Papers

Euler's Gradus Suavitatis (1739) assigns a dissonance value to a musical interval p/q by the formula G(p/q) = 1 + \Omega^(p) + \Omega^(q), where \Omega^(n) = \sum_i e_i(p_i - 1) sums the weighted prime exponents of n. We propose the simpler asymmetric formula f(p/q) = p + \Omega^(q), which treats numerator and denominator differently and performs comparably on standard consonance data. We also show that, under a model in which harmonics are integer-indexed and counted uniformly up to a fixed truncation level, Gradus is equivalent to a weighted harmonic coincidence count with weights w(n) = \Omega^(n), connecting it to Galileo's earlier pulse-coincidence model (1638). The formula naturally generates a coprime integer triangle T(n,k) = n + \Omega^(k), whose rightmost diagonal gives the two-stage dissonance of the superparticular (consecutive-harmonic) intervals. The formula f admits a simple two-stage interpretation in terms of harmonic context and partial recognition, which we offer as a speculative perceptual hypothesis.

In this paper, we introduce SP$^3$, a novel Plug-and-Play algorithm that accelerates maximum a posteriori image restoration by replacing denoisers with Spherical Encoders (SE) as generative priors. SP$^3$ approximates the intractable proximal prior step by utilizing the SE tightly structured latent space as a robust projection onto the natural image manifold. Alternating this projection with a closed-form data-consistency step, via Half-Quadratic Splitting, achieves stable convergence without requiring gradient computation during inference. This unique formulation unlocks "anytime" restoration capabilities, producing sharp, plausible images from the first iteration. Evaluations across a variety of image restoration tasks demonstrate that SP$^3$ achieves perceptual quality comparable to state-of-the-art zero-shot diffusion and flow methods while being $3$-$630\times$ faster.

Managing autonomous vehicle platoons requires a delicate balance between string stability and rigorous safety. This challenge is intensified by aggressive transients, such as highway merging. Although Constant Time Headway (CTH) spacing is the industry standard for Cooperative Adaptive Cruise Control, it lacks formal safety guarantees during significant velocity deviations. This letter proposes a computationally efficient control framework that considers a linear time-invariant model for the dynamics of each vehicle, while ensuring formal transient safety and stability. By introducing a spacing policy that naturally converges to CTH at steady state, we establish platoon safety as an inductive property. We derive a non-linear and saturated control law for the lead follower and provide sufficient initial conditions to guarantee velocity non-negativity and safety throughout the platoon for any CTH-based followers' control law. Numerical examples indicate the proposed methodology may be applicable even under non-nominal setups.

Deep neural networks have achieved strong performance in medical image classification, but often work like black-box. Commonly used post-hoc interpretation methods often provide heuristic visualizations whose relationship to the classifier's predictive distribution is indirect. This work introduces a local sensitivity analysis framework based on the input-dependent Fisher Information Matrix (iFIM) of a trained classifier. The iFIM characterizes how the classifier's predictive distribution changes under infinitesimal perturbations of the input image. By using a Gram-matrix formulation, the nonzero eigenspectrum of the iFIM can be recovered without explicitly forming the full image-dimensional Fisher matrix. The leading iFIM eigenspace is then used to project an input image into a high local-sensitivity component and its orthogonal component. These components provide a model-intrinsic description of local predictive sensitivity, rather than a conventional pixel-wise attribution heatmap or a causal segmentation of task-relevant anatomy. The framework is evaluated on controlled and clinical medical image classification tasks using multiple classifier architectures. Perturbation-based experiments show that high-sensitivity iFIM components are more strongly coupled to changes in predictive confidence and classification performance than lower-sensitivity complementary components. The results support the iFIM framework as a principled tool for analyzing local decision sensitivity and for complementing existing attribution-based interpretability methods in medical imaging.

