Papers

The full potential of artificial intelligence in tibial plateau fracture characterisation remains unrealised, constrained by a fundamental dependency on labelled datasets whose consistency cannot be guaranteed: conventional classification schemes such as Schatzker and AO/OTA suffer from inter-observer variability, causing supervised models to learn human disagreement rather than stable fracture morphology. We design, implement, and validate a label-agnostic framework that eliminates this constraint by learning fracture representations directly from imaging data without observer-assigned labels. A RadImageNet-pretrained ResNet-50 encoder is fine-tuned on 154 cleaned knee radiographs using the SimCLR contrastive objective, preceded by a data cleaning protocol and followed by UMAP dimensionality reduction and k-means clustering to discover four imaging-derived phenotypes. Phenotype validity is assessed through a blinded expert review protocol administered to two independent clinicians. The four phenotypes demonstrate robust stability (bootstrap ARI = 0.319 +/- 0.041), strong internal cohesion (silhouette = 0.511), and coherence ratings of 3-5/5 from both reviewers under blinded conditions; one phenotype was unanimously identified as exhibiting comminution – a high-complexity feature isolated without any supervisory signal. Inter-partition comparison against Schatzker labels yields ARI = 0.013, confirming orthogonality to conventional classification boundaries. Notably, expert reviewers anchored to established classification vocabularies perceived imaging-derived groups as heterogeneous precisely where Schatzker alignment was lowest, suggesting that Schatzker-trained perception and label-agnostic embedding geometry measure orthogonal dimensions. These findings establish label-agnostic SSL phenotyping as a reproducible and clinically interpretable complement to conventional classification.

Safe set computation is a fundamental challenge in safety-critical control systems, especially in direct data-driven settings where safety analysis is performed directly from noise-affected measurements, without explicit modeling. A recently proposed method, Data-Driven Hamiltonian (DDH), enables reachability analysis directly from measurements, without relying on prior knowledge of the underlying system dynamics. This paper extends the DDH framework to a robust setting that accounts for measurement noise, exogenous disturbances, and sampling-induced state-velocity estimation error. A Robust Data-Driven Hamiltonian (R-DDH) is derived from noisy measurements and shown to yield a certified lower bound on the exact Hamiltonian. This results in a provable under-approximation of the value function and an inner approximation of the associated safe set. The gap between the data-driven and exact Hamiltonians is quantified, and it is shown to converge to zero with more data in a noise-free setting with additive disturbances. The effectiveness of the approach is shown through two case studies: a constrained double integrator and an aircraft taxiing system with a nonlinear closed-loop controller operating under perceptual uncertainty.

While Large Language Model (LLM) based Automatic Speech Recognition (ASR) enables seamless multilingual use, models often misidentify the output language, compromising transcription fidelity and downstream application quality. To preserve flexibility and code-switching capabilities, we propose a soft prompting approach that hints at potential spoken languages without strictly constraining the output. We formally define this challenge as a lack of language adherence, introduce a novel metric to quantify violations, and evaluate three mitigation strategies: (1) zero-shot prompting for robust guidance under uncertainty, (2) supervised fine-tuning (SFT) to improve prompt adherence, and (3) Chain-of-Thought (CoT) reasoning to enforce adherence during decoding. We present a comparative analysis of these methods across multiple languages, evaluating effectiveness in reducing the language violation while maintaining overall ASR performance. Finally, we discuss trade-offs to guide strategy selection under various compute constraints.

In this paper, a novel optimal soft-landing guidance law with inequality approach-angle path constraints is analytically derived. The proposed guidance law prevents ground collision and enables approach-angle control by constraining the optimal trajectory to remain within a convex inverted pyramid originating at the landing point. A 3D point-mass linear kinematic model in a constant gravitational field is employed, together with a quadratic control-effort cost and terminal constraints on position and velocity. Analytical open-loop and closed-loop solutions, together with the optimal final time, are derived using Pontryagin's Minimum Principle and the optimality conditions at the transitions between unconstrained and constrained arcs. It is additionally shown that the optimal final time decreases when the path constraints become active. The resulting guidance law is continuous, piecewise linear in time, and nonlinear in the states in closed-loop. When a constraint becomes active, the controller cancels the gravitational component normal to the constraint, causing the trajectory to evolve along the constraint surface. The proposed guidance law is evaluated in simulations under various initial conditions, demonstrating accurate landing performance and consistent satisfaction of the path constraints.

