Papers

Peer-to-peer (P2P) energy management facilitates decentralized resource allocation among prosumers, improving local hosting capacity for renewables and minimizing energy expenditures while ensuring data privacy through distributed coordination. However, conventional P2P energy management methods are confined to synchronous scheduling paradigms, creating synchronization bottlenecks that fundamentally conflict with the dynamic and decentralized nature of P2P energy management tasks. To bridge this gap, this paper focuses on resolving a class of dynamic energy management problems over asynchronous P2P (Asyn-P2P) transactive networks. We first recast the dynamic energy management problems into a saddle-point problem, and then propose a synchronous decentralized dynamic energy management algorithm, dubbed Syn-DYNA,based on operator splitting theory. To eliminate the global synchronization clock in Syn-DYNA, we introduce a random activation scheme, together with local buffers for latest state tracking, to develop an asynchronous variant of Syn-DYNA, namely Asyn-DYNA. Based on monotone operator theory, theoretical analysis proves a non-asymptotic linear convergence rate for Syn-DYNA and establishes the almost sure convergence ofAsyn-DYNA. Numerical experiments validate effectiveness of Syn-DYNA and Asyn-DYNA algorithms by tackling a dynamic energy management task over P2P transactive networks.

Deep learning has enabled highly realistic synthetic speech, raising concerns about fraud, impersonation, and disinformation. Despite rapid progress in neural detectors, transparent baselines are needed to reveal which acoustic cues reliably separate real from synthetic speech. This paper presents an interpretable classical machine learning baseline for deepfake audio detection using the Fake-or-Real (FoR) dataset. We extract prosodic, voice-quality, and spectral features from two-second clips at 44.1 kHz (high-fidelity) and 16 kHz (telephone-quality) sampling rates. Statistical analysis (ANOVA, correlation heatmaps) identifies features that differ significantly between real and fake speech. We then train multiple classifiers – Logistic Regression, LDA, QDA, Gaussian Naive Bayes, SVMs, and GMMs – and evaluate performance using accuracy, ROC-AUC, EER, and DET curves. Pairwise McNemar's tests confirm statistically significant differences between models. The best model, an RBF SVM, achieves ~93% test accuracy and ~7% EER on both sampling rates, while linear models reach ~75% accuracy. Feature analysis reveals that pitch variability and spectral richness (spectral centroid, bandwidth) are key discriminative cues. These results provide a strong, interpretable baseline for future deepfake audio detectors.

Cross-facility knowledge transfer in Controlled Environment Agriculture (CEA) can reduce HVAC energy consumption by 30-38% and accelerate new facility commissioning from months to days. However, facility operators refuse to share raw operational data because it encodes commercially sensitive grow recipes. We present HierFedCEA, a hierarchical federated learning framework that enables privacy-preserving climate control optimization across heterogeneous CEA facilities. HierFedCEA decomposes the neural network PID auto-tuning model into three tiers aligned with the physical structure of the control problem: (1) a global physics tier capturing universal thermodynamic relationships; (2) a crop-cluster tier encoding cultivar-specific VPD-to-gain mappings; and (3) a local personalization tier adapting to facility-specific equipment dynamics. The framework applies tier-specific differential privacy budgets and leverages the extreme compactness of the 36-parameter PID model to achieve privacy essentially for free (excess risk < 0.15%). Simulation experiments calibrated from 7+ years of production deployment across 30+ commercial facilities in 8 U.S. climate zones demonstrate that HierFedCEA achieves 94% of centralized training performance while reducing total communication cost to under 1 MB. To the best of our knowledge, this is the first federated learning framework designed for CEA climate control.

This paper addresses the problem of fixed-time cooperative output regulation for linear multi-agent systems over directed graphs under denial-of-service attacks. A novel distributed resilient fixed-time controller is developed that comprises a distributed resilient fixed-time observer taking general directed graphs into consideration, and a distributed resilient fixed-time control law for each agent. The proposed controller neither depends on Laplacian symmetry nor requires strong connectivity and detail-balanced condition, in contrast to existing distributed resilient fixed-time controllers. Under the proposed controller, the regulated outputs converge to zero in a fixed time with its upper bound independent of the initial states of the multi-agent system. Ultimately, the efficacy of the proposed controller is demonstrated via a simulation example.