We present a domain-extension framework for output-feedback boundary stabilization of reaction-diffusion equations on arbitrary bounded Lipschitz domains, including non-convex and multiply connected geometries. The plant is posed on an irregular domain whose boundary has actuated and uncontrolled portions. Just as backstepping transforms the plant dynamics into a stable target system, the method embeds the plant in a target domain, such as a ball or a rectangle, where a stabilizing design is already known. Every boundary portion through which the extension proceeds must carry actuation and the complementary collocated measurement. Uncontrolled portions are allowed when they are shared with the target boundary and have the same boundary-condition type. The gap between the two domains is filled with a virtual copy of the plant dynamics, coupled to the plant through interface conditions, and the concatenated state evolves exactly as the known closed loop on the target domain. Well-posedness and exponential stability of the physical state follow by restriction. The offline design data are inherited from the target design and are closed-form for constant-coefficient plants on balls and rectangles. Online simulation of the virtual PDE has the same computational character as a full-order PDE observer, a standard component of output-feedback designs. A new explicit Neumann-actuated backstepping law on n-balls enlarges the available target designs. Output feedback is obtained by lifting the target-domain observer, driven by a collocated interface measurement relayed through the virtual domain. Numerical experiments on star-shaped, horseshoe, and multiply connected domains, with a partitioned plant/controller implementation and a shared-wall cavity, test the designs.

Recent acoustic-to-articulatory inversion (AAI) models rely on electromagnetic articulography (EMA) data, which are costly and limited in scale. To address this limitation, we propose ArtBoost, a novel data augmentation strategy that leverages large-scale speech–mesh datasets originally developed for speech-driven 3D facial animation to improve AAI under limited EMA supervision. ArtBoost extracts pseudo articulatory trajectories from visible facial anchors and uses them for pre-training before fine-tuning on real EMA data. Experiments show consistent improvements in PCC and RMSE. Trajectory analyses confirm that the pseudo articulatory signals reflect physically meaningful visible articulatory dynamics. Additional evaluations across different AAI architectures demonstrate stable performance gains, indicating that ArtBoost can be integrated into diverse AAI models. These results suggest that speech–mesh data provide an effective and scalable source of articulatory supervision for AAI. Project page: https://cau-irislab.github.io/Interspeech26-ArtBoost/

Space heating in buildings accounts for 10% of the global CO2 footprint. The widespread adoption of energy-efficient heating technology, e.g., heat pumps, could help reduce this figure, but technology alone may not suffice to reach carbon neutrality. Additionally, human occupants have an important role to play by adopting sustainable heating behaviors, e.g., avoid excessive window opening in the winter or (pre-)heat their units while clean energy is abundant. Thus far demand response policies aimed at promoting these behaviors have been monetary, which discriminates against low-income households and exposes human occupants who do not actively engage with real-time control signals to financial risks. This paper instead investigates the suitability of a non-monetary karma economy for promoting sustainable heating behaviors. Karma leverages the repeated and dynamic nature of heating energy allocations to attain climate targets both fairly and efficiently over time without resorting to financial means. As a first step towards experimentally validating the karma concept with real human occupants in the KTH Live-In Lab, we perform a simulation study on a digital model of the Live-In Lab. The study provides initial estimates of expected effects to guide the design of human-in-the-loop experiments, as well as assists with designing and tuning the karma economy in this context. As a specific example, we investigate how incorporating consumption memory in the form of karma affects window opening behaviors in comparison to conventional memory-less heating operation.

Graph signal processing (GSP) provides a framework for analyzing data on irregular domains, with applications in neuroscience, finance, chemistry, and social sciences. Classical GSP primarily models symmetric relationships using undirected graphs, yet many real-world systems exhibit asymmetric interactions, motivating extensions to directed graphs. Central to directed GSP is the graph shift operator, typically defined via the directed graph Laplacian. Building on the well-known link between the undirected graph Laplacian and the diffusion operator, we establish a correspondence between the directed graph Laplacian and the diffusion-advection operator. This perspective opens new avenues for addressing crucial points such as frequency ordering, smoothness definition, and the design of spectral and graph filters. Specifically, we introduce two new orderings of frequencies based on the modulus and argument of the eigenvalues, naturally leading to new definitions of smoothness. Then we present two kernels reflecting diffusive and advective processes, namely the heat and transport kernels, respectively. Finally, we propose novel graph filters obtained by composing diffusive and advective parts, which approximate ideal spectral filters accurately and characterize the evolution of graph signals in richer ways. All aforementioned developments are illustrated on both synthetic and real graphs, including an application to temperature graph and signals.

