Papers

Engineering system design – whether mechatronic, control, or embedded – often proceeds in an ad hoc manner, with requirements left implicit and traceability from intent to parameters largely absent. Existing specification-driven and systematic design methods mostly target software, and AI-assisted tools tend to enter the workflow at solution generation rather than at problem framing. Human–AI collaboration in the design of physical systems remains underexplored. This paper presents Design-OS, a lightweight, specification-driven workflow for engineering system design organized in five stages: concept definition, literature survey, conceptual design, requirements definition, and design definition. Specifications serve as the shared contract between human designers and AI agents; each stage produces structured artifacts that maintain traceability and support agent-augmented execution. We position Design-OS relative to requirements-driven design, systematic design frameworks, and AI-assisted design pipelines, and demonstrate it on a control systems design case using two rotary inverted pendulum platforms – an open-source SimpleFOC reaction wheel and a commercial Quanser Furuta pendulum – showing how the same specification-driven workflow accommodates fundamentally different implementations. A blank template and the full design-case artifacts are shared in a public repository to support reproducibility and reuse. The workflow makes the design process visible and auditable, and extends specification-driven orchestration of AI from software to physical engineering system design.

Deadline misses are more common in real-world systems than one may expect. The weakly-hard task model has become a standard abstraction to describe and analyze how often these misses occur, and has been especially used in control applications. Most existing control approaches check whether a controller manages to stabilize the system it controls when its implementation occasionally misses deadlines. However, they usually do not incorporate deadline-overrun knowledge during the controller synthesis process. In this paper, we present a framework that explicitly integrates weakly-hard constraints into the control design. Our method supports various overrun handling strategies and guarantees stability and performance under weakly-hard constraints. We validate the synthesized controllers on a Furuta pendulum, a representative control benchmark. The results show that constraint-aware controllers significantly outperform traditional designs, demonstrating the benefits of proactive and informed synthesis for overrun-aware real-time control.

With the advancement of IoT technologies and the rapid expansion of cyber-physical systems, there is increasing interest in distributed state estimation, where multiple sensors collaboratively monitor large-scale dynamic systems. Compared with its continuous-time counterpart, a discrete-time distributed observer faces greater challenges, as it cannot exploit high-gain mechanisms or instantaneous communication. Existing approaches depend on three tightly coupled factors: (i) system observability, (ii) communication frequency and dimension of the exchanged information, and (iii) network connectivity. However, the interdependence among these factors remains underexplored. This paper identifies a fundamental trilemma among these factors and introduces a general design framework that balances them through an iterative semidefinite programming approach. As such, the proposed method mitigates the restrictive assumptions present in existing works. The effectiveness and generality of the proposed approach are demonstrated through a simulation example.

Getting a real cybersecurity risk assessment for a small organization is expensive – a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip it entirely. We built a six-agent AI system where each agent handles one analytical stage: profiling the organization, mapping assets, analyzing threats, evaluating controls, scoring risks, and generating recommendations. Agents share a persistent context that grows as the assessment proceeds, so later agents build on what earlier ones concluded – the mechanism that distinguishes this from standard sequential agent pipelines. We tested it on a 15-person HIPAA-covered healthcare company and compared outputs to independent assessments by three CISSP practitioners – the system agreed with them 85% of the time on severity classifications, covered 92% of identified risks, and finished in under 15 minutes. We then ran 30 repeated single-agent assessments across five synthetic but sector-realistic organizational profiles in healthcare, fintech, manufacturing, retail, and SaaS, comparing a general-purpose Mistral-7B against a domain fine-tuned model. Both completed every run. The fine-tuned model flagged threats the baseline could not see at all: PHI exposure in healthcare, OT/IIoT vulnerabilities in manufacturing, platform-specific risks in retail. The full multi-agent pipeline, however, failed every one of 30 attempts on a Tesla T4 with its 4,096-token default context window – context capacity, not model quality, turned out to be the binding constraint.

