Papers

This paper proposes novel differentiable and severity-invariant (DSI) discrete token approaches that are not only tightly integrated with downstream dysarthric speech recognition tasks, but also minimise discrete token diversity across speech impairment severity groups. Experiments conducted on the UASpeech and TORGO corpora suggest that Conformer models trained using the DSI tokens outperform the comparable baseline HuBERT discrete/continuous features by statistically significant WER reductions of 2.22%/0.78% absolute (9.14%/3.41% relative) and 1.78%/1.06% absolute (18.43%/11.86% relative) on the two tasks, respectively. After system combination, the lowest WERs of 18.90% and 6.38% were obtained on UASpeech and TORGO. Phoneme-specific T-SNE visualizations show that severity-invariant regularization reduces severity-dependent variation by producing greater overlap and less distinct boundaries among severity-group distributions.

This paper proposes a movable waveguide (MW)-enabled pinching-antenna system (PASS), in which each waveguide is connected via a flexible cable and can be linearly moved by drivers. By simultaneously moving the MWs and the pinching antennas (PAs) on them, MW-enabled PASS can effectively track user locations and form flexible array geometries for efficient beamforming. We first examine the special case with a single user and derive the closed-form solutions for the optimal MW positions as well as an upper bound on the user rate. Furthermore, we develop a two-step optimization algorithm to maximize the achievable rate for the user, where the first step determines the optimal MW positions using the derived closed-form solutions, and the second step alternately optimizes the PA positions through a one-dimensional (1D) local search based on the user location. Then, for the general multi-user scenario, we derive the upper bounds on the minimum rate among all users. To maximize their minimum rate, we propose a low-complexity two-scale optimization algorithm, where the large-scale global search coarsely determines the MW and PA positions, followed by a small-scale local search to finely tune them. In addition, a two-timescale optimization scheme based on statistical channel information is investigated to reduce the mechanical movement overhead of the MWs. Simulation results demonstrate that the proposed scheme achieves performance close to the derived bounds. It also flexibly adapts to different user distributions compared with the conventional PASS employing dense or sparse fixed-position waveguides (FPWs), as well as fixed-position antenna (FPA) schemes.

Reconfigurable battery systems (RBS) synthesize the converter output voltage by inserting and bypassing battery cell groups, so every switching state changes not only the source voltage but also the source impedance. This paper shows that this configuration-dependent impedance breaks a tacit assumption of optimized pulse patterns (OPP): patterns designed with the customary linear plant model overestimate their achievable current quality by up to an order of magnitude and converge to a distortion floor set by the resistance modulation. We propose impedance-aware optimized pulse patterns (IA-OPP), which embed the level-dependent source impedance in the optimization objective, combined with an event-budget formulation that treats the reconfiguration rate of the communication bus as a managed resource. An exact closed-form evaluation of the piecewise-exponential load current renders the objective smooth in the switching instants. In a simulated cascaded-bridge reference system, IA-OPP attains 0.52% current total harmonic distortion (THD) at a reconfiguration rate of 2.4 kHz, outperforming nearest-level modulation, phase-shifted carrier pulse-width modulation (PWM) at up to five times the switching rate, and a classical OPP baseline at every event budget; the advantage persists across the modulation-index range and under +/-30% parameter mismatch. For three-wire star-connected systems, masking triplen orders in the objective restores the full advantage, with the impedance-aware patterns beating their linear-model counterparts by about 20% at equal budget.

The growing integration of converter interfaced renewable energy resources (RESs) intensifies stability challenges. Energy storage system (ESS) can provide fast and flexible frequency support to mitigate frequency deviations. However, the interface converter of ESS may encounter converter-grid interaction stability issues. This paper proposes a converter-grid interaction stability guaranteed safe DRL (CIS-DRL) method for ESS integrated power systems to achieve frequency regulation. We first obtain a double DNN-based stability region to identify the guaranteed converter-grid interaction stability. Next, a novel converter-grid interaction stability Safe-TD3 (CIS-STD3) algorithm is designed that integrates a stability feasibility projection layer to map unsafe actions into stable action set before execution, enforcing converter-grid interaction stability as a hard constraint throughout learning process. The proposed approach enables ESS for grid frequency support with 100% converter-grid interaction stability without violations. Experimental results show that the proposed CIS-DRL method achieves improved frequency regulation performance while preventing unstable operating points, demonstrating its practical applicability for real time ESS frequency support.