This paper addresses real-time state estimation for a nine-compartment nonlinear COVID-19 epidemic model with two co-circulating strains, a super-spreader subpopulation, vaccination with waning immunity, hospitalization, and mortality. Time-varying transmission and vaccination rates are known inputs from a companion calibration, leaving the reconstruction of all nine states from three routinely reported observables: hospitalizations H, fatalities F, and vaccinated stock V. The contributions are theoretical rather than in the filter recursion. First, a Lie-derivative observability analysis yields, via a six-step derivation, the closed-form determinant |det(O9)| = delta_w * gamma_a^2 * kappa * rho2 * w1^2 * (delta_i - delta_p)^2 * |r1 - r2|, showing the level-2 codistribution is rank-deficient at the calibrated symmetric parameters (delta_i = delta_p, r1 = r2); the third Lie derivative restores full rank 9, with r2 the symmetry-breaking parameter. Second, an EKF is designed on the Euler-discretized dynamics with a closed-form 9x9 Jacobian and Joseph covariance update. Third, local exponential mean-square boundedness of the error is proved as a full theorem via the Reif-Gunther-Yaz-Unbehauen hypotheses, exploiting the bilinear drift and linear output to obtain a global-radius quadratic remainder bound that extends to bilinear-drift, linear-output systems. Fourth, the noise covariances are designed from calibration residuals and assessed by NEES and innovation-whiteness tests. All experiments use synthetic measurements from the calibrated model, so reported RMSE values (0.07%-2.72%) are methodology benchmarks, not predictive accuracy. A parameter-mismatch study shows measured and directly-coupled channels stay accurate under model error up to +/-30% while indirectly observed states degrade gracefully. The framework provides the state-feedback basis for future Model Predictive Control.

This paper introduces a learning-based control framework for real-time constrained optimal control of nonlinear systems with safety guarantees based on the Pontryagin's Minimum Principle. The approach learns a neural co-state (adjoint) policy that encodes optimality through the system Hamiltonian, rather than directly approximating a control law. Feasibility is enforced separately at runtime through an efficient convex projection that incorporates actuator limits and safety constraints expressed as control barrier functions. We refer to this framework as an adjoint-based neural regulator (ANR) as it yields a controller that satisfies constraints while retaining the optimality structure encoded by the learned adjoint. We demonstrate the effectiveness of the proposed framework on nonlinear constrained control tasks using a unicycle model. The ANR achieves performance at par with nonlinear model predictive control at more than two orders of magnitude lower computational cost, while exhibiting near-invariant performance across unseen scenarios, thus, significantly outperforming reinforcement learning methods in out-of-training-distribution regimes.

This paper presents a geometry-driven detection and fault-classification framework for grid-forming (GFM) inverters based on normally hyperbolic invariant manifolds (NAIM) and stochastic hypothesis testing. The GFM droop manifold $\mathcal{M}_0$ is identified as a NAIM of the closed-loop dynamics. Transverse fluctuations under grid noise are modeled as an Ornstein–Uhlenbeck process, and the long-run covariance is obtained from the algebraic Lyapunov equation. The detection statistic $D_t=T_w\bar{\xi}_{\perp}^{\top}\Sigma_{\mathrm{long}}^{-1}\bar{\xi}_{\perp}$ converges to $\chi^2(2)$ under the null hypothesis, yielding the tuning-free threshold $D_{\alpha}=-2\ln\alpha$ and an asymptotically exact false-alarm rate $\alpha$. A factor-of-2 error in earlier formulations is corrected and validated using 8,000 Monte Carlo realizations over nine window lengths and three significance levels. The Berry–Esseen bound $d_{\mathrm{KS}}\leq1.6704/(\beta T_w)$ is confirmed empirically. The minimum window condition $T_w\geq10/\beta_{\min}\approx1.0$ s, where $\beta_{\min}=\min(\omega_f,\omega_v)$, satisfies the IEEE 1547-2018 two-second detection requirement. A co-design theorem shows that increasing $(\omega_f,\omega_v)$ simultaneously enlarges the Fenichel spectral gap, tightens the null covariance, and reduces the false-alarm rate. Modal decomposition separates frequency and voltage contributions, enabling classification of islanding and voltage faults without additional sensors. Case studies confirm correct acceptance of normal operation, rapid detection of soft islanding, and accurate identification of a 10% voltage sag.