We study the asymptotic optimality of abstraction-based control synthesis algorithms. Specifically, we consider uncertain MDP (UMDP) abstraction, and investigate whether refinement leads to optimal results, i.e., an optimal controller and zero error bound. Additionally, we study completeness of abstraction-refinement algorithms, i.e., that the algorithm produces near-optimal results in finite time. The focus is on nonlinear stochastic systems with general vector fields and temporal logic specifications. We present an algorithm that abstracts the system into a UMDP and synthesizes a controller with performance guarantees via robust dynamic programming. Then, the algorithm iteratively refines the abstraction until a near-optimality criterion is met. A thorough theoretical analysis reveals a sufficient condition, which we denote vanishing ambiguity, guaranteeing asymptotic optimality of the abstraction process and completeness of the algorithm. We show that set-valued MDP abstractions satisfy this criterion, whereas interval MDP abstractions lack such a guarantee.

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate system identification as an in-context meta-learning problem and compare deterministic and generative sequence models for forward dynamics prediction. We take a Transformer-based meta-model, as a strong deterministic baseline, and introduce to this setting two complementary diffusion-based approaches: (i) inpainting diffusion (Diffuser), which learns the joint input-observation distribution, and (ii) conditioned diffusion models (CNN and Transformer), which generate future observations conditioned on control inputs. Through large-scale randomized simulations, we analyze performance across in-distribution and out-of-distribution regimes, as well as computational trade-offs relevant for control. We show that diffusion models significantly improve robustness under distribution shift, with inpainting diffusion achieving the best performance in our experiments. Finally, we demonstrate that warm-started sampling enables diffusion models to operate within real-time constraints, making them viable for control applications. These results highlight generative meta-models as a promising direction for robust system identification in robotics.

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is critical for applications such as captioning, media search, and multimodal synchronization, yet it is often handled by external alignment tools. In this work, we extend an existing speech-aware language model to predict timestamps directly alongside transcripts. We introduce a set of novel lightweight training strategies that improve alignment robustness while preserving recognition quality. Experiments across multiple datasets show that these strategies not only enhance timestamp accuracy, but also yield gains in overall ASR performance. Together, they demonstrate an efficient and unified approach to speech recognition with precise timestamp prediction.

AI-enhanced interference rejection in radio frequency (RF) transmissions has recently attracted interest because deep learning approaches trained on both the signal of interest (SOI) and the signal mixture (SOI plus interference) can outperform traditional approaches which only consider the SOI. The goal is to detect, demodulate, and decode signals over a range of signal-to-interference-plus-noise (SINR) levels without having a detailed, design-level knowledge of the interfering signal or the propagation conditions. Our present AI interference suppression results are based on Autoregressive Transformer Decoder models which exhibit orders of magnitude faster throughput at inference time than WaveNet models developed in earlier work. As a specific example, we investigate an analog FM "Walkie Talkie" radio signal of interest in the presence of an Orthogonal Frequency-Division Multiplexing (OFDM) interferer. This type of interferer is near-ubiquitous in the current RF landscape. Our results clearly show the benefits of transformer-based interference mitigation in tactical settings. We show that unintelligible transmissions become intelligible via metrics such as Perceptual Evaluation of Speech Quality (PESQ), while overall latency is kept to a minimum using readily available lightweight GPUs such as a Jetson AGX Orin. We believe these same techniques can also be applied to a broader set of national security scenarios, as well as having commercial applications.

Classical vehicle dynamics contains several widely adopted misconceptions that, while intuitively appealing, may lead to inconsistencies when examined under a rigorous mechanical framework. This paper revisits a number of such misconceptions, clarifying their domains of validity and highlighting potential sources of misunderstanding. The aim is not to dismiss established models, but to promote a more precise and scientifically grounded interpretation of key concepts.

Accurate inference from quartz crystal microbalance (QCM) measurements in liquids is often limited by reducing resonance behavior to two scalar endpoints (frequency and dissipation shifts, $\Delta f$ and $\Delta D$) or by relying on single-equation analytical models (Kanazawa-model). We propose an AI-ready, impedance-resolved workflow that preserves full resonance line-shape information and converts it into compact, physically interpretable features for supervised regression. A passive microfluidic mixer generates glycerol–water concentration gradients under a constant total flow rate (50~$\mu$L/min), while complex impedance spectra of a 10~MHz AT-cut quartz crystal are recorded in real time. Each sweep of nine spectra is parameterized via constrained Gaussian/Lorentzian models to yield 52 line-shape descriptors spanning extrema of $|Z|$, $X$, and $B$ and peaks of $R$, phase, and $G$. The pipeline integrates consensus outlier handling, redundancy-aware feature ranking (mRMR), and cross-validated regression across linear, kernel, and ensemble models. Compared with the classical Kanazawa baseline, the impedance line-shape approach reduces concentration-prediction error from 0.456 to 0.148~%v/v RMSE (3.09$\times$ lower). The results demonstrate that impedance-resolved line-shape features provide a robust and interpretable basis for machine-learning-assisted QCM inference and illustrate a generalizable pattern for AI-enabled spectral sensing.

