Papers

Interactive driving, wherein an intelligent lead vehicle equipped with real-time traffic data coordinates route choices of connected vehicles, offers a promising approach to dynamic traffic management. To address the challenge of harmonising decisions, this paper considers the strategic information revealing framework of Bayesian persuasion. Here, the principal (lead vehicle) aims to guide the agent's (connected vehicle) partially observable sequential decision making towards its own objectives by selectively revealing information, such as real-time traffic ahead, using signals. However, the agent's farsighted response to maximize its long-term reward, renders the principal's signaling strategy design computationally challenging. We propose an online structured reinforcement learning framework to synthesize computationally efficient signaling strategy which is persuasive for a far-sighted agent. The main contributions of the paper are as follows: (i) For a monotonic agent with approximate best response, we propose MAPL, a structured policy learning algorithm for faster online learning, (ii) Identification of sufficient conditions for the supermodular structure of the Q function of the principal for a monotonic agent, (iii) Identification of sufficient conditions to ensure the persuasiveness of the principal's signaling strategy, (iv) Supermodular Q learning for Principal (SQP), which leverages the supermodular structure of principal's action value to synthesize computationally efficient signaling strategy that is persuasive for a monotonic learning agent, (v) Numerical analysis considering a real-time application of Bayesian persuasive driving for lane selection demonstrates that the proposed method is 30% cost efficient for optimising travelling rewards of both the lead and connected vehicle compared to the existing methodologies for signaling strategy design.

Sound event detection relies on frame-level strong labels whose annotation is expensive. Active learning addresses this problem by selecting the audio segments whose labels help the classifier most. One of the prevailing acquisition strategies for this task, mismatch-first farthest-traversal (MFFT), combines the disagreement between two classifiers and the diversity of the selected segments through hard sequential decisions. It selects whole groups of high-disagreement segments first and spreads only the remaining budget by farthest traversal. On two multi-label datasets we show that this design is blind to the similarity among the selected segments and fails under low budgets, with every mismatch-first variant ending below the plain geometric strategy it builds on. We propose mismatch-weighted facility location (MW-FL), which spends the entire budget through a disagreement-weighted coverage objective that penalizes similarity among the selected segments. The disagreement signal from MFFT is used to obtain the nonnegative weights of this facility-location objective, using fixed smoothing without dataset-specific tuning. Experiments across two geometric mechanisms with three ways of using disagreement show that coverage of the selected segments is the dominant factor, hard disagreement gating of selection is harmful on both mechanisms, and soft disagreement weighting helps on top of coverage. MW-FL attains the best area under the learning curve on both datasets.

Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert annotation and using the labeled segments for training the classifier. The setting is hard: the target calls are extremely sparse and the call-type distribution is long-tailed, so a tight budget must be spent on the few rare, informative segments. We propose BADGE-Greedy-DPP, a deterministic batch selector that greedily adds the segment whose BADGE gradient embedding most enlarges the volume spanned by the batch; because this log-volume objective is submodular, the greedy rule guarantees a batch value at least a (1-1/e) fraction of the optimum of this objective, a guarantee not provided by BADGE's existing k-means++ and MCMC DPP sampling heuristics. There is also a temporal granularity mismatch in the task. The acquisition function scores whole segments, yet the informative frames inside them are few. Uniform averaging therefore washes them out. The BADGE construction naturally addresses this mismatch when applied frame-wise, as prediction residuals weight the aggregated pseudo-gradient, so confidently predicted no-call frames contribute little while a single uncertain rare-call frame can still set the segment's direction. Across 10 runs on a sparse, imbalanced hyena call-type dataset, BADGE-Greedy-DPP achieves the best overall and rare-call-type performance among all compared query strategies, including MFFT, the strongest non-BADGE baseline, and the two vanilla BADGE traversals.