Mosquito-borne diseases affect more than one billion people each year and cause close to one million deaths. Traditional surveillance methods rely on traps and manual identification that are slow, labor-intensive, and difficult to scale. Audio-based mosquito monitoring offers a non-destructive, lower-cost, and more scalable complement to trap-based surveillance, but reliable species classification remains difficult under real-world recording conditions. Mosquito flight tones are narrow-band, often low in signal-to-noise ratio, and easily masked by background noise, and recordings for several epidemiologically relevant species remain limited, creating pronounced class imbalance. Variation across devices, environments, and collection protocols further increases the difficulty of robust classification. Such variation can cause models to rely on domain-specific recording artefacts rather than species-relevant acoustic cues, which makes transfer to new acquisition settings difficult. The BioDCASE 2026 Cross-Domain Mosquito Species Classification (CD-MSC) challenge is designed around this deployment problem by evaluating performance on both seen and unseen domains. This paper presents the official baseline system and evaluation pipeline as a simple, fully reproducible reference for the CD-MSC challenge task. The baseline uses log-mel features and a multitemporal resolution convolutional neural network (MTRCNN) with species and auxiliary domain outputs, together with complete training and test scripts. The baseline system performs strongly on seen domains but degrades markedly on unseen domains, showing that cross-domain generalisation, rather than within-domain recognition, is the central challenge for practical mosquito species classification from multi-source bioacoustic recordings.

Three-dimensional (3D) Ultrasound (US) can facilitate diagnosis, treatment planning, and image-guided therapy. However, current studies rarely provide a comprehensive evaluation of volumetric accuracy and reproducibility, highlighting the need for robust Quality Assurance (QA) frameworks, particularly for tracked 3D US reconstruction using freehand or robotic acquisition. This study presents a QA framework for 3D US reconstruction and a flexible open source platform for tracked US research. A custom phantom containing geometric inclusions with varying symmetry properties enables straightforward evaluation of optical, electromagnetic, and robotic kinematic tracking for 3D US at different scanning speeds and insonation angles. A standardised pipeline performs real-time segmentation and 3D reconstruction of geometric targets (DSC = 0.97, FPS = 46) without GPU acceleration, followed by automated registration and comparison with ground-truth geometries. Applying this framework showed that our robotic 3D US achieves state-of-the-art reconstruction performance (DSC-3D = 0.94 +- 0.01, HD95 = 1.17 +- 0.12), approaching the spatial resolution limit imposed by the transducer. This work establishes a flexible experimental platform and a reproducible validation methodology for 3D US reconstruction. The proposed framework enables robust cross-platform comparisons and improved reporting practices, supporting the safe and effective clinical translation of 3D ultrasound in diagnostic and image-guided therapy applications.

This paper proposes a hybrid quantum optimization framework for large-scale antenna-array beamforming with jointly optimized discrete phases and continuous amplitudes. The method combines quantum-inspired search with classical gradient refinement to handle mixed discrete-continuous variables efficiently. For phase optimization, a Gray-code and odd-combination encoding scheme is introduced to improve robustness and avoid the complexity explosion of higher-order Ising models. For amplitude optimization, a geometric spin-combination encoding and a two-stage strategy are developed, using quantum-inspired optimization for coarse search and gradient optimization for fine refinement. To enhance solution diversity and quality, a rainbow quantum-inspired algorithm integrates multiple optimizers for parallel exploration, followed by hierarchical-clustering-based candidate refinement. In addition, a double outer-product method and an augmented version are proposed to construct the coupling matrix and bias vector efficiently, improving numerical precision and implementation efficiency. Under the scoring rules of the 7th National Quantum Computing Hackathon, simulations on a 32-element antenna array show that the proposed method achieves a score of 461.58 under constraints on near-main-lobe sidelobes, wide-angle sidelobes, beamwidth, and optimization time, nearly doubling the baseline score. The proposed framework provides an effective reference for beamforming optimization in future wireless communication systems.

