, quality of service (QoS)-aware system that bridges this gap through a local-first architecture with on-demand edge augmentation. Built upon the highly modular architecture of VLMs, QuickGrasp shares the vision representation across model variants to avoid redundant computation. To maximize system-wide efficiency, QuickGrasp introduces three key designs: accelerated video tokenization, query-adaptive edge augmentation, and delay-aware, accuracy-preserving vision token density configuration. We implement a prototype of QuickGrasp and evaluate it across multiple video understanding benchmarks. The results show that QuickGrasp matches the accuracy of large VLMs while achieving up to a 12.8x reduction in response delay. QuickGrasp represents a key advancement toward building responsive video querying services for open-world understanding that fully leverage the capabilities of VLMs.

We present StochasticBarrier.jl, an open-source Julia-based toolbox for generating Stochastic Barrier Functions (SBFs) for safety verification of discrete-time stochastic systems with additive Gaussian noise. StochasticBarrier.jl certifies linear, polynomial, and piecewise affine (PWA) systems. The latter enables verification for a wide range of system dynamics, including general nonlinear types. The toolbox implements a Sum-of-Squares (SOS) optimization approach, as well as methods based on piecewise constant (PWC) functions. For SOS-based SBFs, StochasticBarrier.jl leverages semi-definite programming solvers, while for PWC SBFs, it offers three engines: two using linear programming (LP) and one based on gradient descent (GD). Benchmarking StochasticBarrier.jl against the state-of-the-art shows that the tool outperforms existing tools in computation time, safety probability bounds, and scalability across over 30 case studies. Compared to its closest competitor, StochasticBarrier.jl is up to four orders of magnitude faster, achieves significant safety probability improvements, and supports higher-dimensional systems.

Nowadays, waveforms of integrated sensing and communication (ISAC) are almost based on conventional communication and sensing signal, which bounds both the communication and sensing performance. To deal with this issue, in this paper, a novel waveform design is presented for the partial-time superimposed (PTS) ISAC system. At the base station (BS), a parameter-adjustable linear frequency modulation (LFM) pulse signal and a continuous communication orthogonal frequency division multiplexing (OFDM) signal are employed to broadcast public information and perform sensing tasks, respectively, using a PTS scheme. Pulse compression gain enhances the system's long-range sensing capability, while OFDM ensures the system's high-speed data transmission capability. Meanwhile, the LFM signal is utilized as superimposed pilot for channel estimation, which has higher time-frequency resource utilization and stronger real-time performance compared to orthogonal pilots. We present an accurate parameter estimation method of multi-path sensing signal for reconstructing and interference cancellation in communication users. Additionally, a cyclic maximum likelihood method is introduced for channel estimation and the Cramer-Rao lower bound (CRLB) of channel estimation is derived. Simulations demonstrate the accuracy and robustness of the proposed parameter estimation algorithm as well as the improved channel estimation performance over traditional methods. The proposed waveform design method can achieve reliable data transmission and accurate target sensing.

Inverse problems in imaging are ill-posed, leading to infinitely many solutions consistent with the measurements due to the non-trivial null-space of the sensing matrix. Common image priors promote solutions on the general image manifold, such as sparsity, smoothness, or score function. However, as these priors do not constrain the null-space component, they can bias the reconstruction. Thus, we aim to incorporate meaningful null-space information in the reconstruction framework. Inspired by smooth image representation on graphs, we propose Graph-Smooth Null-Space Representation (GSNR), a mechanism that imposes structure only into the invisible component. Particularly, given a graph Laplacian, we construct a null-restricted Laplacian that encodes similarity between neighboring pixels in the null-space signal, and we design a low-dimensional projection matrix from the $p$-smoothest spectral graph modes (lowest graph frequencies). This approach has strong theoretical and practical implications: i) improved convergence via a null-only graph regularizer, ii) better coverage, how much null-space variance is captured by $p$ modes, and iii) high predictability, how well these modes can be inferred from the measurements. GSNR is incorporated into well-known inverse problem solvers, e.g., PnP, DIP, and diffusion solvers, in four scenarios: image deblurring, compressed sensing, demosaicing, and image super-resolution, providing consistent improvement of up to 4.3 dB over baseline formulations and up to 1 dB compared with end-to-end learned models in terms of PSNR.