Autonomous robotic navigation in nonstationary time-varying fluid flows remains a fundamental challenge due to partial observability and the unpredictability of realistic environments. While classical optimal control frameworks employed in robotics require unrealistic a-priori global flow knowledge, biological systems are able to navigate successfully by exploiting localized sensory cues. In this work we present a reinforcement learning approach using the TD3 algorithm to train autonomous agents to reach arbitrary targets within a parametric, chaotic double-gyre flow. To investigate optimal sensory mechanisms, we evaluate five bio-inspired observation strategies based on relative position, local velocity or local vorticity measures, and short-term memory variants. Additionally, we analyze the impact of providing agents with explicit global flow parameters. Numerical results demonstrate that an agent that is able to sense and remember a set number of flow velocity measures achieves the highest performance. The experiments reveal a trade-off in sensor utility: velocity-aware agents optimize energy efficiency, whereas vorticity sensors provide superior structural mapping and achieve better target proximity. Incorporating explicit global flow parameters is shown to decrease navigation performance. This behavior suggests that reinforcement learning-based autonomous systems develop more robust and general policies when restricted to implicit flow representations. The presented results offer insights for improving the transition of bio-inspired robotic navigation from simulation to real-world environments.

Inverter-based resources and IEC 61850 process-bus measurements introduce new protection challenges, including nontraditional fault behavior and measurement-domain cyber-physical attacks. This paper evaluates DL-Xformer, an attention-based Transformer classifier for multi-class fault and cyberattack diagnosis, side-by-side with Dynamic State Estimation-Based Protection (DSE-EBP) on identical high-fidelity electromagnetic-transient (EMT) streaming measurements from an IBR-rich power grid. The evaluation uses an 18-class taxonomy covering normal operation, 11 physical faults, and six measurement-domain attacks, including CT/PT ratio manipulation and GPS spoofing, sampled at 4.8 kHz from synchronized upstream and downstream merging units. DSE-EBP detects all streaming anomalies in 0.417-1.660 ms, with a mean detection time of 0.756 ms, while DL-Xformer classifies the same events in 2.50-50.42 ms, with a mean classification time of 13.46 ms. The longest delay occurs in a deliberate stress case where a CT ratio attack is introduced while residual oscillations from a preceding DLG fault have not fully settled; the event-window accuracy drops to 76.1 %, but the stable final classification remains correct. Measurement-level feature attribution shows that the DL-Xformer decision is driven by physically meaningful current and voltage channels at the attacked measurement location. Together, the two methods motivate a layered protection architecture for next-generation inverter-dominated smart grids.

The terahertz (THz) band is a promising candidate for high-data-rate transmission in future wireless communication systems, where large-scale antenna arrays are deployed to combat the severe propagation loss. In such configurations, near-field and far-field multipath components (MPCs) coexist in the channel, which challenges conventional parameter estimation methods. This paper presents a 260–380 GHz virtual uniform linear array (ULA) measurement campaign in an indoor scenario, and proposes a hybrid-field space-alternating generalized expectation-maximization (SAGE) algorithm that discriminatively estimates near-field and far-field MPCs via a visible region (VR)-aided weighted wideband Bayesian phase-curvature classification, while tracking spatial birth-death phenomena through VR estimation. Simulations with known ground truth validate the effectiveness of the proposed classifier and the hybrid wavefront modeling. Measurement-based characterization reveals that near-field MPCs account for over 90% of total MPCs at a 2 m distance, the scatterer distances and invisible region lengths follow lognormal and exponential distributions, respectively, and spatial non-stationarity intensifies with increasing frequency and decreasing distance. These findings provide quantitative guidelines for THz channel modeling and system design.