This paper presents a comparative optimization framework for smart charging of electrified vehicle fleets. Using heuristic sequential dynamic programming (SeqDP), the framework minimizes electricity costs while adhering to constraints related to the power grid, charging infrastructure, vehicle availability, and simple considerations of battery aging. Based on real-world operational data, the model incorporates discrete energy states, time-varying tariffs, and state-of-charge (SoC) targets to deliver a scalable and cost-effective solution. Classical DP approach suffers from exponential computational complexity as the problem size increases. This becomes particularly problematic when conducting monthly-scale analyses aimed at minimizing peak power demand across all vehicles. The extended time horizon, coupled with multi-state decision-making, renders exact optimization impractical at larger scales. To address this, a heuristic method is employed to enable systematic aggregation and tractable computation for the Non-Linear Programming (NLP) problem. Rather than seeking a globally optimal solution, this study focuses on a time-efficient smart charging strategy that aims to minimize energy cost while flattening the overall power profile. In this context, a sequential heuristic DP approach is proposed. Its performance is evaluated against a full-fleet solver using Gurobi, a widely used commercial solver in both academia and industry. The proposed algorithm achieves a reduction of the overall cost and peak power by more than 90% compared to uncontrolled schedules. Its relative cost remains within 9% of the optimal values obtained from the full-fleet solver, and its relative peak-power deviation stays below 15% for larger fleets.

We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the problem as a world modeling task and leverages the Joint Embedding Predictive Architecture (JEPA) to learn action-conditioned latent dynamics from CSI trajectories. To promote geometric consistency and compositionality, we parameterize transitions using homomorphic updates derived from Lie algebra, yielding a structured latent space that reflects spatial layout and user motion. Evaluations on the DICHASUS dataset show that our approach outperforms strong baselines in preserving topology and forecasting future embeddings across unseen environments. The resulting latent space enables metrically faithful channel charts, offering a scalable foundation for downstream applications such as mobility-aware scheduling, localization, and wireless scene understanding.

In endoscopic surgery, surgeons continuously locate the endoscopic view relative to the anatomy by interpreting the evolving visual appearance of the intraoperative scene in the context of their prior knowledge. Vision-based navigation systems seek to replicate this capability by recovering camera pose directly from endoscopic video, but most approaches do not embody the same principles of reasoning about new frames that makes surgeons successful. Instead, they remain grounded in feature matching and geometric optimization over keyframes, an approach that has been shown to degrade under the challenging conditions of endoscopic imaging like low texture and rapid illumination changes. Here, we pursue an alternative approach and investigate a policy-based formulation of endoscopic camera pose recovery that seeks to imitate experts in estimating trajectories conditioned on the previous camera state. Our approach directly predicts short-horizon relative motions without maintaining an explicit geometric representation at inference time. It thus addresses, by design, some of the notorious challenges of geometry-based approaches, such as brittle correspondence matching, instability in texture-sparse regions, and limited pose coverage due to reconstruction failure. We evaluate the proposed formulation on cadaveric sinus endoscopy. Under oracle state conditioning, we compare short-horizon motion prediction quality to geometric baselines achieving lowest mean translation error and competitive rotational accuracy. We analyze robustness by grouping prediction windows according to texture richness and illumination change indicating reduced sensitivity to low-texture conditions. These findings suggest that a learned motion policy offers a viable alternative formulation for endoscopic camera pose recovery.

We develop a predictor-feedback control design for a class of linear systems with state-dependent switching. The main ingredient of our design is a novel construction of an exact predictor state. Such a construction is possible as for a given, state-dependent switching rule, an implementable formula for the predictor state can be derived in a way analogous to the case of nonlinear systems with input delay. We establish uniform exponential stability of the corresponding closed-loop system via a novel construction of multiple Lyapunov functionals, relying on a backstepping transformation that we introduce. We validate our design in simulation considering a switching rule motivated by communication networks.