In laser powder bed fusion (L-PBF) processes, the rapid evolution of gas and fluid interactions complicates our ability to properly monitor or control the process, with unstable keyholes leading to porosity and spatter formation. High-speed operando x-ray imaging of the keyhole has been used to better understand the impact of these interactions on the monitoring and control of the L-PBF process. MOSAIC, a Mobile Object Segmentation algorithm for experiments under Adverse Imaging Conditions, is designed to perform rapid analysis of keyhole dynamics during active beamline experimentation without needing time consuming manual labeling or model training. Validation studies performed on 12 unique samples proved the robustness of MOSAIC with an average F1 score of 0.894 and a precision of 0.953 when compared to manually segmented images, performing equally or better than the SAM and YOLO machine learning methods tested. MOSAIC is efficient, processing frames cropped to a moving window approximately 150x250 pixels at 19.9 milliseconds per image on CPU, compared to 54 and 5284 milliseconds per image for inference on CPU for YOLO and SAM models.

Multi-fuel compression ignition (CI) engines offer superior power density and fuel flexibility. However, achieving consistent and optimal combustion phasing across a wide range of operating conditions remains a major challenge, particularly in the presence of modeling uncertainties. This paper presents a novel, data-driven real-time uncertainty compensation framework for combustion control in multi-fuel CI engines. The proposed approach introduces a pseudo-engine speed that enables dynamic adaptation of control inputs in response to uncertainty affecting the engine. To model the underlying combustion process, a Gaussian Process Regression (GPR) model is first trained on available input-output data, capturing the nonlinear and fuel-dependent behavior across varying operating conditions. Control inputs are then synthesized through model inversion of the learned GPR surrogate and augmented with an uncertainty compensator designed to mitigate deviations caused by dynamic variations in operating conditions and model inaccuracies. This integrated control strategy allows for real-time input corrections within a finite number of combustion cycles. Theoretical analysis establishes finite-time convergence guarantees for the proposed controller. Simulation results demonstrate that the proposed method steers the combustion phasing to the desired value in real-time, providing a scalable and adaptive control solution for multi-fuel CI engine operation.

Owing to the potential to reduce pilot overhead and mitigate channel aging, channel prediction is emerging as an important research topic in wireless communications. Meanwhile, deep neural networks are becoming a foundational technology for high-precision prediction thanks to their excellent non-linear representation capabilities. In this paper, we conceive a task-driven prediction network, which aims to deeply synergize the following two functions: learning global patterns for shareable features across adjacent time slots and structurally encoding time order to characterize the inherent causality within the channel dynamics. To implement channel prediction accuracy, we employ RWKV (receptance weighted key value) as network backbone and adapt it to the task's specific characteristics, utilizing its deep interleaved learning architecture to extract global patterns across multiple channel samples and leveraging its unique exponential decay to characterize temporal order. These task-driven unique designs significantly improve the learning efficiency of prediction network. Comprehensive experimental evaluations demonstrate the superiority of the proposed method over current data-driven methods, such as long short-term memory and Transformer, in the channel prediction task, including 1.84~4.29 dB gains in normalized mean squared error and 2.6~10.5 percentage point gains in cosine correlation.