We present Ripple, an open, AI-formalized Lean 4 framework for the mathematics of computing with chemical reaction networks (CRNs) – one extensible, machine-checked development that gathers several strands of the field into a single setting, and is built to grow. It formalizes: the theory of which real numbers a CRN can compute – a single Lean definition of real-time CRN computation, the class of reals it captures, and the compilation pipeline (a GPAC / polynomial-ODE layer, a dual-rail compiler, and four stages down to large-population protocols) that realizes them, built so that adding a new number is a plug-in; three landmark population-protocol majority algorithms – approximate, exact, and self-stabilizing exact majority; the stochastic-to-deterministic bridge, through three machine-checked versions of Kurtz's mean-field theorem; and two classical Turing-completeness results – Bournez–Graca–Pouly for the deterministic GPAC and Soloveichik–Cook–Winfree–Bruck for stochastic CRNs. Each of these is verified to depend on exactly the three Mathlib foundational axioms, with no sorry. Along the way the formalization repaired genuine, previously unnoticed gaps in published proofs – a compilation step that can transiently leave the unit interval, and an algebraic-number construction that silently rests on Catalan's conjecture – and surfaced a sharp open problem about when a holonomic series admits an exact, rational-data polynomial-ODE encoding. The whole development is open and every proof is kernel-checked, so the results can be independently re-verified; and because it was written predominantly by AI agents using only publicly available models, the workflow that produced it can be reproduced with the same public toolchain.

This paper studies learning-based model predictive control (MPC) for stabilizing unknown discrete-time linear systems with hard input constraints and additive unbounded sub-Gaussian disturbances. We adopt a certainty-equivalence (CE) design that combines a switching MPC control law with online regularized least-squares (RLS) parameter estimation. The resulting switching control law blends the MPC with a saturated deadbeat controller, ensuring global closed-loop stability. Building upon non-asymptotic error bound of least-squares, we derive non-asymptotic, high-probability stability bounds for the closed-loop system under the proposed switching controller. Numerical experiments illustrate and support the theoretical findings.

Pinching-antenna systems (PASS) are capable of dynamically reconfiguring wireless channels by flexibly repositioning pinching antennas (PAs) along the waveguides to establish short-range line-of-sight links. In this paper, a user-side navigation framework for PASS is proposed, where mobile users determine their own positions using only downlink broadcast signals without any prior knowledge of the PA positions. First, a Lambert W function-based PA positioning and pseudorange estimation (LWF-PAP) algorithm is developed, in which the closed-form expressions for both the PA positions along the waveguide and the PA-user pseudoranges are derived. Second, a weighted least squares-based PASS navigation (WLS-PAN) algorithm is formulated, where the nonlinear PASS-based navigation equations are transformed into a closed-form linear system, and the optimal weight matrix is derived, achieving minimum-variance unbiased estimation. Third, the PA-derived position dilution of precision (PA-PDOP) metric is further defined to characterize the theoretical accuracy bound. Simulation results demonstrate that centimeter-level positioning accuracy is achieved for both PAs and users within the breakpoint distance. It is also shown that uniform PA deployment and a moderate increase in the number of PAs effectively improve navigation accuracy, thereby validating the effectiveness and robustness of the proposed framework for distributed real-time user-side self-navigation.

Large audio-language models (LALMs) are increasingly used as automatic judges for speech evaluation. However, high agreement with human ratings does not guarantee that their verdicts are grounded in the audio. A judge may instead rely on specialist labels or reference data supplied by the evaluation protocol itself, taking a shortcut in place of listening to the audio. In this paper, we audit such protocol-level “shortcuts” in LALM judges across three common deployment protocols: feature-blueprint judging, where the audio is replaced by a structured text description of acoustic features, reference-conditioned judging, and pairwise A/B comparison. Across six judges and four attributes, we find that several LALMs rely on protocol-level shortcuts. For example, in feature-blueprint judging, incorrect specialist labels reduce five judges' emotion accuracy to 0.10 or below, and in concatenated A/B comparisons, Qwen3-Omni-Thinking often picks the same slot regardless of order swaps. These results indicate that aggregate agreement can overstate the validity of LALM judges unless the model and the evaluation protocol are assessed jointly, and that each model-protocol pair should be evaluated with a matched shortcut probe.