Accurate pipe roughness estimation in large-scale water distribution networks is often hindered by the high cost of traditional field methods. This study investigates whether network partitioning, by utilizing hydraulic and graph-derived attributes, can enhance the calibration of these parameters. Using a high-fidelity model of a real network as a benchmark, we evaluate density-based clustering, and topology-driven grouping strategies. Optimization experiments demonstrate that attribute-based grouping yields stable, repeatable results comparable to manual calibration for hydraulically significant pipes. While hydraulic attributes generate more distinct cluster structures, the inclusion of graph-based data improves calibration robustness by stabilizing the optimization process. Notably, density-based clustering achieves similar accuracy to k-means while reducing computational effort in specific configurations. Although the method does not eliminate all sources of uncertainty, results suggest that topology-informed grouping provides a systematic, reproducible, and computationally efficient alternative to manual heuristics, highlighting the critical role of network structure in reliable parameter estimation.

Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most efficient attention methods use one approximation everywhere, yet video features are spectrally structured: low frequencies carry global layout and coarse motion; high frequencies carry texture and fine detail. We present FreqFormer, a frequency-aware heterogeneous attention framework. Token features are split into spectral bands with different operators: dense global attention on compressed low-frequency content, structured block-sparse attention on mid frequencies, and sliding-window local attention on high frequencies. A lightweight spectral routing network allocates heads across bands using layer statistics and the diffusion timestep, shifting compute toward global structure early in denoising and detail later. Cross-band summary tokens provide cheap residual exchange. FreqFormer is paired with a fused GPU execution plan that co-schedules dense, sparse, and local branches to cut kernel launches and memory traffic. We give a consistent complexity model, an orthonormal-decomposition view of approximation, and simulation-based systems numbers (throughput, arithmetic intensity, memory traffic, duration scaling). In simulations from 64K to 1M tokens, FreqFormer substantially reduces estimated attention FLOPs and KV-related memory traffic versus dense attention while keeping a hardware-friendly pattern, supporting spectrally structured heterogeneous attention as a practical direction for long-video diffusion transformers.

Optimal transport with quadratic cost provides a geometric framework for steering an ensemble, modeled by a probability law, with minimal effort. Yet ambient-space formulations become unwieldy in high dimensions, and sensing or actuation in practice often reveals only linear views of the state – camera silhouettes, LiDAR beams, tomographic slices. We develop a sliced feedback controller for distribution steering: the evolving law is projected onto one-dimensional directions on the sphere, the optimal one-dimensional velocity is synthesized in each projection, and these velocities are averaged to produce a feedback control in the ambient space. The construction reduces to the Benamou–Brenier problem in one dimension. In addition, it is invariant under orthogonal transforms, nonexpansive under projections, and well posed on $\mathcal{P}_2(\mathbb{R}^n)$. Computation proceeds by sampling directions on the sphere and solving independent one-dimensional subproblems, yielding a scalable method aligned with partial observations. In the Gaussian setting, we show that the developed sliced controller steers the law to the prescribed target. Furthermore, we derive an identity relating the energy consumption incurred by the controller to the sliced Wasserstein distance.

Augmented reality (AR) systems pose unique privacy risks due to their continuous capture of visual data. Existing AR privacy frameworks lack semantic understanding of visual content, limiting their effectiveness in detecting context-dependent privacy risks. We propose PrivAR, which leverages vision language models (VLMs) with chain-of-thought prompting for contextual privacy risk detection in AR environments. PrivAR uses visual scene cues to infer potential sensitive information types, such as identifying password notes in office environments through contextual reasoning. PrivAR detects and obfuscates textual content, preventing exposure of sensitive information while preserving contextual cues necessary for VLM inference. Additionally, we investigate contextually-informed warning interfaces to enhance user privacy awareness. Experiments on a real-world AR dataset show that PrivAR achieves superior accuracy (81.48%) and F1-score (84.62%) compared to baselines, while reducing privacy leakage rate to 17.58%. User studies evaluating contextually-informed warning interfaces provide insights into effective privacy-aware AR design.