In this paper, we explore a cooperative integrated sensing and communication (ISAC) framework that utilizes orthogonal frequency division multiplexing (OFDM) waveforms. Under the control of a central processing unit (CPU), multiple access points (APs) collaboratively perform multistatic sensing while providing communication service in a cell-free multiple-input multiple-output (MIMO) system. Achieving high sensing accuracy requires the collection of global sensing information at the CPU, which can lead to significant fronthaul signaling overhead due to the feedback of the sensing signals from each AP. To tackle this issue, we propose a collaborative processing scheme in which the APs locally compress and quantize the received sensing signals before forwarding them to the CPU. The CPU then aggregates the information from all APs to estimate the location and velocity of the targets. We develop a distributed vector-quantized variational autoencoder (D-VQVAE) to enable an end-to-end implementation of this scheme. D-VQVAE consists of distributed encoders at the APs to locally encode the received sensing signals, codebooks for quantizing the encoded results, and a decoder at the CPU for location and velocity estimation. It effectively reduces the amount of data transmitted from each AP to the CPU while maintaining a high sensing accuracy. We employ a collaborative learning-assisted scheme to train D-VQVAE in an end-to-end manner. Simulation results show that the proposed D-VQVAE network outperforms the baseline schemes in sensing accuracy and reduces fronthaul signaling overhead by 99% when compared with the centralized sensing approach.

Scientific discovery increasingly depends on finding meaningful patterns within volumes of sensor data too large for manual inspection. Existing time-frequency event extractors are often engineered or trained on manually labeled examples for each instrument, which can be laborious and difficult to adapt to new environments. To address this, we introduce TokEye, a reference-free method that learns a general criterion for coherent structure from heterogeneous fusion measurements. A model developed under this method, without retraining, can extract signals from various other fields including marine bioacoustics and wideband radar. It recovers 82.5% of expert-annotated stellarator signals, detects 78% of dolphin whistles, and identifies radar events with 81.5% average precision across six benchmarks, while processing full experimental spectrograms in under one second on a GPU. This transfer across unrelated sensors and physical systems reveals common exploitable structure in time-frequency measurements and establishes a scalable foundation for automated scientific signal discovery.

Magnetic resonance spectroscopy (MRS) is used to quantify metabolites in vivo and estimate biomarkers for conditions ranging from neurological disorders to cancers. Quantifying low-concentration metabolites such as GABA ($\gamma$-aminobutyric acid) is challenging due to low signal-to-noise ratio (SNR) and spectral overlap. We investigate and validate deep learning for quantifying complex, low-SNR, overlapping signals from MEGA-PRESS spectra, devise a convolutional neural network (CNN) and a Y-shaped autoencoder (YAE), and select the best models via Bayesian optimisation on 10,000 simulated spectra from slice-profile-aware MEGA-PRESS simulations. The selected models are trained on 100,000 simulated spectra. We validate their performance on 144 spectra from 112 experimental phantoms containing five metabolites of interest (GABA, Glu, Gln, NAA, Cr) with known ground truth concentrations across solution and gel series acquired at 3 T under varied bandwidths and implementations. These models are further assessed against the widely used LCModel quantification tool. On simulations, both models achieve near-perfect agreement (small MAEs; regression slopes $\approx 1.00$, $R^2 \approx 1.00$). On experimental phantom data, errors initially increased substantially. However, modelling variable linewidths in the training data significantly reduced this gap. The best augmented deep learning models achieved a mean MAE for GABA over all phantom spectra of 0.151 (YAE) and 0.160 (FCNN) in max-normalised relative concentrations, outperforming the conventional baseline LCModel (0.220). A sim-to-real gap remains, but physics-informed data augmentation substantially reduced it. Phantom ground truth is needed to judge whether a method will perform reliably on real data.