Music visualization offers a powerful way to enhance listeners' understanding and experience of music by translating auditory signals into visual forms. However, most existing approaches either rely heavily on lyrics or generate flat, non-immersive videos similar to conventional music videos, which limits their ability to convey the emotional dynamics of music and provide an immersive listening experience. We propose Bring Music The Horizon, an emotion-aware pipeline for music-driven 360$^\circ$ video generation. Given an input song, our work first estimates its emotional trajectory by predicting valence-arousal values at the level of every four bars. These values are then converted into emotion-aware visual guidance using EmotiCrafter, and these guidance vectors can be manipulated by the SEGA framework, which provides fine-grained semantic control for keyframe generation. Finally, image-to-video models are applied to the generated keyframes to synthesize temporally continuous 360$^\circ$ videos for immersive music visualization. Our pipeline generates 360$^\circ$ music visualization videos that reflect the emotional progression and temporal structure of the input song. We demonstrate its capability using songs from different genres and provide qualitative comparisons with From-Sound-To-Sight, a representative audio-to-visual generation baseline, on our project page at https://etoile-et-toi-mp3.github.io/BMTH_Project_Page/.

Energy efficiency will pose an essential limitation for sixth-generation (6G) integrated sensing and communication (ISAC) systems, given the high sensing power consumption associated with persistent sensing, despite stable communication requirements. This paper proposes an energy-efficient multiple-input multiple-output (MIMO) dual-functional radar-communication (DFRC) beamforming framework that minimizes transmit power while guaranteeing per-user signal-to-interference-plus-noise ratio (SINR) and reliable multi-target tracking. The key innovation is a tracking-aware, skip-enabled sensing policy that departs from the conventional always-on probing paradigm. Instead of enforcing sensing at every epoch, sensing is selectively triggered according to two complementary statistics derived from an extended Kalman filter (EKF): a posterior confidence metric and the normalized innovation squared (NIS). While the former ensures accurate estimation, the latter guarantees reliable measurements, and thus sensing can only be activated when additional information is required. To ensure robustness under intermittent sensing, sector-based beampattern constraints are combined with a nonzero safety illumination floor imposed to guarantee reliable target tracking when skipping occurs. Numerical results show that the proposed framework achieves a significant reduction in transmit power compared to other baselines, without any deterioration in the communication system's performance or excessive impact on the sensing process.

Automatic composite modulation recognition (ACMR) is critical for integrated sensing and communication (ISAC) systems, while conventional approaches face significant challenges due to the semantic coupling between inner-layer and outer-layer modulations in composite modulation (CM), degraded performance under joint hardware and channel imperfections, and limited capability to handle unknown modulation schemes. To this end, we design a disentangled semantic space and propose zero-shot learning framework. Within this framework, a logarithmic projection first linearizes the multiplicative coupling between modulation layers and a learnable geometric transformation is used for layer-wise semantic features. We instantiate the framework as the Tangent Space Disentanglement Network (TSDN). TSDN integrates logarithmic mapping, a spatial transformer network for learning the geometric transformation, and a multi-objective loss function that balances discrimination with cross-domain generalization. Comprehensive experiments demonstrate that TSDN achieves over 93% zero-shot recognition accuracy, outperforms unified-semantic and multi-task baselines by significant margins, and maintains robust performance under combined channel fading and hardware imperfections down to 4 dB SNR.

Unmanned aerial vehicle (UAV) environments present significant challenges for machine learning (ML) due to limited platform resources, heterogeneous sensor data, dynamic mission conditions, and safety-critical requirements. This paper examines these constraints across the core functional areas of UAV intelligence, including navigation, perception, communication-aware operation, and resilience specifically in the context of developing economies. In such settings, these challenges are often amplified by constraints such as cost sensitivity, limited infrastructure, intermittent connectivity, regulatory uncertainty, and harsh or variable operating environments. The discussion highlights the gap between ML performance in controlled experimental backgrounds and dependable deployment in real-world UAV missions within developing economies context.