In skill-constrained production-inventory systems, the qualified human capacity available tomorrow depends on training decisions made today: production requires certified workers, certifications decay unless maintained, and training consumes the same scarce worker hours that production needs now. We study a closed-loop skill-constrained model predictive controller that, at every shift, solves a finite-horizon mixed-integer program over production, inventory, backlog, and training, with binary predicted certification, hard production eligibility, and an interpretable terminal value that prices certified-capacity gaps at the horizon boundary; only the first-period action is applied before replanning. On synthetic, seed-controlled SkillChain-Gym scenarios - announced and surprise new-skill shocks, demand shocks, absenteeism, forecast- and availability-quality modes, capacity-boundary and training-rate sweeps, and negative controls - we evaluate the controller against production-only and maintenance-only ablations, static cross-training insurance plans, and a strong reactive heuristic, under an ex-ante locked configuration and paired statistics. The result is regime dependence, not superiority: no policy class dominates. Predictive control helps when skill or labor bottlenecks are forecastable early enough for training to complete; lean static insurance remains hard to beat under surprise shocks, near the demand-capacity boundary, and wherever pre-shock slack makes insurance cheap. Attribution ablations separate certification maintenance, re-acquisition of lapsed certifications, and greenfield skill acquisition. Forecastability, not adaptivity per se, decides when predictive control pays.

Production planning increasingly has to treat workforce capability as a decision variable: certifications lapse when skills are not maintained, new products require skills the current workforce does not hold, and reskilling competes for the same worker hours needed for production. Existing operations benchmarks usually treat labor as exogenous, while workforce-planning models with skills and learning are rarely released as reusable testbeds. We introduce SkillChain-Gym, a benchmark specification for reskilling-aware production-inventory control: a single-site environment with stylized worker skill-state dynamics, hard threshold certification, forgetting, and capacity-consuming training actions constrained by the same per-worker time budget as production. The benchmark includes seed-controlled disruption scenarios, three feasibility modes with projection diagnostics, deterministic replay, and metrics covering operations, resilience, capability growth, and training-access distribution. We evaluate production-only, reactive adaptive, water-filling adaptive, and static-insurance policies with budget variants over 60-shift horizons with paired statistical tests. The results are regime-dependent rather than a ranking. Training-capable policies dominate the production-only baseline, and maintenance training is necessary under forgetting even without disruptions. Among training-capable classes, adaptive training helps when bottlenecks are visible in the forecast, while a lean static cross-training plan, a deliberately favorable comparator whose structure encodes relevant skill contingencies, acts as strong insurance under surprise shocks and absenteeism. Capacity slack and the forgetting rate govern the boundary between these regimes. No policy class dominates across regimes, motivating forecast-driven controllers that decide when to buy skill insurance and when to react.

In distant microphones, broadband (BB) methods for direction-of-arrival (DoA) estimation are more suitable than narrowband (NB) methods. Due to the aggregation of their optimization function across all frequency bands, BB estimators are robust to spatial aliasing, a known problem in processing distant microphone data. In NB methods, DoA estimation is performed by utilizing local information in each frequency band and hence the estimation is affected by spatial aliasing. However, unlike BB methods, NB methods exploit frequency sparsity to estimate the DoAs of multiple speakers in a single time frame. In this article, a method to improve the robustness of a NB DoA estimator to spatial aliasing is developed. The proposed method is based on cross-correlation of speech-present time-frequency regions obtained by single frequency filtering (SFF) of the microphone signals. The SFF spectrum is chosen because SFF components have regions of high signal-to-noise ratio both in time and frequency and because speech and non-speech discrimination is robust to degradations in the SFF domain. The proposed NB estimator is compared to four state-of-the-art estimators (one NB and three BB) using detection and accuracy metrics on simulated and real-world data in different reverberation and noise conditions. The results show that in all the environments, the SFF-based NB approach outperforms the state-of-the-art NB approach. Furthermore, the performance of the SFF-based approach is better than some of the BB estimators.