Localizing from a single base station is a longstanding goal, since it removes the synchronized anchors that geometric methods require. A radio map (RM) answers a position query from this one-station survey, yet classical RMs store coarse received power and match it by correlation, ignoring the small-scale path structure a ray tracer provides. We instead build a small-scale RM and show that cell identification, rather than candidate generation, is its information-limited bottleneck. We propose path-atom localization by matching (PALM), which super-resolves a coarse angle-delay observation into scored atoms and matches them to a ray-traced RM by an exact marginal likelihood. The score marginalizes atom reality inside the logarithm, and we prove that the common posterior-scaled surrogate is a Jensen lower bound whose deficit grows with the number of strong paths. We match on the absolute delay axis under a clock nuisance, since relative delays jump across shadowing boundaries, and we prove a unit-gradient law, a capped miss cost, a minimum-mean-square local centroid, and finite-sample conformal coverage. On the real DeepMIMO campus scenario, PALM localizes to a 1.7 meter median from a single base station, cuts the ninetieth-percentile error of received-power RM matching by 34 to 62 percent, and halves the single-snapshot median to 7 meters.

Array calibration is critical to achieving accurate beamforming in millimeter-wave (mmWave) antenna-in-package (AiP) phased arrays, where over-the-air (OTA) calibration in ALL-ON mode is a standard requirement. For practical calibration measurements, two core metrics are paramount: efficiency (defined by measurement time) and reliability (robustness, governed by the condition number of the phased array calibration codebook). In this work, we propose a neural network-enabled codebook generation method for phased array calibration compatible with arrays of arbitrary sizes. Codebooks generated via the proposed method achieve low condition numbers while requiring the minimum number of measurements, outperforming state-of-the-art calibration approaches. Practical measurements on a 26-GHz AiP phased array validate the effectiveness and robustness of the proposed method, with superior performance in both array calibration accuracy and beamforming quality.

The US faces a growing resource adequacy challenge: new loads are being added at unprecedented scale while aging generating assets are being retired. In transmission-constrained grids, it is difficult to determine which units can be safely retired and which cannot be retired and instead require lifetime extensions until new generation can be built. Historically, this analysis was prohibitively time consuming. Transmission-constrained AC optimal power flow (ACOPF) is computationally intensive, and a thorough comparison and prioritization of generators could require hundreds or thousands of scenarios. We present an HPC-enabled framework that enables computation and geospatial mapping of the effects of generator retirement in terms of voltage magnitude and angle effects in the steady state. Specifically, our framework detects the effects of generator retirement using a simple k-nearest-neighbors model and a voltage-class-adjusted neighbor model. We demonstrate the results on over 8,000 generator retirement scenarios for a 70,000-bus transmission-constrained synthetic grid.

This paper studies safe distributed consensus for single-integrator multi-agent systems over connected undirected graphs under simultaneous asymmetric actuator constraints and output safety constraints. Each agent is equipped with a continuously differentiable asymmetric actuator dynamics that maps a commanded control signal to the realized plant input while keeping the latter strictly inside a prescribed admissible interval. To address output safety, a barrier-coordinate transformation is introduced over a common time-varying safe interval, and a distributed synchronization law is designed in the transformed coordinates. The resulting controller integrates a graph-based coordination layer with an actuator-side tracking layer, thereby enabling simultaneous enforcement of input admissibility, forward invariance of the safe output set, and asymptotic synchronization. For compact admissible sets of initial conditions, it is shown that the closed-loop solution is complete, all signals remain bounded, the actuator inputs remain strictly within their asymmetric bounds, and the agent outputs remain inside the prescribed safe interval for all time. Moreover, the transformed synchronization errors converge exponentially to zero, and the original agent outputs asymptotically synchronize to a designer-selected admissible trajectory embedded in the common safe interval. Numerical simulations validate the proposed framework and demonstrate safe consensus under both asymmetric actuation bounds and time-varying output constraints.

Short-duration speaker verification (SDSV) is crucial for personalized keyword spotting, where test utterances are typically shorter than three seconds. Limited speech duration results in unstable speaker representations and increased sensitivity to noise and phoneme variations, thereby degrading performance. To investigate this issue, we construct VoxPhrase, a large-scale SDSV corpus automatically segmented from the VoxCeleb dataset. Our analysis shows that text-dependent (TD) enrollment is constrained by duration and yields unstable speaker representations. In contrast, although text-independent (TI) enrollment introduces content mismatch, its representations become more stable as the enrollment duration increases. Accordingly, we propose a hybrid-enrollment neural re-scoring framework that combines TD and TI enrollment and performs frame-level comparison via parallel cross-attention. Experiments on VoxPhrase demonstrate consistent improvements across multiple speaker models.