Structural damage in modular spacecraft can disrupt mechanical and communication connectivity, reducing system capability. Existing approaches rely on redundancy or preplanned reconfiguration and do not enable autonomous repair under local information and physical constraints. We model the spacecraft as a lattice-constrained graph and introduce a fully decentralized, asynchronous stress-sharing repair policy inspired by biological wound healing: local distress signals guide surviving modules toward damaged regions to close fragmented gaps, after which each displaced module locally retraces its own motions to recover the pre-damage shape, using only local information and no absolute position sensing. We evaluate the policy in PyBullet rigid-body simulation across structures of up to 160 modules, three fault densities (10, 20, 30%), and random and localized damage. The policy consolidates the surviving modules into a single connected body: even in the most severe case tested, where 30% of modules fail at random, it gathers roughly 80% or more of the surviving modules into one connected component, and this fraction improves with assembly size, making the approach well suited as a swarm-scale repair policy for large modular spacecraft.

Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulation of an IL problem that optimizes performance under distributional uncertainty while systematically accounting for safety constraints. We demonstrate the effectiveness of the proposed approach on an unmanned aerial vehicle (UAV) case study where the UAV performs a task in an uncertain environment while avoiding unsafe regions.

This paper proposes a rigorous framework for sensing of environmental objects using diffraction mechanisms prevalent at wireless communication frequencies. Specifically, we develop a physics-consistent parameterized diffraction channel model, derive maximum likelihood (ML) approaches for estimating the blockage shape, range, and source directions of arrival (DoAs), and quantify fundamental performance limits via the Cramér–Rao bound (CRB). In our physics-based modeling, we integrate various approximations for the wave propagation (far-field, paraxial Fresnel, and exact near-field regimes), enabling a wide range of applicability. The underlying model is frequency-agnostic, and we derive Fresnel-number scaling laws that map the diffraction pattern, and hence the estimation problem, across carrier frequency, object size, and range. We quantify the maximum likelihood estimation performance and its relationship to the CRB, and we study the impact of the modeling approximations developed in this work. Numerical results demonstrate that ML estimators closely approach the CRB at moderate to high signal-to-noise ratio (SNR), and highlight the utility of diffraction-based modeling for high-fidelity blockage characterization.

Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing evaluation and training signals mainly emphasize global similarity or perceptual quality, with limited supervision on instruction-level correctness. We propose an instruction-level framework that uses audio-aware large language models (ALLMs) as fine-grained judges to verify target event presence and temporal relations in generated audio. After validating ALLM judgments on benchmarks and through human verification, we use their feedback to construct preference pairs for direct preference optimization. We further introduce S3Bench, a narrative benchmark for evaluating multi-event temporal instruction following. Experiments show that our method improves event completeness, temporal ordering, and joint instruction-following accuracy across existing benchmarks and S3Bench, while maintaining audio quality.

Reliable state estimation in dynamical systems is often challenged by model mismatches, unknown noise statistics, and temporal variations. While AI-aided Kalman filters such as KalmanNet leverage deep learning to enhance classical estimation, they remain vulnerable to distribution shifts and lack mechanisms for autonomous adaptation. This work introduces Change-Aware Self-Adaptive KalmanNet (CASA-KalmanNet), an online adaptation framework that integrates a dedicated neural module, termed CPDNet, to monitor the interpretable internal features of KalmanNet and provide soft indicators of reliability degradation. These indicators dynamically regulate an online learning process, enabling data-efficient and timely adaptation to both abrupt and gradual changes in the system without requiring additional state labels from the changed regime. Numerical experiments on linear and nonlinear state-space models show that CASA-KalmanNet consistently outperforms existing learning-based filters under model mismatch, while approaching the accuracy of optimal classical methods with full domain knowledge.