Synthetic Aperture Radar (SAR) data is inherently complex-valued, while quantum machine learning (QML) models operate in complex Hilbert spaces. This similarity suggests that using both the magnitude and phase of SAR data in quantum encoding should help automatic target recognition in SAR images. In this study, we test this assumption by comparing five encoding strategies for quantum models: magnitude-only encoding, joint magnitude-phase encoding, in-phase and quadrature encoding, preprocessed phase encoding, and a purely quantum architecture. All approaches are evaluated under a unified experimental setup on the MSTAR benchmark dataset. Surprisingly, we find that magnitude-only encoding performs better than phase-inclusive encodings in hybrid quantum-classical models. It achieves 99.57 percent accuracy on the 3-class task and 71.19 percent accuracy on the 8-class task, outperforming complex-valued alternatives under the same framework. Adding phase information provides little or no improvement and can sometimes degrade performance. However, in purely quantum models with only 184 to 224 trainable parameters and no classical neural-network layers, phase information becomes much more important, improving accuracy by up to 21.65 percentage points. These findings show that the usefulness of phase information depends not only on the data, but also on the architecture used to process it. Hybrid models can compensate for missing phase information through their classical components, while pure quantum models rely more strongly on phase information for class discrimination. The results provide practical guidance for encoding complex-valued data in quantum machine learning and highlight the importance of jointly designing encoding strategies and model architectures for current quantum systems.

Biosignals exhibit substantial cross-subject and cross-session variability, inducing severe domain shifts that degrade post-deployment performance for small, edge-oriented AI models. On-device adaptation is therefore essential to both preserve user privacy and ensure system reliability. However, existing sub-100 mW MCU-based wearable platforms can only support shallow or sparse adaptation schemes due to the prohibitive memory footprint and computational cost of full backpropagation (BP). In this paper, we propose BioTrain, a framework enabling full-network fine-tuning of state-of-the-art biosignal models under milliwatt-scale power and sub-megabyte memory constraints. We validate BioTrain using both offline and on-device benchmarks on EEG and EOG datasets, covering Day-1 new-subject calibration and longitudinal adaptation to signal drift. Experimental results show that full-network fine-tuning achieves accuracy improvements of up to 35% over non-adapted baselines and outperforms last-layer updates by approximately 7% during new-subject calibration. On the GAP9 MCU platform, BioTrain enables efficient on-device training throughput of 17 samples/s for EEG and 85 samples/s for EOG models within a power envelope below 50 mW. In addition, BioTrain's efficient memory allocator and network topology optimization enable the use of a large batch size, reducing peak memory usage. For fully on-chip BP on GAP9, BioTrain reduces the memory footprint by 8.1x, from 5.4 MB to 0.67 MB, compared to conventional full-network fine-tuning using batch normalization with batch size 8.

Balancing the societal costs of non-pharmaceutical interventions with epidemic suppression requires adaptive feedback control. Rather than relying on state-dependent operational caps, we formulate an infinite-horizon optimal control problem for a networked SIQR model that strictly enforces suppression via a hard spectral constraint on the transmission dynamics. We derive a safety-critical Model Predictive Control (MPC) approximation that embeds this spectral certificate stage-wise, yielding a tunable exponential decay rate. Furthermore, we construct a terminal set ensuring recursive feasibility and a feasible continuation that decays globally, proving positive invariance directly via the physical depletion of susceptibles rather than standard quadratic Lyapunov functions. To handle prediction uncertainty, we develop a robust counterpart that replaces nominal constraints by upper-envelope versions, recovering recursive feasibility and finite-horizon realized decay. We conclude by validating our approaches using simulation studies that leverage public data from counties in the state of Massachusetts.

The increasing penetration of distributed energy resources (DERs) is transforming distribution networks into actively managed systems, introducing challenges related to voltage regulation, thermal loading limits, and operational security. This paper presents the development and implementation of a real-time Digital Twin (DT) for security assessment and coordinated flexibility activation in active distribution networks, demonstrated on the Bornholm Island system using real measurement data. The implemented DT integrates network topology and smart meter measurements to perform security assessment under normal operation and N-1 contingencies, and to determine corrective and preventive flexibility actions using an optimization-based approach. Results show that load variation and contingency scenarios introduce operational limit violations, primarily driven by voltage magnitude constraints. The implemented flexibility strategy effectively mitigates these violations through coordinated active and reactive power control, enhancing system security and operational efficiency. The findings highlight the potential of DT-based approaches for reliable and flexible operation of future distribution networks.