In the digital age, image compression is crucial for numerous applications, including web media, streaming services, high-resolution medical imaging, and connected vehicle networks, enabling efficient data storage and transmission. With the increasing demand for high-quality image communication, the need for advanced compression techniques becomes increasingly critical. Numerous Deep Image Compression (DIC) techniques have recently been introduced, showing impressive performance compared to traditional standards. However, variable-rate image compression remains an unresolved issue. Specific DIC methods deploy multiple networks to attain different compression rates, whereas others use a single model, which often results in higher computational complexity and reduced performance. This work proposes a progressive learning approach for variable-rate image compression based on the parameter-efficient fine-tuning method, the Low-Rank Adaptation (LoRA). We introduce an additional LoRA Rate-Adaptive Module (LoRAM) in DIC methods. Due to the re-parameterized merging of LoRA, our proposed method does not introduce additional computational complexity during inference. Compared to methods utilizing multiple models, comprehensive experiments demonstrate that our approach achieves competitive performance, saving 99% in parameter storage, 90% in datasets, and 97% in training steps.

Speech systems used in customer-facing applications often require domain-specific language coverage. We present a synthetic Bengali speech dataset for telecom customer-care scenarios. The dataset contains 10,000 audio-text pairs, approximately 26.82 hours of 24 kHz speech, and predefined train, validation, and test splits of 9,000, 500, and 500 examples. It is publicly released on Hugging Face under the CC-BY-4.0 license. The speech was generated with OmniVoice in voice-cloning mode using a real female reference recording and transcript, with bfloat16 precision, 16 diffusion sampling steps, and a speaking-rate control value of 1.0. Along with the original Bengali text, the dataset provides a normalized transcript field designed for ASR/STT training and evaluation. We report an automatic intelligibility check over all 10,000 samples using a domain-adapted Whisper ASR model fine-tuned from bengaliAI/tugstugi_bengaliai-regional-asr_whisper-medium, along with a manual listening check on selected samples. The evaluation gives an average WER of 2.54%, an average CER of 0.59%, and median WER and CER values of 0.00%. These results suggest strong text-audio consistency under the selected automatic evaluation pipeline, while the paper also discusses the limitations of synthetic speech and STT-based evaluation.

Accurate RF-based ranging is critical for location-aware wireless systems, yet no open platform exists for fair, reproducible comparison across protocols under realistic hardware impairments. Existing simulators target communication-layer metrics and lack ranging algorithms, impairment models, and positioning-specific evaluation. We present RadioRange, an open-source, positioning-first digital twin that unifies UWB, Wi-Fi, and 5G NR on identical ray-traced physical channels. The platform models eleven independently toggleable hardware impairments across three injection stages, spanning antenna-level offsets, RF circuit non-idealities, and post-compensation CSI residuals, each with documented physical models and protocol-specific defaults. Five first-path ranging detectors and three multipath identification algorithms are provided within a protocol-specific evaluation framework, enabling controlled Monte Carlo benchmarking and systematic ablation studies. The simulator is validated against real-world UWB and Wi-Fi measurements, demonstrating that the channel model captures geometry-dependent multipath bias. RadioRange-Sim is publicly available at https://github.com/Togure/RadioRange.

In recent years, emerging research at the intersection of quantum physics and sound synthesis has opened new conceptual and technical possibilities for instrument design and sonic exploration. This study investigates the potential of formal analogies between quantum systems and classically non-deterministic systems for the generation of tangible acoustic phenomena. Specifically, it explores how quantum mechanical concepts can serve not only as metaphors but as operative frameworks in the design of new musical tools. Building on recent theoretical work on stochastic string excitation, we present the design, fabrication, and spectral characterization of a custom-built noise-driven electroacoustic string instrument. The system implements open-loop stochastic electromagnetic actuation without feedback or pitch stabilization. We show that this excitation strategy produces a dense and uniformly distributed spectral regime that differs from conventional deterministic string excitation. This work contributes to a growing field of quantum music creation by offering a hybrid artistic-scientific platform with potential applications in live performance, experimental composition, and science education.