Reliable fault diagnosis of rotating machinery is essential for the safe and stable operation of industrial systems. Although deep learning methods perform well under closed-set conditions, real machinery may encounter previously unseen fault states. Existing open-set fault diagnosis (OSFD) methods remain limited in fine-grained severity diagnosis because they often rely on coarse type levels, heuristically selected Short-Time Fourier Transform (STFT) settings, and global class boundaries. We propose a fine-grained OSFD method that combines metric-guided data-centric (MGDC) STFT configuration selection with class-specific autoencoder (CSAE)-based anomaly rejection. MGDC screens candidate STFT configurations using the Silhouette score computed from spectrogram representations, identifying promising time-frequency representations before network training. The diagnostic model then uses a bank of CSAEs to learn compact class-specific manifolds for known degradation states. During inference, reconstruction-error-based class affinity identifies known classes, while a dual-criteria mechanism based on latent dimension-wise boundaries and class-specific reconstruction error rejects unknown samples. Experiments on the Case Western Reserve University (CWRU) and Paderborn University (PU) bearing datasets show that the proposed method achieves H-scores of 0.9924 and 0.9509 for fine-grained fault severity diagnosis. MGDC also identifies the best-performing configuration found by exhaustive search while evaluating only 9 of 38 candidates on CWRU and 2 of 39 candidates on PU, reducing the selection cost by factors of 5.69 and 29.87, respectively. These results indicate that the proposed method supports accurate open-set severity diagnosis with substantially lower configuration-selection cost.

The Griffin-Lim algorithm has been a seminal contribution for phase reconstruction from amplitude spectrograms, however, requiring (infinitely) high algorithmic delay. Its low-delay variant suffers in speech quality. Recent (generative) neural network methods improve on speech quality still at medium to high algorithmic delay, but often they are complex and optimized only for one specific input representation. We build upon an efficient low-delay speech vocoder and propose EffVOC, which supports synthesis of wideband (WB) or fullband (FB) speech from either amplitude spectrum or Mel coefficient inputs. We evaluate both input representations across multiple model sizes in a unified framework and compare against state of the art. Results show that our proposed low-delay (20 ms vs. 32 ms or more) efficient approach marks a new SOTA by achieving top-ranked subjective MOS scores (WB: 4.17/4.15, FB: 4.14/4.11) for amplitude spectrum/Mel representations, very close to ground truth.

Traditional controllers are designed for specific systems and do not transfer across different system orders and dynamics. We present a Generalist Controller, a learning-based controller capable of controlling systems of varying orders and dynamics. The approach introduces a novel dynamic state-space representation using attention mechanisms with masking, enabling a single neural network, trained in one shot, to handle systems with different dimensions without architectural modifications by assigning a system tag to each system. We generated 314,630 demonstrations from 25 diverse systems, including stable, unstable, minimum-phase, and non-minimum-phase dynamics, spanning linear and nonlinear systems from autonomous underwater and aerospace vehicles to mechanical systems and chemical processes. The model learns cross-system control strategies through multi-scale temporal processing and a mixture-of-experts architecture. Simulation results demonstrate that the proposed generalist controller achieves comparable performance to system-specific LQI controllers across all tested systems, including challenging cases such as non-minimum-phase and unstable dynamics, whilst generalising to unseen operating conditions including actuator saturation, noise, disturbance, and reference trajectories not encountered during training. This work represents a significant step towards generalist control policies within a defined family of dynamical systems, demonstrating effective control across a range of single-input single-output (SISO) systems of varying order and dynamics using a single learned policy without system-specific tuning.

Hybrid beamforming (HB) with quality-of-service (QoS) provisioning per stream in millimeter waves is indispensable in 5G/6G networks. HB includes baseband and radio frequency (RF) beamforming, and requires error-free channel state information (CSI), which is erroneous in practice. So there is a need for efficient, feasible, robust, and QoS-aware HB. To achieve this, we mitigate CSI uncertainty via baseband beamforming, and we steer the RF beamformer by using the estimates of the channel's eigenvectors. In doing so, we consider the effective channel's uncertainty region instead of the uncertainty region of the channel itself, as the former is smaller than the latter, requiring less transmit power to satisfy the QoS constraint. We also detect and eliminate the infeasible data streams. Our iterative scheme (which is based on the cutting-set method) for baseband beamforming satisfies the mean-squared error (MSE) constraint per stream, where a limited number of constraints are considered instead of infinitely many constraints. In our low-complexity scheme, we derive a simple sufficient condition to check the feasibility of each stream, we diagonalize the effective channel at the baseband precoder, and we use minimum MSE combining at the baseband combiner. Extensive simulations validate our formulations and theoretical derivations.