It is well known that intelligibility of speech reduces in the presence of ambient noise. However, studies show that all sounds are not affected uniformly (or equally) and that vowels are more robust to noise than consonants. In this study, intelligibility of various consonants is assessed and analyzed in stationary white noise and non-stationary babble noise conditions. Specifically, this study investigates the individual contribution of magnitude and phase spectra of a given speech signal on human speech recognition of consonants in noisy conditions. In this regard, three experiments are carried out. In experiment 1, clean signal, signal reconstructed with only magnitude spectrum information (magnitude only signal) and signal reconstructed with only phase spectrum information (phase only signal) are assessed for intelligibility. In experiment 2, noise is added to clean speech. From noisy speech, phase only signal and magnitude only signal are reconstructed and intelligibility tests are performed for all these three signals. In experiment 3, noise is added directly to the magnitude only and phase only signals reconstructed from clean speech and their intelligibility is assessed. Results of these experiments show that magnitude spectrum contributes more to intelligibility in clean condition than phase spectrum, while information from phase spectrum is more robust in noisy conditions. It is also observed that, among consonants, nasals are more susceptible to noise whereas fricatives and approximants were observed to be comparatively more robust.

Robust direction-of-arrival (DoA) estimation from noisy and reverberant microphone signals remains challenging. Conventional estimators such as generalized cross-correlation (GCC) and its variants operate in the short-time Fourier transform (STFT) domain, where spectral features primarily reflect vocal-tract characteristics. Recent single frequency filtering (SFF)-based estimators instead use a time-frequency representation that provides high spectral resolution of harmonics along with high temporal resolution of excitation-source events, such as epoch-like impulses. Since excitation-source features have been shown to be more robust to noise and reverberation than spectral features, this work proposes an improved SFF-based DoA estimator that correlates the envelopes of SFF outputs across microphone channels using PHAT-weighted GCC. We further provide a comprehensive evaluation of SFF-based and state-of-the-art GCC-based estimators using publicly available real-room recordings under challenging reverberant, multi-speaker, and noise-corrupted conditions. Experimental results show that the proposed method and an existing SFF-based estimator achieve detection and accuracy performance that is superior or comparable to the best GCC-based estimator across all test cases. We also demonstrate that using speech-dominant bins improves GCC-PHAT robustness, motivating future incorporation of such weighting strategies into SFF-based DoA estimation.

In this work, we study zero-shot cross-lingual speech-based Alzheimer's disease detection (SADD). We hypothesize that learning language-invariant multimodal representations by fusing multilingual speech and text pretrained models is essential for reliable transfer to unseen languages, as the two modalities capture complementary acoustic and linguistic markers of cognitive impairment while adversarial learning suppresses language-specific confounds. Empirical results in zero-shot cross-lingual evaluation substantiate the hypothesis, showing that multimodal fusion consistently outperforms unimodal baselines. To this end, we propose ORBIT, a novel framework that combines cross-attentive fusion, multi-tap language adversaries, and complementary spherical–hyperbolic geometric learning with consensus clustering. Across settings, ORBIT achieves the strongest performance compared to unimodal models and simple concatenation-based fusion baselines.