Safety filters provide a practical approach for enforcing safety constraints in autonomous systems. While learning-based tools scale to high-dimensional systems, their performance depends on informative data that includes states likely to lead to constraint violation, which can be difficult to efficiently sample in complex, high-dimensional systems. In this work, we characterize trajectories that barely avoid safety violations using the Pontryagin Maximum Principle. These boundary trajectories are used to guide data collection for learned Hamilton-Jacobi Reachability, concentrating learning efforts near safety-critical states to improve efficiency. The learned Control Barrier Value Function is then used directly for safety filtering. Simulations and experimental validation on a shared-control automotive racing application demonstrate PMP sampling improves learning efficiency, yielding faster convergence, reduced failure rates, and improved safe set reconstruction, with wall times around 3ms.

This paper extends path integral control (PIC) to partially observed systems by formulating the problem in Gaussian belief space. PIC uses the matching condition, which requires the diffusion and control channels to be proportional, to linearize the Hamilton–Jacobi–Bellman equation through the Cole–Hopf transform. We show that the belief diffusion satisfies this condition only when the observation function is affine. Thus, the standard Cole–Hopf linearization does not apply to non-affine observation models. Restricting the problem to Gaussian beliefs provides a finite-dimensional approximation with deterministic covariance evolution and reduces the problem to stochastic control of the belief mean. We derive necessary and sufficient conditions for matching in this reduced space, obtain an exact Cole–Hopf linearization and a Feynman–Kac representation, and develop the MPPI-Belief algorithm. Numerical experiments on a navigation task with state-dependent observation noise demonstrate the effectiveness of MPPI-Belief compared with certainty-equivalent and particle-filter-based methods.

The United States designates Food and Agriculture as one of sixteen critical infrastructure sectors, yet no mandatory cybersecurity requirements exist for agricultural operations and no formal threat model has been published for Controlled Environment Agriculture (CEA) systems. This paper presents the first comprehensive threat model for IoT-enabled CEA, applying STRIDE analysis, MITRE ATT&CK for ICS mapping, and IEC 62443 zone-and-conduit decomposition to a production platform deployed across 30+ commercial facilities in 8 U.S. climate zones. We enumerate 123 unique threats across 25 data-flow-diagram elements spanning 15 communication protocols, 10 of which operate with zero authentication or encryption by design. We identify five novel attack classes unique to AI-driven CEA: stealth destabilization of neural-network-tuned PID controllers, baseline drift poisoning of anomaly detectors, cross-facility propagation via federated transfer learning, adversarial agronomic schedules that exploit crop biology rather than computational models, and reward poisoning of reinforcement-learning energy optimizers. Physical impact analysis quantifies crop loss timelines from minutes (aeroponics) to days, including worker safety hazards from CO2 injection manipulation. A survey of 10 commercial CEA vendors reveals only one CVE ever issued, zero bug bounty programs, and zero IEC 62443 certifications. We propose a defense-in-depth countermeasure framework and recommend Security Level 2 as a minimum baseline.

This paper investigates the problem of data-driven modeling of port-Hamiltonian systems while preserving their intrinsic Hamiltonian structure and stability properties. We propose a novel neural-network-based port-Hamiltonian modeling technique that relaxes the convexity constraint commonly imposed by neural network-based Hamiltonian approximations, thereby improving the expressiveness and generalization capability of the model. By removing this restriction, the proposed approach enables the use of more general non-convex Hamiltonian representations to enhance modeling flexibility and accuracy. Furthermore, the proposed method incorporates information about stable equilibria into the learning process, allowing the learned model to preserve the stability of multiple isolated equilibria rather than being restricted to a single equilibrium as in conventional methods. Two numerical experiments are conducted to validate the effectiveness of the proposed approach and demonstrate its ability to achieve more accurate structure- and stability-preserving learning of port-Hamiltonian systems compared with a baseline method.