Retrieval over corpora that mix several domains often returns relevant but wrong-domain evidence that ranking metrics miss and that conformal risk control bounds only marginally, under-covering the worst domains. This work introduces C3R, a drop-in control layer that, from an inferred domain posterior and no query-time label, certifies a per-domain contamination budget where feasible and otherwise abstains rather than silently violating; on the hardest domains it guarantees a reduction, not a tight bound. The core is a two-split scheme built on risk-controlling prediction sets, whose finite-sample transfer bound crosses from the inferred to the true domain with fully estimable slack, supports heterogeneous budgets, and inverts for deployment. Population validity rests on this bound and a controlled simulation; across a thousand resampled calibrations the certificate never violates (a stability result) while marginal control violates the most-contaminated domain in every draw, and soft demotion retains more recall than the strongest calibrated cascade at equal certified contamination. The method replicates across open testbeds including an independent one from public federal regulations, and an LLM-judged downstream probe indicates wrong-authority grounding rises with contamination and falls under control. The layer is frozen-stack and reranker-agnostic.

Graph signal processing built on the eigenvectors of a Laplacian or adjacency shift inherits three structural compromises: the eigenbasis is fixed only up to rotation within degenerate eigenspaces, the shift is not an isometry, and there is no genuine translation under which filtering is a true convolution. We develop an alternative harmonic analysis that removes all three at once. Given an isometric embedding of a connected graph into a Cayley graph of a finite abelian group, a host on which classical Fourier analysis applies exactly, we define a group-embedding graph Fourier transform from the host characters, lift graph signals to the host, and process them there. The characters supply a canonical orthonormal Fourier basis; the group translations form a family of unitary permutation operators obeying an exact group law; and filtering is genuine group convolution, for which the convolution theorem holds as a theorem rather than a definition and which possesses an identity element. We prove the Plancherel, convolution, translation-covariance, and sampling identities in the embedded setting, and compare the shift and convolution operators of the two frameworks side by side. Numerically, the structural identities hold to machine precision; under a same-filter protocol the groupcharacter basis denoises equivalently to the Laplacian eigenbasis once the host complement is filled by a smoothness-respecting extension. The contribution is exact, canonical structure, not a denoising advantage.

Diffusion-based text-to-audio generative models such as AudioLDM achieve high perceptual quality and strong semantic consistency; however, their practical deployment is hindered by the substantial computational cost of the U-Net denoising backbone. In this work, we apply model pruning to improve the computational efficiency of AudioLDM, a U-Net-based text-conditioned audio latent diffusion model. We analyse parameter redundancy across U-Net convolutional blocks and evaluate a filter-pruning strategy. Pruning is guided by norm-based criteria and followed by lightweight finetuning to recover performance losses. Experimental results demonstrate that up to 83% of the parameters and 39% of the multiply-accumulate operations of U-Net have been reduced while maintaining, and in some cases improving, generation quality compared to the baseline unpruned network. We find that pruning affects AudioLDM's ability to generate certain sound events including safety-critical sounds such as gunshots, sirens, and explosions, as well as mechanical sounds such as drills and sewing machines, and other sounds such as sprays and tick-tocks, which are mostly recovered by lightweight finetuning of the pruned model.

Safety critical autonomous systems often adapt by adjusting controller parameters while keeping the underlying architecture fixed. This strategy breaks down when shifts in sensing, resource availability, or component health invalidate the original structural assumptions. This work introduces a method in which system maintain an explicit, graph-based representation of their architecture and reason over it during operation. The system is modeled as a directed graph of physical, functional, and model based modules, with edges capturing information and control dependencies. Adaptation is posed as a joint optimization over architectural configurations and module parameters, subject to operational constraints using a Monitor-Analyze-Plan-Execute loop-based finite state machine. Performance degradation is isolated via residual decomposition and dependency weighted influence propagation, and candidate adaptations are filtered using a stability aware mechanism. The approach is demonstrated on a differential drive robot under sensor drift and actuator faults. A fixed architecture accumulates tracking errors of up to 24 m and 13 m, respectively, whereas architecture aware adaptation reduces error under 1.5 m in each case, by selecting fault appropriate configurations. These results show the value of reasoning over system structure, while preserving stability, rather than relying solely on parameter tuning.