The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets. Yet a multi-year global semiconductor supply constraint and the growing energy and carbon cost of always-online inference expose the fragility of this trajectory and motivate the opposite direction: refactoring AI and ML algorithms to fit the small, ubiquitous microcontrollers already in mass production in wearables, sensors, and edge appliances. We present an end-to-end open-source reproduction of FastGRNN, a compact gated recurrent cell, deployed on two bare-metal targets: the 8-bit Arduino (ATmega328P) and the 16-bit MSP430 (no hardware multiplier; 16 KB Flash; 512 B SRAM). Our compression pipeline combines low-rank weight factorization, iterative hard-thresholding sparsity, and per-tensor Q15 post-training quantization with explicit activation calibration. The deployed model occupies 566 bytes of weights and achieves macro F1 = 0.918 (seed 0; five-seed Q15 mean 0.853+-0.107) on the HAPT test set. It matches a PyTorch reference at 100% prediction agreement across 3,399 test windows (MCU seed 0; 99.91-100% C-equivalent across five seeds). Both platforms sustain real-time 50 Hz streaming inference (9.21 ms per sample on Arduino; 13 ms on MSP430), where a 256-entry sigmoid/tanh look-up table delivers a 30.5x speedup on the multiplier-less MSP430. Four contributions extend the original FastGRNN paper: (i) cross-platform bit-equivalent deterministic inference; (ii) characterization of recurrent warm-up latency (median 74 samples, 1.48 s; worst-case 125 samples, 2.50 s over 100 test windows); (iii) a deployable look-up-table recipe for multiplier-less embedded targets; and (iv) hardware energy characterization showing 17.7 mW active inference power, <0.09 mW idle power, and 96.7% energy reduction with the LUT.

This paper investigates the performance of tunable liquid lens (TLL)-assisted receivers in large-scale visible light communication (VLC) systems under random receiver orientation. A simple electrowetting-based TLL architecture is proposed, capable of dynamically steering the incident optical signal toward the photodiode receiver by adjusting the orientation of the liquid interface. The proposed architecture enhances the desired signal reception while mitigating interference from neighboring access points (APs). The spatial distribution of APs is modeled using a Matérn hard-core point process, whereas receiver orientation is characterized by uniformly distributed azimuth angles and Gaussian-distributed polar angles. Furthermore, a tractable mathematical optical channel model is developed to capture the combined effects of AP/receiver locations, receiver orientation, and lens adjustment angles on the VLC channel gain. Based on this framework, three lens orientation strategies, namely best signal reception (BSR), closest LED selection, and vertical upward lens orientation, are proposed to improve system performance under dynamic receiver conditions. Using stochastic geometry tools, exact and approximate analytical expressions for the outage probability are derived for each scheme. Numerical results verify the accuracy of the developed analysis and demonstrate that the proposed TLL-assisted receiver architecture significantly improves the robustness of VLC systems under severe receiver orientation fluctuations and dense AP deployments. In particular, the BSR scheme reduces the outage probability by $57.1\%$ compared with conventional fixed-lens receivers at an AP height of $3.5$ m and AP density of $0.2~\text{m}^{-2}$. The presented analytical framework and numerical results provide useful design insights for the deployment of future TLL-assisted VLC networks.

Continuous AI inference on resource-constrained edge hardware introduces deployment effects that are largely invisible to conventional benchmark evaluation, including temporal instability in streaming video, thermal throttling under sustained load, and workload-dependent performance variability. We present Edge-TSR, a deployment-oriented continuous edge inference system for sustained roadside perception on the NVIDIA Jetson Orin Nano. Edge-TSR integrates detection, tracking, fine-grained classification, and a lightweight track-aware temporal stabilization mechanism that improves streaming inference consistency with negligible computational overhead. Our central finding is that benchmark-centric evaluation systematically overstates deployed edge inference performance. Across three state-of-the-art baselines, we observe consistent 20-30% relative degradation when transitioning from static-image evaluation to real-world streaming deployment. Edge-TSR addresses this gap through temporal inference stabilization, recovering up to 10.16% classification accuracy over per-frame inference baselines while maintaining sustained real-time performance under continuous operation. We evaluate the complete system under diverse real-world deployment conditions, jointly characterizing inference quality, latency, throughput, and thermal behavior during long-duration operation. A 55-minute vehicular deployment over a 26 km route demonstrates sustained operation at 16.18 FPS within safe thermal limits on a single embedded device without cloud offload. Our findings show that deployment-aware evaluation and temporal inference stabilization are necessary components of continuously operating edge AI systems intended for real-world sensing deployments. We release a sample annotated streaming video evaluation dataset and full system implementation to support reproducible deployment-centric evaluation.