Aerial object detection in UAV imagery presents unique challenges due to the high prevalence of tiny objects, adverse environmental conditions, and strict computational constraints. Standard YOLO-based detectors fail to address these jointly: their minimum detection stride of 8 pixels renders sub-32px objects nearly undetectable, their CIoU loss produces zero gradients for non-overlapping tiny boxes, and their architectures contain significant filter redundancy. We propose DroneScan-YOLO, a holistic system contribution that addresses these limitations through four coordinated design choices: (1) increased input resolution of 1280x1280 to maximize spatial detail for tiny objects, (2) RPA-Block, a dynamic filter pruning mechanism based on lazy cosine-similarity updates with a 10-epoch warm-up period, (3) MSFD, a lightweight P2 detection branch at stride 4 adding only 114,592 parameters (+1.1%), and (4) SAL-NWD, a hybrid loss combining Normalized Wasserstein Distance with size-adaptive CIoU weighting, integrated into YOLOv8's TaskAligned assignment pipeline. Evaluated on VisDrone2019-DET, DroneScan-YOLO achieves 55.3% mAP@50 and 35.6% mAP@50-95, outperforming the YOLOv8s baseline by +16.6 and +12.3 points respectively, improving recall from 0.374 to 0.518, and maintaining 96.7 FPS inference speed with only +4.1% parameters. Gains are most pronounced on tiny object classes: bicycle AP@50 improves from 0.114 to 0.328 (+187%), and awning-tricycle from 0.156 to 0.237 (+52%).

This paper studies a stochastic algorithm for linearly constrained nonconvex optimization, where the objective function is smooth but only unbiased stochastic gradients with bounded variance are available. We propose a momentum-based augmented Lagrangian method that employs a Polyak-type gradient estimator and requires only one stochastic gradient evaluation per iteration. Under the standard stochastic oracle model and the smoothness condition of the expected objective, we establish a convergence guarantee in terms of the first-order KKT residual of the original constrained problem. In particular, the proposed method computes an $\epsilon$-stationary solution in expectation within $O(\epsilon^{-4})$ stochastic gradient evaluations. Numerical experiments further show that the proposed method achieves competitive iteration complexity and improved wall-clock efficiency compared with representative recursive-momentum baselines.

We study sequential decision-making in time-varying Markov decision processes (TVMDPs) under limited update rates, where the decision-maker observes the system and updates its model only intermittently. Such settings arise in applications with sensing, communication, or computational constraints that preclude continuous adaptation. Our goal is to understand how the performance of an agent, which learns and plans using receding-horizon control under these information constraints, degrades as a function of the update rate. We propose a skip-update learning and planning framework that combines likelihood-based estimation of time-varying transition kernels with finite-horizon planning and executes policies between updates using stale information. We analyze its performance via dynamic regret relative to an oracle policy with full knowledge of the dynamics and continuous observations. Our main result establishes a dynamic regret bound that explicitly quantifies the impact of intermittent updates, decomposing regret into contributions from update times and skip intervals and revealing its dependence on temporal variation, estimation uncertainty, and the duration of intervals without updates. In particular, the dominant contribution from skip intervals admits a linear dependence on the interval length and the rate of temporal variation, while its effect is mitigated by mixing-induced contraction.

Safe navigation for multi-robot systems requires enforcing safety without sacrificing task efficiency under decentralized decision-making. Existing decentralized methods often assume robot homogeneity, making shared safety requirements non-uniformly interpreted across heterogeneous agents with structurally different dynamics, which could lead to avoidance obligations not physically realizable for some robots and thus cause safety violations or deadlock. In this paper, we propose Capability-Aware Heterogeneous Control Barrier Function (CA-HCBF), a decentralized framework for consistent safety enforcement and capability-aware coordination in heterogeneous robot teams. We derive a canonical second-order control-affine representation that unifies holonomic and nonholonomic robots under acceleration-level control via canonical transformation and backstepping, preserving forward invariance of the safe set while avoiding relative-degree mismatch across heterogeneous dynamics. We further introduce a support-function-based directional capability metric that quantifies each robot's ability to follow its motion intent, deriving a pairwise responsibility allocation that distributes the safety burden proportionally to each robot's motion capability. A feasibility-aware clipping mechanism further constrains the allocation to each agent's physically achievable range, mitigating infeasible constraint assignments common in dense decentralized CBF settings. Simulations with up to 30 heterogeneous robots and a physical multi-robot demonstration show improved safety and task efficiency over baselines, validating real-world applicability across robots with distinct kinematic constraints.