Objectives: To externally validate targeted T2 fluid-attenuated inversion recovery (T2-FLAIR) dropout for robust automated glioblastoma segmentation and whole-tumor volumetry without T2-FLAIR, while preserving performance when the full MRI protocol is available. Methods: In this retrospective multi-dataset study, 3D nnU-Net models were developed on BraTS 2021 (n=848) and externally validated on an independent University of Pennsylvania glioblastoma cohort (n=403). Models were trained with or without targeted T2-FLAIR dropout, zeroing the T2-FLAIR channel during training. Testing used prespecified T2-FLAIR-present and T2-FLAIR-absent scenarios; the absent scenario was simulated by zeroing the T2-FLAIR channel at inference. The primary endpoint was per-patient overall region-wise Dice similarity coefficient (DSC). Secondary endpoints were region-specific DSC, 95th percentile Hausdorff distance, and Bland-Altman whole-tumor volume bias. Results: In external validation, performance was preserved with the full MRI protocol: overall median DSC was 94.8% (interquartile range [IQR] 90.0%-97.1%) with dropout and 95.0% (IQR 90.3%-97.1%) without dropout. In the T2-FLAIR-absent scenario, targeted dropout improved overall median DSC from 81.0% (IQR 75.1%-86.4%) to 93.4% (IQR 89.1%-96.2%). Whole-tumor DSC improved from 60.4% to 92.6%, whole-tumor 95th percentile Hausdorff distance from 17.24 mm to 2.45 mm, and whole-tumor volume bias from -45.6 mL to 0.83 mL. Conclusions: In an independent external test cohort, targeted T2-FLAIR dropout preserved glioblastoma segmentation performance with the full MRI protocol and substantially reduced whole-tumor segmentation error and volumetric bias when T2-FLAIR was absent. These findings support targeted sequence dropout as a practical robustness strategy for automated glioblastoma analysis in retrospective and heterogeneous clinical workflows.

We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on heterogeneous optical devices through a structured tool abstraction layer. We implement 64 standardized MCP tools across 8 representative optical devices and construct a 410-task benchmark to evaluate request understanding, role-aware responses, multi-step coordination, robustness to linguistic variation, and error handling. We assess two deployment configurations–commercial online LLMs and locally hosted open-source LLMs–and compare them with LLM-based code generation baselines. AgentOptics achieves 87.7%–99.0% average task success rates, significantly outperforming code-generation approaches, which reach up to 50% success. We further demonstrate broader applicability through five case studies extending beyond device-level control to system orchestration, monitoring, and closed-loop optimization. These include DWDM link provisioning and coordinated monitoring of coherent 400 GbE and analog radio-over-fiber (ARoF) channels; autonomous characterization and bias optimization of a wideband ARoF link carrying 5G fronthaul traffic; multi-span channel provisioning with launch power optimization; closed-loop fiber polarization stabilization; and distributed acoustic sensing (DAS)-based fiber monitoring with LLM-assisted event detection. These results establish AgentOptics as a scalable, robust paradigm for autonomous control and orchestration of heterogeneous optical systems.

In this paper, we show how informativity and identifiability for networks of dynamical systems can be investigated using Gröbner bases. We provide a sufficient condition for generic informativity in terms of positive definiteness of the spectrum of external signals and full generic row rank of the transfer function relating the external signals to the inputs of the predictor. Moreover, we show how generic local network identifiability in the algebraic sense can be investigated by computing the dimension of the generic fiber associated with the closed loop transfer function from external measurable signals to the measured outputs.

Underwater Acoustic (UWA) networks are vital for remote sensing and ocean exploration but face inherent challenges such as limited bandwidth, long propagation delays, and highly dynamic channels. These constraints hinder real-time communication and degrade overall system performance. To address these challenges, this paper proposes a bilevel Multi-Armed Bandit (MAB) framework. At the fast inner level, a Contextual Delayed MAB (CD-MAB) jointly optimizes adaptive modulation and transmission power based on both channel state feedback and its Age of Information (AoI), thereby maximizing throughput. At the slower outer level, a Feedback Scheduling MAB dynamically adjusts the channel-state feedback interval according to throughput dynamics: stable throughput allows longer update intervals, while throughput drops trigger more frequent updates. This adaptive mechanism reduces feedback overhead and enhances responsiveness to varying network conditions. The proposed bilevel framework is computationally efficient and well-suited to resource-constrained UWA networks. Simulation results using the DESERT Underwater Network Simulator demonstrate throughput gains of up to 20.61% and energy savings of up to 36.60% compared with Deep Reinforcement Learning (DRL) baselines reported in the existing literature.