This paper addresses the synthesis of an optimal fixed-gain distributed observer for discrete-time linear systems over wireless sensor networks. The proposed approach targets the steady-state estimation regime and computes fixed observer gains offline from the asymptotic error covariance of the global distributed BLUE estimator. Each node then runs a local observer that exchanges only state estimates with its neighbors, without propagating error covariances or performing online information fusion. Under collective observability and strong network connectivity, the resulting distributed observer achieves optimal asymptotic performance among fixed-gain schemes. In comparison with covariance intersection-based methods, the proposed design yields strictly lower steady state estimation error covariance while requiring minimal communication. Numerical simulations illustrate the effectiveness of the approach and its advantages in terms of accuracy and implementation simplicity.

This paper introduces a unified analytical and optimization framework for fluid antenna system-active reconfigurable intelligent surface (FAS-ARIS) communications in 6G. By combining the port reconfigurability of FAS with the signal amplification of ARIS, the proposed design enables more flexible control of the propagation environment and enhanced link reliability beyond what passive solutions can offer. We first derive the optimal ARIS amplification gain under a reflection power constraint to maximize the user's signal-to-noise ratio (SNR). Using a block-diagonal matrix approximation, we obtain a tractable outage expression and a tight independent-antenna equivalent upper-bound. Building on this, we establish the monotonic relationship between outage and effective channel gain, which enables a closed-form solution for ARIS phase optimization under limited channel state information (CSI). To further improve spectral efficiency, we propose a region-partitioned throughput optimization framework that achieves near-optimal performance without exhaustive search, thereby verifying its low computational complexity. Extensive simulations confirm the accuracy of the analysis and demonstrate consistent gains in outage and throughput compared to baselines.

This paper investigates the fundamental tradeoff between reconfigurable intelligent surfaces (RISs) and network-controlled repeaters (NCRs) in terms of achievable signal-to-noise ratio (SNR). Considering an uplink system with a multi-antenna base station (BS) and a single-antenna user equipment (UE), we derive closed-form SNR expressions for passive RIS-, active RIS-, and NCR-assisted communication under line-of-sight propagation between the BS-RIS/NCR and RIS/NCR-UE. Both narrowband and wideband transmissions are analyzed, with and without the presence of a direct BS–UE link. Our analysis reveals a key structural difference: while the SNR achieved with RISs grows unboundedly with the number of RIS elements, the SNR provided by an NCR is fundamentally limited by the UE–repeater channel due to noise amplification. Nevertheless, we show that NCRs can outperform both passive and active RISs when deployed close to the UE, provided that sufficient amplification is available. Numerical results based on realistic path loss models quantify the amplification levels required for NCRs to outperform RISs across different deployment geometries and system dimensions. These findings provide clear design guidelines for the practical integration of RISs and NCRs in future wireless networks.

Efficient multi-user multi-task video transmission is an important research topic within the realm of current wireless communication systems. To reduce the transmission burden and save communication resources, we propose a goal-oriented semantic communication framework for optical flow-based multi-user multi-task video transmission (OF-GSC). At the transmitter, we design a semantic encoder that consists of a motion extractor and a patch-level optical flow-based semantic representation extractor to effectively identify and select important semantic representations. At the receiver, we design a transformer-based semantic decoder for high-quality video reconstruction and video classification tasks. To minimize the communication time, we develop a deep deterministic policy gradient (DDPG)-based bandwidth allocation algorithm for multi-user transmission. For video reconstruction tasks, our OF-GSC framework achieves a significant improvement in the received video quality, as evidenced by a 13.47% increase in the structural similarity index measure (SSIM) score in comparison to DeepJSCC. For video classification tasks, OF-GSC achieves a Top-1 accuracy slightly surpassing the performance of VideoMAE with only 25% required data under the same mask ratio of 0.3. For bandwidth allocation optimization, our DDPG-based algorithm reduces the maximum transmission time by 25.97% compared with the baseline equal-bandwidth allocation scheme.

Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the first evaluation of TTA methods for FER under natural domain shifts, performing cross-dataset experiments with widely used FER datasets. This moves beyond synthetic corruptions to examine real-world shifts caused by differing collection protocols, annotation standards, and demographics. Results show TTA can boost FER performance under natural shifts by up to 11.34%. Entropy minimization methods such as TENT and SAR perform best when the target distribution is clean. In contrast, prototype adjustment methods like T3A excel under larger distributional distance scenarios. Finally, feature alignment methods such as SHOT deliver the largest gains when the target distribution is noisier than our source. Our cross-dataset analysis shows that TTA effectiveness is governed by the distributional distance and the severity of the natural shift across domains.

This paper analyzes the computational complexity of validated interval methods for uncertain nonlinear systems and steady-state enclosure. Interval analysis produces guaranteed enclosures that account for uncertainty and round-off, but its adoption is often limited by computational cost in high dimensions. We develop an algorithm-level worst-case framework that makes explicit the dependence on the problem dimension $n$, the initial search region size $\mathrm{Vol}(X_0)$, the target tolerance $\varepsilon$, and the costs of validated primitives (inclusion-function evaluation, Jacobian evaluation, and interval linear algebra). Within this framework, we derive worst-case time and space bounds for interval bisection, subdivision$+$filter, interval constraint propagation, interval Newton, and interval Krawczyk, and identify dominant cost drivers. We also show that the computation of the determinant and inverse of interval matrices via naive Laplace expansion exhibits factorial growth with increasing matrix dimension, motivating specialized interval linear algebra. We complement the worst-case bounds with computational results on two application-motivated biochemical steady-state models (a Hill-type regulatory network and an enzyme-saturation-based winner-take-all circuit) in dimensions $n\in\{2,5,10\}$, including instances that process millions of boxes. The resulting analysis and experiments support the practical design of validated solvers for uncertainty-aware steady-state screening tasks such as robust operating-point certification and multistability assessment.

Controlling real-world networked systems, including ecological, biomedical, and engineered networks that exhibit higher-order interactions, remains challenging due to inherent nonlinearities and large system scales. Despite extensive studies on graph controllability, the controllability properties of hypergraphs remain largely underdeveloped. Existing results focus primarily on exact controllability, which is often impractical for large-scale hypergraphs. In this article, we develop a structural controllability framework for hypergraphs by modeling hypergraph dynamics as polynomial dynamical systems. In particular, we extend classical notions of accessibility and dilation from linear graph-based systems to polynomial hypergraph dynamics and establish a hypergraph-based criterion under which the topology guarantees satisfaction of classical Lie-algebraic and Kalman-type rank conditions for almost all parameter choices. We further derive a topology-based lower bound on the minimum number of driver nodes required for structural controllability and leverage this bound to design a scalable driver node selection algorithm combining dilation-aware initialization via maximum matching with greedy accessibility expansion. We demonstrate the effectiveness and scalability of the proposed framework through numerical experiments on hypergraphs with tens to thousands of nodes and higher-order interactions.

In this paper, the potential capacity and spatial efficiency of future autonomous lane-free traffic in urban environments are explored using a combination of analytical and simulation-based approaches. For lane-free roadways, a simple analytical approach is employed, which shows not only that lane-free traffic offers a higher capacity than lane-based traffic for the same street width, but also that the relationship between capacity and street width is continuous under lane-free traffic. To test the potential capacity and properties of lane-free signal-free intersections (automated intersection management), two approaches were simulated and compared, including a novel approach which we call OptWULF. This approach uses a multi-agent conflict-based search approach with a low-level planner that uses a combination of optimization and simple window-based reservation. With these simulations, we confirm the continuous relationship between capacity and street width for intersection scenarios. We also show that OptWULF results in an even utilization of the entire drivable area of the street and intersection area. Furthermore, we show that OptWULF is capable of handling asymmetric demand patterns without any substantial loss in capacity compared to symmetric demand patterns.