We use temporal unitary transforms to generate 16-QAM up to 220 GBd using only 50-GHz electrical bandwidth. The technique is theoretically lossless and can generate arbitrary optical waveforms beyond the bandwidth of the constituent modulators.

Farrow structures based on linear–phase FIR subfilters provide an efficient realization of variable fractional–delay (VFD) filters with reduced implementation complexity. While the all–linear–phase configuration admits a decoupled least–squares (LS) formulation with an analytical solution, this decoupling fails when branches of mixed types, linear–phase and general FIR, are required, as occurs when a group–delay constraint is imposed. This letter presents a unified LS design for Farrow structures via a nullspace parameterization of the per–branch symmetry constraints, yielding an analytical solution that accommodates arbitrary per–branch types. Numerical results demonstrate that the proposed framework satisfies group–delay constraints that the all linear–phase approach cannot meet, while substantially reducing the number of free parameters relative to the unconstrained general FIR baseline.

This paper develops and analyses the Fair Play Automatic Market Maker (FP-AMM), a programmable electricity allocation mechanism in which scarcity allocation is treated as a controlled, stateful, and auditable cyber-physical process. Existing mechanisms such as locational marginal pricing are memoryless and cannot account for historical service outcomes, preventing guarantees of equitable treatment across market intervals. The FP-AMM employs a two-stage stochastic clearing rule comprising service-priority sampling and inverse-fairness weighting, coupled with a DC-OPF feasibility set and bounded shortage memory updated through a saturated integrator. Four main results are established. First, the shortage-memory state is invariant in $[0,1]^N$ and the update map is a contraction with rate $1-\beta$. Second, the intra-interval clearing operator converges linearly to a unique fixed point with contraction factor $q\in(0,1)$. Third, under the Fair Play priority rule, the per-node delivery ratio converges almost surely to the contracted target $F^\star$, with a finite-time $O(1/\sqrt{T})$ bound obtained via Lyapunov analysis of the deficit recursion. Fourth, event-triggered execution guarantees practical ultimate boundedness of the allocation tracking error and quantifies the computation-fidelity trade-off. The mechanism is validated on the IEEE 14-, 57-, and 118-bus systems over $T=5000$ market intervals. Fairness convergence to $F^\star$ is achieved on all benchmarks, peak weak-bus fairness error is reduced by 54% on the IEEE-57 network and by up to 55% relative to an equal-weight baseline during scarcity periods, and DC feasibility is maintained throughout.

This paper revisits the strong duality in the linear quadratic regulator (LQR) for continuous-time and discrete-time systems, and explores its interconnection with typical assumptions and the uniqueness of primal-dual solutions. Using a linear operator $\Psi$, we formulate a common nonconvex LQR problem that captures both time domains. We then derive its Lagrange dual problem and establish the strong duality via a rank-constrained tight semidefinite program (SDP) relaxation. Further, we show that the primal-dual optimal solutions to the SDP relaxation, after dropping the rank constraint, recover the classical algebraic Riccati equations and optimal feedback gains in a constructive manner. The dual derivation and strong duality analysis rely on mild standard assumptions and exploit the properties of the linear operator and its adjoint, revealing a structural symmetry between the two time domains.

Numerical integration plays a central role in inertial navigation systems, where sensor measurements are propagated through time to obtain orientation, velocity, and position states. The accuracy of this propagation depends on the numerical integrator type, order and step-size. Prior work showed that for second-order systems with known forcing functions, the gauge freedom in the variation of parameters technique can be exploited to reduce truncation error without modifying the integrator. However, this approach requires analytical knowledge of the forcing function, limiting its applicability in real-world systems. To address this limitation we propose the u-space methodology, a novel state mapping that generalizes the gauge freedom to systems with unknown forcing functions. The optimal gauge is derived in closed form for second-order systems and in both closed and empirical form for first-order systems. The proposed approach was evaluated through Monte Carlo simulations across four forcing functions, five sensor grades, and four Adams-Bashforth orders, as well as on a real-world inertial navigation dataset. Results show consistent error reduction across all tested conditions, with the largest gains observed in the full inertial mechanization pipeline, making the approach applicable to high-grade inertial systems, where truncation error constitutes a larger share of the error budget, and to aided low-cost systems with high-rate updates, where propagation spans only short inter-update intervals.