The dependence on expert annotation has long constituted the primary rate-limiting step in the application of artificial intelligence to biomedicine. While supervised learning drove the initial wave of clinical algorithms, a paradigm shift towards unsupervised and self-supervised learning (SSL) is currently unlocking the latent potential of biobank-scale datasets. By learning directly from the intrinsic structure of data - whether pixels in a magnetic resonance image (MRI), voxels in a volumetric scan, or tokens in a genomic sequence - these methods facilitate the discovery of novel phenotypes, the linkage of morphology to genetics, and the detection of anomalies without human bias. This article synthesises seminal and recent advances in "learning without labels," highlighting how unsupervised frameworks can derive heritable cardiac traits, predict spatial gene expression in histology, and detect pathologies with performance that rivals or exceeds supervised counterparts.

The Control Barrier Function (CBF) method has been widely adopted in solving safety-critical control problems. However, the existence of a CBF is only a sufficient condition for system safety. The recently proposed Taylor-Lagrange Control (TLC) method addresses this limitation by providing a necessary and sufficient condition, but it is still vulnerable to the feasibility preservation problem (e.g., due to the inter-sampling effect when time is discretized). In this paper, we propose a robust TLC (rTLC) method to address the feasibility preservation problem and show how to use it to solve optimal control problems. Specifically, the rTLC method expands the safety function to an order higher than its relative degree using Taylor's expansion with Lagrange remainder, which allows the control to explicitly show up at the current time instead of a future time in the original TLC method. This implies that the safety constraint remains satisfied over the entire discretization time interval that follows. Moreover, the rTLC method naturally addresses the feasibility preservation problem with only a single hyper-parameter (the discretization time interval size during implementation), compared to significantly more parameters for its counterparts. Finally, we illustrate the effectiveness of the proposed rTLC method through an adaptive cruise control problem, and compare it with existing safety-critical control methods.

Integrated sensing and communication (ISAC) enables efficient sharing of wireless resources to support emerging applications, but it also introduces new sensing-based security vulnerabilities. Here, potential communication security threats include confidential messages intended for legitimate users being intercepted, and unauthorized receivers (Eves) passively exploiting target echoes to infer sensing parameters without users being aware. Despite these risks, the joint protection of sensing and communication security in ISAC systems remains unexplored. To address this challenge, this paper proposes a dual-secure ISAC framework that simultaneously protects sensing and communication against passive sensing Eves and communication Eves, without requiring their channel state information (CSI). Specifically, transmit beamformers are jointly designed to inject artificial noise (AN) to introduce interference to communication Eves, while deliberately distorting the reference signal available to sensing Eves to impair their sensing capability. Furthermore, the proposed design generates artificial ghosts (AGs) with fake angle-delay-Doppler profiles. The legitimate sensing receiver can suppress these AGs using its prior knowledge of the true target directions, whereas sensing Eves cannot, thereby significantly reducing their probability of correctly detecting the true targets. Numerical results demonstrate that the proposed framework effectively enhances both communication and sensing security, while preserving the performance of communication users and legitimate sensing receivers.