Semiconductor failure analysis (FA) requires engineers to examine inspection images, correlate equipment telemetry, consult historical defect records, and write structured reports, a process that can consume several hours of expert time per case. We present SemiFA, an agentic multi-modal framework that autonomously generates structured FA reports from semiconductor inspection images in under one minute. SemiFA decomposes FA into a four-agent LangGraph pipeline: a DefectDescriber that classifies and narrates defect morphology using DINOv2 and LLaVA-1.6, a RootCauseAnalyzer that fuses SECS/GEM equipment telemetry with historically similar defects retrieved from a Qdrant vector database, a SeverityClassifier that assigns severity and estimates yield impact, and a RecipeAdvisor that proposes corrective process adjustments. A fifth node assembles a PDF report. We introduce SemiFA-930, a dataset of 930 annotated semiconductor defect images paired with structured FA narratives across nine defect classes, drawn from procedural synthesis, WM-811K, and MixedWM38. Our DINOv2-based classifier achieves 92.1% accuracy on 140 validation images (macro F1 = 0.917), and the full pipeline produces complete FA reports in 48 seconds on an NVIDIA A100-SXM4-40 GB GPU. A GPT-4o judge ablation across four modality conditions demonstrates that multi-modal fusion improves root cause reasoning by +0.86 composite points (1-5 scale) over an image-only baseline, with equipment telemetry as the more load-bearing modality. To our knowledge, SemiFA is the first system to integrate SECS/GEM equipment telemetry into a vision-language model pipeline for autonomous FA report generation.

Speech deepfake detection (SDD) systems perform well on standard benchmarks datasets but often fail to generalize to expressive and emotional spoofing attacks. Many methods rely on spoof-heavy training data, learning dataset-specific artifacts rather than transferable cues of natural speech. In contrast, humans internalize variability in real speech and detect fakes as deviations from it. We introduce ProSDD, a two-stage framework that enriches model embeddings through supervised masked prediction of speaker-conditioned prosodic variation based on pitch, voice activity, and energy. Stage I learns prosodic variability from real speech, and Stage II jointly optimizes this objective with spoof classification. ProSDD consistently outperforms baselines under both ASVspoof 2019 and 2024 training, reducing ASVspoof 2024 EER from 25.43% to 16.14% (2019-trained) and from 39.62% to 7.38% (2024-trained), while achieving 50% relative reductions on EmoFake and EmoSpoof-TTS.

This work explores methods to identify energy system designs for infeasible control co-design optimization problems. Control co-design, or CCD, has been recognized as a powerful tool to maximize energy system capabilities through simultaneous determination of plant and controller parameters. However, due to the inherent nonlinearities, complexity, and conflicting criteria of energy systems, CCD optimization problems are susceptible to infeasibility and can lack potential solutions. While transforming the optimization problem by relaxing constraints has been developed for optimal control infeasibility challenges, solution feasibility for CCD is relatively unexplored. This paper proposes a framework to convert infeasible optimization problems into solvable forms for a class of CCD problems. The framework introduces a procedure to rank metric bounds from least likely to most likely to cause infeasibility. This provides guidance to algorithmically relax a limited number of constraints, leaving others intact. The proposed framework is applied to a CCD problem for designing a battery within a microgrid. Comparison against a baseline approach for relaxing optimization problems shows the framework requires only a reduced number of iterations to determine a solution.

Robust control barrier functions (CBFs) provide a principled mechanism for smooth safety enforcement under worst-case disturbances. However, existing approaches typically rely on explicit, closed-form structure in the dynamics (e.g., control-affine) and uncertainty models. This has led to limited scalability and generality, with most robust CBFs certifying only conservative subsets of the maximal robust safe set. In this paper, we introduce a new robust CBF framework for general nonlinear systems under bounded uncertainty. We first show that the safety value function solving the dynamic programming Isaacs equation is a valid robust discrete-time CBF that enforces safety on the maximal robust safe set. We then adopt the key reinforcement learning (RL) notion of quality function (or Q-function), which removes the need for explicit dynamics by lifting the barrier certificate into state-action space and yields a novel robust Q-CBF constraint for safety filtering. Combined with adversarial RL, this enables the synthesis and deployment of robust Q-CBFs on general nonlinear systems with black-box dynamics and unknown uncertainty structure. We validate the framework on a canonical inverted pendulum benchmark and a 36-D quadruped simulator, achieving substantially less conservative safe sets than barrier-based baselines on the pendulum and reliable safety enforcement even under adversarial uncertainty realizations on the quadruped.