This paper proposes low-overhead and low-complexity channel estimation (CE) of frequency-domain equalization aided faster-than-Nyquist (FTN) signaling. In the proposed CE scheme, the concept of pilot superimposition is employed, where the FTN block is designed to superimpose pilot symbols with information symbols, and thus, no dedicated time and frequency resources nor guard bands are required, resulting in a 50% reduction of the overhead. Furthermore, interference induced by the pilot superimposition is eliminated by invoking a novel scheme, referred to as spectral interference alignment, where a data-dependent sequence is subtracted from transmitted information symbols. The theoretical mean-square error (MSE) of the proposed CE is derived, which verifies that the MSE is no longer affected by interference due to the pilot superimposition.

Whole slide image (WSI) analysis heavily relies on multiple instance learning (MIL). While recent methods benefit from large-scale foundation models and advanced sequence modeling to capture long-range dependencies, they still struggle with two critical issues. First, directly applying frozen, task-agnostic features often leads to suboptimal separability due to the domain gap with specific histological tasks. Second, relying solely on global aggregators can cause over-smoothing, where sparse but critical diagnostic signals are overshadowed by the dominant background context. In this paper, we present ReconMIL, a novel framework designed to bridge this domain gap and balance global-local feature aggregation. Our approach introduces a Latent Space Reconstruction module that adaptively projects generic features into a compact, task-specific manifold, improving boundary delineation. To prevent information dilution, we develop a bi-stream architecture combining a Mamba-based global stream for contextual priors and a CNN-based local stream to preserve subtle morphological anomalies. A scale-adaptive selection mechanism dynamically fuses these two streams, determining when to rely on overall architecture versus local saliency. Evaluations across multiple diagnostic and survival prediction benchmarks show that ReconMIL consistently outperforms current state-of-the-art methods, effectively localizing fine-grained diagnostic regions while suppressing background noise. Visualization results confirm the models superior ability to localize diagnostic regions by effectively balancing global structure and local granularity.

For many nonlinear Bayesian state estimation problems, the posterior recursion is not analytically tractable, leading to algorithms that are influenced by numerical approximation errors. These algorithms depend on parameters that affect the approximation's accuracy and computational cost. The parameters include, for example, the number of particles, scaling parameters, and the number of iterations in iterative computations. Typically, these parameters are fixed or adjusted heuristically, although the approximation accuracy can change over time with the local degree of nonlinearity and uncertainty. The approximation errors introduced at a time step propagate through subsequent updates, affecting the accuracy, consistency, and robustness of future estimates. This paper presents adaptive parameter selection in nonlinear Bayesian filtering as a sequential decision-making problem, where parameters influence not only the immediate estimation outcome but also the future estimates. The decision-making problem is addressed using reinforcement learning to learn adaptive parameter policies for nonlinear Bayesian filters. Experiments with the unscented Kalman filter and stochastic integration filter demonstrate that the learned policies improve both estimate quality and consistency.

Phase synchronization of access points (APs) in a distributed multiple-input multiple-output (D-MIMO) system is critical to leverage the performance benefits of D-MIMO. Existing over-the-air phase synchronization methods assume that APs can communicate directly to perform necessary measurements. However, this assumption might not hold in scenarios where inter-AP signaling is too weak for effective communication. To address this, in this paper, we propose a novel over-the-air calibration scheme that uses repeater nodes to facilitate phase synchronization when direct AP signaling is infeasible. We give the steps of the algorithm for phase calibration in closed form, and show how it enables coherent joint transmission (CJT) by the APs. The framework expands the applicability of D-MIMO systems to challenging environments, where existing over-the-air synchronization techniques fall short.