The presence of interfering scatterers fundamentally changes the design principle for MIMO sensing. Unlike the target-only case, where MIMO sensing sequence design reduces to optimizing the transmit sample covariance, this paper shows that scatterer-induced signal-dependent interference makes the Bayesian Fisher information depend on the full temporal precoding sequence. Consequently, for the MIMO sensing problem with scatterers using the Bayesian Cramér-Rao lower bound (BCRLB) as the objective, the entire sensing sequence must be designed explicitly, instead of just the precoding matrix. This paper considers such a precoding sequence design problem under hardware constraint for MIMO sensing for estimating the azimuth angles of multiple targets based on the prior information of both the targets and the scatterers. We formulate a worst-case BCRLB minimization across multiple target angles, yielding a max-min fractional program under constant-modulus or constant-norm hardware constraints. We further develop a constant-norm linear transform that converts the ratio objectives into linear forms, leading to an iterative algorithm with closed-form precoder updates. The framework extends to joint precoder-combiner design and multi-stage sensing with adaptive prior refinement. Numerical results demonstrate the effectiveness and the efficiency of the proposed algorithm, revealing sweeping-like beampatterns that illuminate target angular regions while suppressing interference from the scatterers.

Graph neural network architectures based on the graph Laplacian approximate the Laplace-Beltrami operator, thus limiting their application to isotropic operators. As a nonlinear alternative to the Laplace-Beltrami operator, we consider estimates of the Finsler Laplacian on point clouds sampled from a manifold. We prove that these discrete estimates converge to the true operator on the manifold as the number of point samples grows. Moreover, we show that this operator can be expressed as a graph neural network layer, which we use to define a family of Finslerian graph neural networks constrained to express Finsler geometry. We show that Finslerian graph neural networks recover the geometry underlying nonlinear diffusion equations in practice.

Over-the-air federated learning (FL) leverages the superposition property of multiple-access channels to enable communication-efficient distributed model training. Existing integrated sensing, communication, and computation (ISCC)-enabled over-the-air FL systems typically require dedicated resources for the sensing module, inevitably compromising FL performance due to resource competition. In this paper, we propose a sensing-native over-the-air FL framework that explores built-in distributed wireless sensing capability with zero overhead per model aggregation. Specifically, the high-dimensional local gradient signals possessing favorable autocorrelation property are concurrently leveraged for target distance estimation, while the gradient statistics already required for over-the-air FL serve as a ready-made gateway to deliver locally-sensed results to the edge server for cooperative localization. To combat inter-device interference, channel fading, and communication noise, we put forth a robust trilateration-based target positioning method building upon an efficient matched-filtering-based distance estimation. Then, by explicitly characterizing the impact of imperfect model aggregation and noisy gradient-statistics transmission on the sensing-native over-the-air FL convergence, we develop a statistics-aware communication-learning co-design approach. We first derive the closed-form optimal power budgets allocated to local gradients and their statistics, based on which an efficient successive convex approximation method is proposed for receiver beamforming optimization. Simulation results show that the proposed framework simultaneously achieves superior learning and sensing performance compared to representative baselines.

The paper proposes a new approach to address the bounded-thrust powered-descent problem while ensuring ground-collision avoidance. A time-dependent polynomial approximation of the mass is employed to formulate a bounded linear-quadratic optimal-control problem that minimizes the thrust-acceleration control effort, terminal miss, and terminal velocity error. The resulting approximation is used to impose a hard constraint on the horizontal thrust profile while keeping the vertical thrust profile unconstrained. The key idea is a hierarchical separation of the thrust allocation, which enables analytical ground-collision avoidance under bounded thrust. Unlike existing bounded-thrust powered-descent approaches based on numerical optimization and trajectory-shaping constraints, the proposed method provides explicit analytical collision-avoidance conditions. Building on this formulation, the guidance law predicts the switching times between saturated and unsaturated arcs and shapes the thrust-acceleration profile to achieve a soft landing, even when the controller remains saturated over extended portions of the trajectory. Owing to its analytical nature, the guidance law is computationally efficient, and its continuous thrust profile facilitates real-time implementation. The proposed method was evaluated over a grid of perturbed initial conditions in realistic simulations, demonstrating accurate collision-free soft-landing performance. The results highlight the importance of combining saturation-aware guidance with ground-collision avoidance under bounded thrust.