Ray tracing is a versatile approach for precise sub-terahertz (sub-THz, 100-300 GHz) channel modeling when designing new mechanisms for beyond-6G cellular systems. Theoretically, wireless channels may exhibit variations over wavelength distances. In the sub-THz band, close-to-millimeter wavelengths thus require extremely large computational efforts for ray-tracing modeling. However, in practice, channel characteristics may remain quantitatively similar over much larger distances, which can drastically decrease computational efforts. The aim of this study is to experimentally characterize the degree of spatial consistency in sub-THz channel characteristics. To this end, we performed a large-scale measurement campaign in the 140-150 GHz frequency band in an indoor-hall (InH) environment and characterized the channel at separation distances from 2.5 mm up to 1 m. Our results show that channel characteristics including delay spread, angular delay spread, and K-factor change only slightly over multiple tens of centimeter distances. This implies that, in the considered InH environment, the mesh grid can be in the range of 10-50 wavelengths (at 145 GHz) along stable line-of-sight (LoS) directions, while a finer resolution is needed in regions not dominated by LoS. For coarser grids, advanced interpolation is required to capture rapidly varying scattered components.

Classical orthogonal wavelets guarantee perfect reconstruction but rely on fixed bases optimized for polynomial smoothness, achieving suboptimal compression on signals with fractal spectral signatures. Conversely, learned methods offer adaptivity but typically enforce orthogonality via soft penalties, sacrificing structural guarantees. This work establishes a rigorous equivalence between Multiscale Entanglement Renormalization Ansatz (MERA) tensor networks and paraunitary filter banks. The resulting framework learns adaptive wavelets while enforcing exact orthogonality through manifold-constrained optimization, guaranteeing perfect reconstruction and energy conservation throughout training. Validation on Long-Range Dependent (LRD) network traffic demonstrates that learned filters outperform classical wavelets by 0.5–3.8~dB PSNR on six MAWI backbone traces (2020–2025, 314~Mbps–1.75~Gbps) while preserving the Hurst exponent within estimation uncertainty ($|\Delta H| \le 0.03$). These results establish MERA-inspired wavelets as a principled approach for telemetry compression in 6G digital twin synchronization.

Softwarized radio access networks (RANs), such as those based on the Open RAN (O-RAN) architecture, generate rich streams of key performance indicators (KPIs) that can be leveraged to extract actionable intelligence for network optimization. However, bridging the gap between low-level KPI measurements and high-level requirements, such as quality of experience (QoE), requires methods that are both relevant, capturing temporal patterns predictive of user-level outcomes, and interpretable, providing human-readable insights that operators can validate and act upon. This paper introduces conformal signal temporal logic learning (C-STLL), a framework that addresses both requirements. C-STLL leverages signal temporal logic (STL), a formal language for specifying temporal properties of time series, to learn interpretable formulas that distinguish KPI traces satisfying high-level requirements from those that do not. To ensure reliability, C-STLL wraps around existing STL learning algorithms with a conformal calibration procedure based on the Learn Then Test (LTT) framework. This procedure produces a set of STL formulas with formal guarantees: with high probability, the set contains at least one formula achieving a user-specified accuracy level. The calibration jointly optimizes for reliability, formula complexity, and diversity through principled acceptance and stopping rules validated via multiple hypothesis testing. Experiments using the ns-3 network simulator on a mobile gaming scenario demonstrate that C-STLL effectively controls risk below target levels while returning compact, diverse sets of interpretable temporal specifications that relate KPI behavior to QoE outcomes.

This work addresses the edge-based synchronization problem in first-order multi-agent systems containing both cooperative and antagonistic interactions with one or multiple leader groups. The presence of multiple leaders and antagonistic interactions means that the multi-agent system typically does not achieve consensus, unless specific conditions (on the number of leaders and on the signed graph) are met, in which case the agents reach a trivial form of consensus. In general, we show that the multi-agent system exhibits a more general form of synchronization, including bipartite consensus and containment. Our approach proposes a signed edge-based agreement protocol for signed networks described by signed edge-Laplacian matrices. In particular, in this work, we present new spectral properties of signed edge-Laplacian matrices containing multiple zero eigenvalues and establish global exponential stability of the synchronization errors. Moreover, we explicitly compute the equilibrium to which all edge states converge, thereby characterizing the resulting synchronization behavior. Numerical simulations validate our theoretical results.