This paper shows that the concept of complex frequency, originally introduced to characterize the dynamics of signals with complex values, constitutes a generalization of eigenvalues when applied to the states of linear time-invariant (LTI) systems. Starting from the definition of geometric frequency, which provides a geometrical interpretation of frequency in electric circuits that admits a natural decomposition into symmetric and antisymmetric components associated with amplitude variation and rotational motion, respectively, we show that complex frequency arises as its restriction to the two-dimensional Euclidean plane. For LTI systems, it is shown that the complex frequencies computed from the system's states subject to a non-isometric transformation, coincide with the original system's eigenvalues. This equivalence is demonstrated for diagonalizable systems of any order. The paper provides a unified geometric interpretation of eigenvalues, bridging classical linear system theory with differential geometry of curves. The paper also highlights that this equivalence does not generally hold for nonlinear systems. On the other hand, the geometric frequency of the system can always be defined, providing a geometrical interpretation of the system flow. A variety of examples based on linear and nonlinear circuits illustrate the proposed framework.

Electroencephalography (EEG) - based air-writing recognition offers a human-computer interaction paradigm by decoding neural activity associated with handwriting movements. Despite its potential, reliable EEG-based air-writing recognition remains challenging due to low signal-to-noise ratio and pronounced inter-subject variability. In this study, we examine the use of supervised contrastive learning to improve representation learning for EEG-based air-writing recognition. The analysis is conducted on preprocessed EEG signals and independent component analysis (ICA)-derived neural components obtained from five participants, with trials segmented from -1 to 2 s relative to movement on-set. EEGNet and DeepConvNet architectures are evaluated under both conventional cross-entropy training and a supervised contrastive learning framework using a subject-dependent five-fold cross-validation scheme. The results indicate that supervised contrastive learning consistently improves classification accuracy across architectures and feature representations. For preprocessed EEG signals, the mean accuracy increases from 33.45% to 43.77% and from 29.14% to 38.06% with EEGNet and DeepConvNet, respectively. Using ICA components, higher mean accuracies of 49.21% and 43.32% are achieved with EEGNet and DeepConvNet, respectively. These results suggest that the supervised contrastive learning framework offers an efficient extension to existing EEG-based air-writing recognition approaches.

Human communication seamlessly integrates speech and bodily motion, where hand gestures naturally complement vocal prosody to express intent, emotion, and emphasis. While recent text-to-speech (TTS) systems have begun incorporating multimodal cues such as facial expressions or lip movements, the role of hand gestures in shaping prosody remains largely underexplored. We propose a novel multimodal TTS framework, Gesture2Speech, that leverages visual gesture cues to modulate prosody in synthesized speech. Motivated by the observation that confident and expressive speakers coordinate gestures with vocal prosody, we introduce a multimodal Mixture-of-Experts (MoE) architecture that dynamically fuses linguistic content and gesture features within a dedicated style extraction module. The fused representation conditions an LLM-based speech decoder, enabling prosodic modulation that is temporally aligned with hand movements. We further design a gesture-speech alignment loss that explicitly models their temporal correspondence to ensure fine-grained synchrony between gestures and prosodic contours. Evaluations on the PATS dataset show that Gesture2Speech outperforms state-of-the-art baselines in both speech naturalness and gesture-speech synchrony. To the best of our knowledge, this is the first work to utilize hand gesture cues for prosody control in neural speech synthesis. Demo samples are available at https://research.sri-media-analysis.com/aaai26-beeu-gesture2speech/

Indoor positioning faces ongoing challenges due to complex propagation conditions, such as multipath propagation, signal blockages, and intrinsic target characteristics that substantially impact measurement reliability and positioning accuracy. Existing methods, in particular Least Squares (LS), frequently struggle to maintain robustness when confronted with unreliable observations caused by multipath interactions and extended targets. In this work, we propose an outlier-resistant algorithm designed to mitigate the impact of outlier measurements and accurately estimate the position of an extended target in multipath-rich environments. We develop a two-step algorithm in which an initial coarse position estimate is obtained using the angle-of-arrival (AoA) and subsequently refined using the Cauchy loss function to suppress outliers. The numerical results confirm that the proposed algorithm improves robustness and accuracy, outperforming existing benchmark methods, such as Iterative Reweighted Least Squares (IRLS), LS, and Huber loss function, and achieving a positioning error of less than $70$ cm in $90\%$ of cases. Its effectiveness in mitigating multipath effects is further assessed by comparing tracking performance in cluttered and empty room scenarios.