Real-time N-1 contingency screening in an energy management system trades assurance against cost: verifying every credible outage with full power flow is too slow, while fast linear-sensitivity screening gives no statistical guarantee and can silently pass unsafe operating points, especially when a controller drives the system into unfamiliar regimes. This paper introduces Audited Selective Verification, a risk-budgeted screening and triage layer for any controller's output (optimization, model-predictive, or learned). A cheap surrogate proposes which outages to skip; an online audit runs full power flow on a small random sample each window; and a calibrated threshold certifies a thermal-violation-rate bound for the skipped set at a chosen budget and confidence, with a corresponding bound for the unverified trusted subset. Validity rests on real verification and the audit rather than on surrogate accuracy, so it holds under arbitrary deployment shift. It is a risk-budgeted screen, not a replacement for deterministic verification when policy requires checking every credible contingency. On three public transmission systems up to 1354 buses, the realized violation rate stays within budget, standard deterministic and calibrated screens become unsafe under shift, and the method cuts full power-flow studies by 29 to 75 percent per real-time operating point.

Medical imaging systems such as CT, MRI, PET, and SPECT do not directly acquire images. Instead, they measure physical signals that encode anatomical or physiological information, and image reconstruction recovers the underlying image by solving an inverse problem. Although these imaging modalities are governed by different imaging physics, they share a common computational framework that naturally connects medical physics, linear algebra, probability, numerical optimization, and efficient computing. As medical imaging systems acquire increasingly large and higher-dimensional datasets, image reconstruction has become one of the primary computational bottlenecks in modern medical imaging. Advanced reconstruction methods, including analytical reconstruction, iterative optimization, and statistical model-based reconstruction, substantially improve image quality while reducing radiation dose or scan time, but at significantly increased computational cost. Efficient computing has therefore become essential for achieving clinically practical reconstruction times. This chapter presents a unified computational perspective on medical image acquisition and reconstruction across CT, MRI, PET, and SPECT. It first reviews the imaging physics and data acquisition process for each modality and derives a generalized mathematical framework for image reconstruction. Building on this framework, the chapter discusses analytical, iterative, and statistical reconstruction methods together with their computational characteristics. Finally, it examines efficient computing considerations, including optimization algorithms, physics-aware forward operators, memory-efficient implementations, and parallel computing strategies. Together, these topics demonstrate how the integration of imaging physics, mathematical modeling, and efficient computing enables accurate and scalable medical image reconstruction.

Active beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) enables hybrid transmitting and reflecting mode to achieve effective signal amplification and full-space coverage, thus providing a promising solution for blockage-aware uplink offloading in heterogeneous mobile edge computing (MEC) systems. However, practical hybrid mode active BD-RIS are realized by reciprocal devices, which inherently generate cross-sector energy leakage that will reshape the system-level energy-latency tradeoff. This paper studies energy-aware offloading and resource allocation for reciprocal active BD-RIS-assisted heterogeneous MEC, where offloading decisions, CPU/GPU computation allocation, transmit powers, receive processing, and active BD-RIS are tightly coupled. The resulting problem is a high-dimensional mixed integer nonconvex problem and is difficult to solve efficiently by conventional per-instance optimization. To address this challenge, we develop an end-to-end joint optimization framework based on a refined version of the distributional soft actor–critic algorithm, named as DSAC-T. By modeling return distributions rather than only expected values, DSAC-T improves policy stability under reward heterogeneity and feasibility-boundary sensitivity. Compared with other baseline algorithms, DSAC-T achieves the best energy-latency reward, the highest feasibility ratio of 81.67%, and a fast online decision time of 0.0267 s per scenario.