Causal discovery problems use a set of observations to deduce causality between variables in the real world, typically to answer questions about biological or physical systems. These observations are often recorded at regular time intervals, determined by a user or a machine, depending on the experiment design. There is generally no guarantee that the timing of these recordings matches the timing of the underlying biological or physical events. In this paper, we examine the sensitivity of causal discovery methods to this potential mismatch. We consider empirical and theoretical evidence to understand how causal discovery performance is impacted by changes of sampling rate and window length. We demonstrate that both classical and recent causal discovery methods exhibit sensitivity to these hyperparameters, and we discuss how ideas from signal processing may help us understand these phenomena.

While deep learning has demonstrated considerable promise in computer-aided diagnosis for pulmonary embolism (PE), practical deployment in Computed Tomography Pulmonary Angiography (CTPA) is often hindered by "domain shift" and the prohibitive cost of expert annotations. To address these challenges, an unsupervised domain adaptation (UDA) framework is proposed, utilizing a Transformer backbone and a Mean-Teacher architecture for cross-center semantic segmentation. The primary focus is placed on enhancing pseudo-label reliability by learning deep structural information within the feature space. Specifically, three modules are integrated and designed for this task: (1) a Prototype Alignment (PA) mechanism to reduce category-level distribution discrepancies; (2) Global and Local Contrastive Learning (GLCL) to capture both pixel-level topological relationships and global semantic representations; and (3) an Attention-based Auxiliary Local Prediction (AALP) module designed to reinforce sensitivity to small PE lesions by automatically extracting high-information slices from Transformer attention maps. Experimental validation conducted on cross-center datasets (FUMPE and CAD-PE) demonstrates significant performance gains. In the FUMPE -> CAD-PE task, the IoU increased from 0.1152 to 0.4153, while the CAD-PE -> FUMPE task saw an improvement from 0.1705 to 0.4302. Furthermore, the proposed method achieved a 69.9% Dice score in the CT -> MRI cross-modality task on the MMWHS dataset without utilizing any target-domain labels for model selection, confirming its robustness and generalizability for diverse clinical environments.

In orthogonal frequency-division multiplexing-based radar and integrated sensing and communication systems, the sensing range is traditionally limited by the round-trip time corresponding to the cyclic prefix duration. Targets whose echoes arrive after this duration induce intersymbol interference (ISI) and associated intercarrier interference (ICI), which significantly degrade detection performance, elevate the interference-noise floor in the radar image, and reduce the useful signal power due to window mismatch. Existing methods face a trade-off between recovering useful signal and suppressing interference, particularly in multi-target scenarios. This paper proposes two frameworks to resolve this dilemma, offering a flexible trade-off between computational cost and target detection performance. First, a signal model is derived, demonstrating that ISI and ICI-oriented interference often dominates thermal noise in high-dynamic-range scenarios. To combat the ISI and ICI-based interference-noise floor increase, joint-interference cancellation with coherent compensation is proposed. This approach is an efficient evolution of the successive-interference cancellation algorithm, utilizing high-precision chirp Z-transform estimation and frequency-domain coherent compensation to recover weak distant targets. For scenarios requiring maximum precision, the full reconstruction-based sliding window scheme is presented, which shifts the receive window to capture optimal signal energy while performing full-signal reconstruction for all detected targets. Numerical results show that both methods outperform state-of-the-art benchmarks.

This work presents a stochastic tube-based model predictive control framework that guarantees hard input constraint satisfaction for linear systems subject to unbounded additive disturbances. The approach relies on a structured design of probabilistic reachable sets that explicitly incorporates actuator saturation into the error dynamics and bounds the resulting nonlinearity within a convex embedding. The proposed controller retains the computational efficiency and structural advantages of stochastic tube-based approaches while ensuring state chance constraint satisfaction alongside hard input limits. Recursive feasibility and mean-square stability are established for our scheme, and a numerical example illustrates its effectiveness.