We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released checkpoint is trained on publicly available human-preference labels covering arena-style (A vs. B) votes, metric-alignment preference pairs, crowdsourced pairwise comparisons, and expert aesthetic ratings. The predicted score margin between two clips is well calibrated on our held-out test split, supporting data filtering via a simple score threshold. TuneJury generalizes to both held-out test pairs and out-of-distribution benchmarks, remaining competitive with prior baselines on the latter. For generators released after training, we introduce anchor calibration, a post-hoc, per-system Bradley-Terry calibration that recovers agreement at substantially better data efficiency than from-scratch retraining. The same frozen reward drives consistent reward-axis gains across three downstream applications: inference-time best-of-N selection, DITTO-style latent optimization, and expert-iteration post-training. TuneJury is available at https://github.com/yonghyunk1m/TuneJury.

Automated insulin delivery (AID) systems are often tuned for the population and offer limited online adaptation to the inter- and intrapatient variability in insulin needs caused by meal patterns, physical activity, and fluctuations in insulin sensitivity. We present a real-time, data-driven personalization approach that adapts controller parameters using the subject's daily glycemic data. The adaptation is formulated as projected gradient descent on a daily risk metric, where the gradient estimation is designed to attenuate noise and metabolic variability. We use contraction theory to validate the optimization framework and convergence of the closed-loop system under adaptation. In silico experiments on the 100-adult cohort of the FDA-accepted UVA/Padova T1D simulator show that our method improves glycemic risk and increases time-in-range (TIR, 70-180\,mg/dL) by 2%, 3%, and 4% after 4, 8, and 17 weeks, respectively, under variability in meal timing, meal size, and insulin sensitivity.

Firmware/software in cyber-physical system (CPS) embedded devices/controllers can have vulnerabilities stemming from multiple sources such as weak security practices, outdated libraries, or supply chain attacks that induce adversarial effects under plant state-based triggers. However, pre-deployment validation of CPS controllers typically relies on digital twins that model controller logic as a black box. On the other hand, side channel monitoring and anomaly detection of CPS controller firmware/software is complementary, but is typically exercised with synthetic inputs or under specific CPS operational profiles and does not simultaneously track software execution and CPS plant evolution. To bridge this gap, we present a closed-loop digital twin framework that hosts unmodified controller binaries in a Linux sandbox (SaMOSA) with its I/O rerouted to an external plant simulator. The framework captures four time-synchronized side channels (hardware performance counters, system calls, disk activity, network activity) alongside plant state and provides orchestration hooks for automated, repeatable, parameterized runs. We demonstrate the framework on an OpenPLC runtime controlling a Modbus-connected IEEE 14-bus power system, and also briefly discuss application to robotics systems. The synchronized traces correlate internal controller execution with plant events, providing an observability foundation for online testing, coverage analysis, and vulnerability detection.

State-space models (SSMs) are the standard formalism for Bayesian treatment of dynamical systems, with natural applications in statistics, signal processing, and machine learning. Despite their importance in both theory and application, dynamical systems have proven difficult to incorporate in modern probabilistic programming languages (PPLs), making state-of-the-art methods less accessible to practitioners and introducing friction in following the "Bayesian workflow." We introduce dynestyx, a probabilistic programming library with first-class support for SSMs, including state-of-the-art methods in the estimation of both states and parameters. Through a single, unified interface, users may specify arbitrary priors for discrete-time or continuous-time dynamical systems, perform inference over mixed-effect data, and make state and parameter estimates with principled uncertainty quantification.