The electrification of heating systems is a critical pathway for decarbonizing the building sector; however, the development of sustainable strategies is often hindered by the lack of granular thermal load profiles. The nature of this problem is such that available data are extremely scarce, irregular, and low-frequency, rendering conventional data-hungry machine learning approaches impractical or unreliable. High-resolution gas metering is rarely available, as it falls outside standard utility business requirements. To bridge this gap and enable data-driven AI analytics under severe data limitations, this paper presents the Generalized Proxy-Guided Load and Temporal Disaggregation framework. Validated on a dataset of 11 multi-unit residential buildings over 18 months, the framework achieves a mean squared percentage error (MSPE) of 6.37% for reconstructed total gas consumption. The methodology operates through a four-stage process: (i) Generalized Occupancy Proxy Extraction via weather normalization to isolate behavioral signals from hourly electricity data; (ii) Unified Segmentation and Normalized Pooling to mitigate the statistical limitations of sparse billing data; (iii) Unified Baseload Parameter Estimation enhanced by local calibration to ensure building-specific accuracy; and (iv) Component-Wise Temporal Disaggregation to reconstruct distinct baseload and heating profiles. Overall, the proposed framework effectively bridges the resolution gap, transforming low-frequency utility data into high-fidelity training sets suitable for scalable, data-driven decarbonization modeling.

We establish sufficient conditions for robust positive invariance under state- and input-dependent disturbances with anisotropic covariance structure. The proposed ansatz maps a fixed ellipsoidal template through a GP-derived positive-definite matrix field, subsuming scalar homothetic scaling while retaining finite graph-based verification. The resulting LMI conditions couple the learned field to Schur-stable dynamics; an isotropic fallback with inflation factor $r=1/(1-\gamma_{\mathrm{cl}})$ proves admissibility. During each learning epoch the field is frozen, so online tube evaluation is one GP covariance query and a small matrix square root, with no online set iteration or LMI solve. Quadrotor simulations show a $195\times$ reduction in 3D velocity-tube volume and a $2.1{\times}10^5$ reduction in the joint 7D velocity-control subspace relative to a non-adaptive homothetic baseline. This extended version adds full proofs, a separated offline/online complexity analysis, and controller-sweep, contraction, and projection-area studies.

Reliable state estimation in robotics and control re quires balancing estimation accuracy against computational cost. While filtering-based methods such as the Extended Kalman Filter (EKF) provide efficient real-time updates, and optimisation based formulations using factor graphs improve global consistency, the role of optimisation scheduling is often treated implicitly rather than examined as an explicit design variable. This paper presents an experimental study that explicitly isolates optimisation scheduling using a Smart Scheduled Hybrid (SSH) EKF-FGO framework as a controlled testbed. By combining EKF-based state propagation with periodically invoked batch optimisation and holding solver structure and effort fixed, the main contribution of this work is the experimental characterisation of optimisation scheduling as an independent design variable governing the trade-off between intermediate estimation accuracy and computational cost. Simulation results in a planar SLAM environment show that scheduling strongly influences pre optimisation drift, transient error behaviour, and runtime. In particular, the results identify operating regimes in which most of the benefit of global optimisation can be retained at a fraction of the computational cost, highlighting optimisation scheduling as an under-explored yet critical consideration in hybrid state estimation systems.