In-Motion physical coupling of multiple mobile ground robots has the potential to enable new applications like in-motion transfer that improves efficiency in handling and transferring goods, which tackles current challenges in logistics. A key challenge lies in achieving reliable autonomous in-motion physical coupling of two mobile ground robots starting at any initial position. Existing approaches neglect the modeling of the docking interface and the strategy for approaching it, resulting in uncontrolled collisions that make in-motion physical coupling either impossible or inefficient. To address this challenge, we propose a central mpc approach that explicitly models the dynamics and states of two omnidirectional wheeled robots, incorporates constraints related to their docking interface, and implements an approaching strategy for rendezvous and docking. This novel approach enables omnidirectional wheeled robots with a docking interface to physically couple in motion regardless of their initial position. In addition, it makes in-motion transfer possible, which is 19.75% more time- and 21.04% energy-efficient compared to a non-coupling approach in a logistic scenario.

Music source restoration (MSR) aims to recover unprocessed stems from mixed and mastered recordings. The challenge lies in both separating overlapping sources and reconstructing signals degraded by production effects such as compression and reverberation. We therefore propose DTT-BSR, a hybrid generative adversarial network (GAN) combining rotary positional embeddings (RoPE) transformer for long-term temporal modeling with dual-path band-split recurrent neural network (RNN) for multi-resolution spectral processing. Our model achieved 3rd place on the objective leaderboard and 4th place on the subjective leaderboard on the ICASSP 2026 MSR Challenge, demonstrating exceptional generation fidelity and semantic alignment with a compact size of 7.1M parameters.

The Low-Altitude Economy (LAE) is rapidly emerging as a new technological and industrial frontier, with unmanned aerial vehicles (UAVs), electric vertical takeoff and landing (eVTOL) aircraft, and aerial swarms increasingly deployed in logistics, infrastructure inspection, security, and emergency response. However, the large-scale development of the LAE demands a reliable aerial foundation that ensures not only real-time connectivity and computational support, but also navigation integrity and safe airspace management for safety-critical operations. High-Altitude Platforms (HAPs), positioned at around 20 km, provide a unique balance between wide-area coverage and low-latency responsiveness. Compared with low earth orbit (LEO) satellites, HAPs are closer to end users and thus capable of delivering millisecond-level connectivity, fine-grained regulatory oversight, and powerful onboard computing and caching resources. Beyond connectivity and computation, HAPs-assisted sensing and regulation further enable navigation integrity and airspace trust, which are essential for safety-critical UAV and eVTOL operations in the LAE. This article proposes a five-stage evolutionary roadmap for HAPs in the LAE: from serving as aerial infrastructure bases, to becoming super back-ends for UAV, to acting as frontline support for ground users, further enabling swarm-scale UAV coordination, and ultimately advancing toward edge-air-cloud closed-loop autonomy. In parallel, HAPs complement LEO satellites and cloud infrastructures to form a global-regional-local three-tier architecture. Looking forward, HAPs are expected to evolve from simple platforms into intelligent hubs, emerging as pivotal nodes for air traffic management, intelligent logistics, and emergency response. By doing so, they will accelerate the transition of the LAE toward large-scale deployment, autonomy, and sustainable growth.

Autonomous drone-based tree pruning needs accurate, real-time depth estimation from stereo cameras. Depth is computed from disparity maps using $Z = f B/d$, so even small disparity errors cause noticeable depth mistakes at working distances. Building on our earlier work that identified DEFOM-Stereo as the best reference disparity generator for vegetation scenes, we present the first study to train and test ten deep stereo matching networks on real tree branch images. We use the Canterbury Tree Branches dataset – 5,313 stereo pairs from a ZED Mini camera at 1080P and 720P – with DEFOM-generated disparity maps as training targets. The ten methods cover step-by-step refinement, 3D convolution, edge-aware attention, and lightweight designs. Using perceptual metrics (SSIM, LPIPS, ViTScore) and structural metrics (SIFT/ORB feature matching), we find that BANet-3D produces the best overall quality (SSIM = 0.883, LPIPS = 0.157), while RAFT-Stereo scores highest on scene-level understanding (ViTScore = 0.799). Testing on an NVIDIA Jetson Orin Super (16 GB, independently powered) mounted on our drone shows that AnyNet reaches 6.99 FPS at 1080P – the only near-real-time option – while BANet-2D gives the best quality-speed balance at 1.21 FPS. We also compare 720P and 1080P processing times to guide resolution choices for forestry drone systems.