For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information. Reinforcement learning's standard scalar reward carries far less information than the directional task error that defines the task. Random exploration further discards whatever information each rollout returns. Through residual learning with directional task-error supervision and a task error model that drives sample selection, we achieve stable three-, four-, and five-ball juggling on anthropomorphic Barrett WAM arms. Despite planning and controlling through a simple, idealized stack, the system converges from the second attempt. The first attempt drops, after which task error decreases monotonically without further failures. In comparison, five-ball juggling typically takes humans years of practice. We compare residual learners across two ternary axes, the directional information in the learning feedback and the commitment of the analytic prior, spanning Newton-style Jacobian updates, Composite Bayesian Optimization, and stochastic search methods. Both axes prove necessary for fast convergence: neither directional feedback nor an informative prior alone matches their combination, and the simplest method that combines them, a fixed-Jacobian Newton update, is the fastest and fully reliable. The learned residual tolerates substantial prior misalignment and degraded joint tracking, affecting mainly convergence speed. The bottleneck for residual learning on real robots is therefore the information content of the supervision signal and how the learner uses it, not the accuracy of the surrounding stack. Video documentation of all experiments is available at https://kai-ploeger.com/residual-juggling.

Robots operating in non-stationary environments must continually adapt their policies as the dynamics drift, but onboard energy and compute budgets cap how often a full state estimation and re-planning step can be performed. This raises a question: when, along a horizon, should a robot spend its limited budget? We formulate this problem in time-varying Markov decision processes (TVMDPs) with a known bound on the rate of transition drift. We model execution as a skip-update scheme in which, at chosen update times, the agent estimates the transition kernel by maximum likelihood and computes a finite-horizon policy, and between updates reuses this policy under a propagated state estimate. We analyze the dynamic regret of this scheme and show how it grows during skip intervals in terms of the properties of the TVMDP and the skip lengths; the resulting bound answers the opening question via an online, regret-guided update rule that allocates the budget adaptively. We evaluate the rule in a simulated Mars-rover navigation task with time-varying slip dynamics and on a Crazyflie quadrotor in indoor obstacle fields. Adaptive allocation outperforms other budgeted baselines.

Low frame rates in neural audio codecs are attractive for autoregressive speech synthesis, where the generation cost scales linearly with the sequence length. Recent work has demonstrated that codecs can operate at 12.5 Hz and below, but the mechanisms underlying low frame rate degradation remain insufficiently understood. We investigate these mechanisms through a controlled frame rate ablation. We reproduce a quality cliff at 6.25 Hz reported in previous works and evaluate candidate explanations: phonemic collisions and codebook saturation, neither of which shows evidence of a fundamental barrier. The cliff is instead caused by suboptimal training configuration: fixed clip duration during training yields too few tokens at low frame rates, starving the decoder of inter-token context. Once corrected, WER degrades smoothly with phonemic load down to 3.1 Hz and 1.6 Hz, suggesting the inference-time efficiency gains of low frame rate codecs are more accessible than previously assumed.

Woody breast (WB) is a myopathy in modern broiler chickens that causes the breast muscle to become unusually stiff and fibrous, leading to decreased meat quality and significant economic losses. State-of-the-art automated WB detection relies on a side-view imaging system to analyze the bending behavior of a single fillet as it falls off a conveyor belt. While highly accurate, this approach is constrained by its single-fillet field of view, creating throughput bottlenecks on commercial processing lines. In this paper, we address this limitation via a novel multi-fillet detection architecture utilizing a top-down camera configuration. To validate our approach, we first develop a high-fidelity digital twin of an industrial conveyor system. Next, we synthesize a diverse dataset of 3D fillet meshes and model their viscoelastic bending dynamics using a physics-based simulation engine. Lastly, a continuous 2D shape deformation score is extracted from the top-down perspective as the simulated fillets traverse the roller precipice. Experimental results demonstrate that the top-down shape score effectively captures the contour changes of the fillets as it bends, providing a robust and scalable alternative to a side-view imaging system for simultaneous multi-fillet WB evaluation.