Bit-serial computation enables sequential processing of data at the bit level, providing several advantages, such as scalable computational precision. This approach has gained significant attention, especially for exploiting bit-level sparsity in AI workloads. While current bit-serial processors leverage bit-level sparsity to eliminate the computation associated with zero bits, they face a fundamental trade-off: either they suffer from low memory-access and computation efficiency caused by irregular patterns of non-zero bits, or they incur substantial area overhead from complex online scheduling mechanisms required to reorganize bit-level data and preserve memory access and computation regularity. Therefore, we present the SparseCol processor, designed to harness extensive bit sparsity while maintaining high hardware utilization across various AI applications, including CNNs, RNNs, and transformers. In contrast to traditional methods, SparseCol exploits structured bit-level sparsity, denoted by bit-column sparsity, without requiring any re-training. Furthermore, SparseCol implements a dynamic dataflow architecture that tackles hardware under-utilization issues commonly found in existing bit-serial solutions. Fabricated in 16nm CMOS node, SparseCol delivers 1320 BTOPS/W (BTOPS represents Binary Tera-Operations Per Second, calculated as #W bits x #A bits TOPS) peak efficiency while maintaining accuracy, outperforming SotA sparse processors in terms of efficiency by 6.8x. Comprehensive evaluations on CNN classification tasks and transformer architectures demonstrate system-level efficiencies of 745.02 BTOPS/W and 850.5 BTOPS/W, respectively.

Lower-limb exoskeletons require actuation systems that can provide accurate joint torque control while preserving low mass and encumbrance. Conventional architectures often rely on independently actuated joints and joint-level torque sensors, increasing system complexity and weight. This paper presents a novel differential actuation architecture for hip-knee flexion/extension, enabling cooperative torque sharing between two motors via a linear differential mapping between motor and joint. To compensate for transmission losses, a model-based friction estimation strategy is developed and experimentally implemented, allowing accurate joint torque estimation without the need for torque sensors. The proposed solution is validated on a physical prototype, demonstrating the feasibility of sensorless torque estimation in a differentially actuated hip-knee module of a lower-limb exoskeleton.

Asthma causes expiratory airflow limitation and is clinically assessed using spirometry, which provides the FEV1/FVC ratio representing the proportion of air exhaled in the first second relative to total forced vital capacity. Prior studies suggest that respiratory sounds recorded at posterior sites (Left Lower, Left Upper, Right Upper, Right Lower) reflect regional airflow patterns. In this study, we investigate the relationship between the expiratory-to-inspiratory (E/I) spectral power ratio and FEV1/FVC in 141 participants aged 20-60 years using Spearman correlation across frequency subbands. The 100-200 Hz and 200-400 Hz bands showed significant correlations. Overall, lower posterior sites showed stronger associations; younger adults showed stronger correlations at the Left Lower site, whereas older adults showed stronger correlations at the Left Upper site. Gender-stratified analysis showed stronger Left Lower correlations in males and stronger Left Upper correlations in females.

Codecfakes (CFs) are a type of speech deepfakes generated through Audio Language Models (ALMs), with Neural Audio Codecs (NACs) forming the core mechanism for speech encoding and generation. CFs exhibit distributional characteristics that differ from vocoder-based deepfakes, causing detectors trained on vocoder data to generalize poorly to CFs detection. Although this has led to the development of CF detection benchmarks, existing resources are largely confined to English – and to a limited extent Chinese – leaving South-East Asian (SEA) languages unexplored. To bridge this gap, we introduce SEA-CF, the first large-scale benchmark for CF detection spanning multiple SEA languages, diverse speaker profiles, and a wide range of NAC architectures. SEA-CF is constructed by synthesizing publicly available real speech corpora. Our experiments show that state-of-the-art (SOTA) CF detectors trained on English-centric datasets fail to generalize to SEA speech due to language-specific phonetic structures, tonal variations, and rich prosodic diversity. We further conduct a comprehensive zero-shot and fine-tuned evaluation of recent SOTA ALMs on SEA-CF. Fine-tuning the ALMs improves performance, however, these are very large being impractical for real-world application due to their scale, particularly in low-resource and latency-constrained settings. To address this limitation, we propose a novel small-ALM, GARUDA tailored for CF detection, which delivers strong performance while remaining lightweight. Extensive evaluations demonstrate that the proposed Small-ALM outperforms strong end-to-end and ALM-based baselines, establishing a new, practical direction for robust CF detection in SEA languages and beyond.