Stochastic control barrier functions (SCBFs) provide a safety-critical control framework for systems subject to stochastic disturbances by bounding the probability of remaining within a safe set. However, finding a valid SCBF that explicitly reflects the long-horizon behavior of the true safety probability remains a challenge. This paper addresses this issue by adopting a spectral perspective, utilizing the linear operator that governs the evolution of the closed-loop system's safety probability. We find that the dominant eigenpair of this Koopman-like operator encodes fundamental safety information of the stochastic system. The dominant eigenfunction is a natural and valid SCBF, with values that characterize relative asymptotic safety across initial states, while the dominant eigenvalue indicates the global asymptotic rate at which the safety probability decays. A practical algorithm for computation is proposed, termed power-policy iteration, which jointly estimates the dominant eigenpair while updating the backup policy with the aim of improving long-term safety. The method is validated using simulation experiments on safety-critical dynamics models.

The increasing use of marine spaces by offshore infrastructure, including oil and gas platforms, underscores the need for consistent, scalable monitoring. Offshore development has economic, environmental, and regulatory implications, yet maritime areas remain difficult to monitor systematically due to their inaccessibility and spatial extent. This study presents an automated approach to the spatiotemporal detection of offshore oil and gas platforms based on freely available Earth observation data. Leveraging Sentinel-1 archive data and deep learning-based object detection, a consistent quarterly time series of platform locations for three major production regions: the North Sea, the Gulf of Mexico, and the Persian Gulf, was created for the period 2017-2025. In addition, platform size, water depth, distance to the coast, national affiliation, and installation and decommissioning dates were derived. 3,728 offshore platforms were identified in 2025, 356 in the North Sea, 1,641 in the Gulf of Mexico, and 1,731 in the Persian Gulf. While expansion was observed in the Persian Gulf until 2024, the Gulf of Mexico and the North Sea saw a decline in platform numbers from 2018-2020. At the same time, a pronounced dynamic was apparent. More than 2,700 platforms were installed or relocated to new sites, while a comparable number were decommissioned or relocated. Furthermore, the increasing number of platforms with short lifespans points to a structural change in the offshore sector associated with the growing importance of mobile offshore units such as jack-ups or drillships. The results highlighted the potential of freely available Earth observation data and deep learning for consistent, long-term monitoring of marine infrastructure. The derived dataset is public and provides a basis for offshore monitoring, maritime planning, and analyses of the transformation of the offshore energy sector.

Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global context or paralinguistic cues, making it hard to capture real-world phenomena such as multi-speaker interactions (interruptions, overlapping speech), evolving emotional arcs, and varied acoustic environments. We introduce the Borderless Long Speech Synthesis framework for agent-centric, borderless long audio synthesis. Rather than targeting a single narrow task, the system is designed as a unified capability set spanning VoiceDesigner, multi-speaker synthesis, Instruct TTS, and long-form text synthesis. On the data side, we propose a "Labeling over filtering/cleaning" strategy and design a top-down, multi-level annotation schema we call Global-Sentence-Token. On the model side, we adopt a backbone with a continuous tokenizer and add Chain-of-Thought (CoT) reasoning together with Dimension Dropout, both of which markedly improve instruction following under complex conditions. We further show that the system is Native Agentic by design: the hierarchical annotation doubles as a Structured Semantic Interface between the LLM Agent and the synthesis engine, creating a layered control protocol stack that spans from scene semantics down to phonetic detail. Text thereby becomes an information-complete, wide-band control channel, enabling a front-end LLM to convert inputs of any modality into structured generation commands, extending the paradigm from Text2Speech to borderless long speech synthesis.