Efficient and accurate load flow calculations are a bedrock of modern power system operation. Classical numerical methods such as the Newton-Raphson algorithm provide highly precise results but are computationally demanding, which limits their applicability in large-scale scenario studies and optimization in time-critical contexts. Research has shown that machine learning approaches can approximate load flow results with high accuracy while substantially reducing computation time. Sample efficiency, i.e., the ability to achieve high accuracy with limited training dataset size, is still insufficiently researched, especially in grids with a fixed topology. This paper presents a systematic investigation of the sample efficiency of a Multilayer Perceptron and two Graph Neural Network variants on a dataset based on a modified IEEE 5-bus system. The results for this grid size show that Graph Neural Networks achieve the lowest losses. However, the availability of large training datasets remains the dominant factor influencing performance compared to architecture choice.

Living organisms rely on endogenous feedback mechanisms to maintain homeostasis in the presence of uncertainty and environmental fluctuations. An emerging challenge at the interface of control systems engineering and synthetic biology is the design of reliable feedback strategies to regulate cellular behavior and collective biological functions. In this article, we review recent advances in multicellular feedback control, where sensing, computation, and actuation are distributed across different cell populations within synthetic microbial consortia, giving rise to biological multiagent control systems governed by molecular communication. From a control-theoretic perspective, these consortia can be interpreted as distributed biomolecular control systems, where coordination among populations replace embedded regulation. We survey theoretical frameworks, control architectures, and modeling approaches, ranging from aggregate population-level dynamics to spatially aware agent-based simulations, and discuss experimental demonstrations in engineered Escherichia coli consortia. We highlight how distributing control functions across populations can reduce metabolic burden, mitigate retroactivity, improve robustness to uncertainty, and enable modular reuse of control components. Beyond regulation of gene expression, we discuss the emerging problem of population composition control, where coordination among growing and competing cell populations becomes an integral part of the control objective. Finally, we outline key open challenges that must be addressed before multicellular control strategies can be deployed in real-world applications such as biomanufacturing, environmental remediation, and therapeutic systems. These challenges span modeling and simulation, experimental platform development, coordination and composition control, and long-term evolutionary stability.

The deployment of in-air acoustic sensors for industrial monitoring and autonomous robotics has grown significantly, often drawing inspiration from biological echolocation. However, developing and validating these systems in existing simulation frameworks remains challenging due to the computational cost of simulating high-frequency wave propagation in large, dynamic, and complex environments. While wave-based methods offer high accuracy, they scale poorly with frequency and volume. Conversely, existing geometric acoustic solvers often lack support for dynamic scenes, complex diffraction, or closed-loop robotic integration. In this work, we introduce SonoTraceUE, a high-fidelity acoustic simulation framework built as a plugin for Unreal Engine. By using a hardware-accelerated ray tracing-based specular reflection model, and a curvature-based Monte Carlo diffraction model, the system enables near real-time simulation of active and passive acoustic sensing in dynamic, multi-material environments. We validate the framework through two distinct experimental domains: a bioacoustic study and a robotics experiment. Our results demonstrate that SonoTraceUE achieves high correlation with real-world spectral and spatial data. The framework provides a versatile platform for synthetic data generation, hypothesis testing in bioacoustics, and the rapid prototyping of closed-loop robotic systems that use acoustic sensing.

Our goal in this paper is to apply the topological signal processing (TSP) framework to the analysis of 3D Point Clouds (PCs) represented on simplicial complexes. Building on Discrete Exterior Calculus (DEC) theory for vector fields, we introduce higher-order Laplacian operators that enable the processing of signals over triangular meshes. Unlike traditional approaches, the proposed approach allows us to characterize both color attributes, modeled as 3D vectors on nodes, and geometry, modeled as 3D vectors on the barycenter of each triangle. Then, we show as TSP tools may efficiently be used to sample, recover and filter PCs attributes treating them as edge signals. Numerical results on synthetic PCs demonstrate accurate color reconstruction with robustness to sparse data and geometry refinement in the case of noisy PC coordinates. The proposed approach provides a topology-based representation to characterize the geometry and attributes of PCs.