Periodic disturbances can produce ambiguous delay estimates, limiting reliable high-precision localization in distributed optical-fiber sensing. We develop spectral delay fusion for a sensing system using a dual-wavelength bidirectional Mach-Zehnder interferometer, with four phase traces recovered by heterodyne detection and digital demodulation. With calibrated propagation parameters and timing offsets fixed, the six pairwise delay predictions form a one-dimensional affine line segment parameterized by the position of a single dominant disturbance, with sensitivities determined by propagation direction and chromatic dispersion. A generalized least-squares estimator combines unwrapped delays from robust cross-spectral phase slopes with wrapped delays from polarity-invariant phase alignment to jointly estimate position and integer ambiguities under the proposed model, using an effective joint covariance to account for shared-channel and cross-representation dependence. Experiments use a 131.335-km sensing fiber at 1530 and 1550 nm, with periodic phase perturbations applied at five nominal positions from 25 to 125 km. Across the reported groups of 20 records, the proposed method yields sample standard deviations of 1.007-1.685 m at a drive voltage of 500 mV and 0.449-1.324 m at 1 V. The ratio of the smallest single-pair sample standard deviation to that of the proposed method ranges from 2.57 to 19.56 at 500 mV and from 2.12 to 2900 at 1 V. The upper ratio reflects unstable single-pair phase-slope delay estimates for periodic disturbances in the 1-V, nominal 50-km group, where the proposed covariance-weighted fusion maintains meter-scale localization repeatability.

Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectures about why the L1 loss outperforms L2 here. First, the hypothesis that the L1 loss confers robustness via parameter sparsity confuses the loss with Lasso regularization: an explicit Lasso penalty produces the predicted sparsity yet fails to reproduce L1's cross-noise behavior, while L1- and L2-trained weight distributions are indistinguishable. Second, the population optima of the two losses coincide exactly for symmetric signal posteriors and nearly so for concentrated ones. Measured differences are therefore dominated by optimization dynamics (bounded-influence gradients), which we probe with gradient statistics and contaminated-target training. On Kodak24 with five synthetic noise families, the L1 loss holds a statistically significant edge over L2, below 1 dB PSNR, holding across three seeds on 13 of the 14 noise columns. On real camera noise the loss is not the decisive variable in distribution: on official SIDD validation blocks, synthetic-Gaussian-trained N2N models gain only 0.8 to 3.7 dB over the noisy input regardless of loss, while retraining on SIDD's own noisy pairs, never reading ground truth, gains 9.4 to 11.0 dB, far ahead of BM3D. All metrics are on raw network outputs, and the study makes no leaderboard claim. The training pair distribution, not the loss, carries the inductive bias. That design rule applies wherever clean references are unobtainable, from microscopy to industrial inspection sensors.

Post-disaster phasor measurement unit (PMU) outages reduce power-system observability and degrade operator situational awareness, requiring sequential restoration under limited resources. Existing PMU restoration methods based on optimization or heuristics can generate restoration schedules, but they often provide limited support for explanation, traceability, and operator interaction. This paper proposes an agentic tool-calling framework orchestrated by a large language model (LLM) for post-disaster PMU restoration and grid observability recovery. In this framework, the LLM does not directly solve the restoration optimization problem; instead, it coordinates validated backend tools required for post-disaster restoration, including observability assessment, restoration planning, state updates, and operator verification. The framework also maintains a structured tool-call history and execution context that keep restoration decisions traceable and explainable, while enabling context-aware operator question answering during the restoration process. Simulation results on IEEE 30-bus and IEEE 57-bus systems show that the proposed framework achieves observability recovery comparable to a mixed-integer linear programming (MILP) solution, while providing tool-grounded explanations, interactive operator support, and human-overseen execution.

The integration of renewable energy sources into the electrical grid introduces complex challenges in fault detection and coordination of grid recovery mechanisms. Traditional relay protection systems, which operate based on static rules and predefined thresholds, are inadequate for addressing these challenges, particularly in detecting and isolating faults such as short circuits. Consequently, the conventional methodologies applied to electrical network protection frequently fail to achieve optimal performance in fault detection, especially in terms of adherence to safety standards and the selective limitation of damage. Recent research indicates that machine learning (ML)-based approaches can effectively tackle these issues; however, variations in grid configurations and analysis windows have impeded consistent comparative assessments. In this study, we assess the efficacy of various ML models in detecting electrical faults and pinpointing defective transmission lines within a 10 ms measurement interval - a critical time-frame for real-time operational viability, for the first time. The most effective model attained an F1 score of 0.991 +/- 0.018 and demonstrated a processing time of 0.342ms +/- 0.509ms.

Power Flow (PF), Optimal Power Flow (OPF), and State Estimation (SE) are fundamental problems in power system analysis, but solving them is computationally expensive. Graph Neural Networks (GNNs) have been proposed as fast surrogates, yet existing solvers are trained for a single problem at a time, producing narrow models that must be rebuilt for each new task. We propose a more general approach: a single Heterogeneous Residual Gated Graph Convolutional Network that solves all three problems with one shared backbone. Rather than learning one mapping, the model learns a reusable representation of how the network behaves, from which PF, OPF, and SE can each be estimated. Trained jointly on the three problems across diverse topologies and loading conditions, and evaluated on the IEEE 14-bus and 118-bus systems, the shared model matches the accuracy of task-specific GNN solvers and stays robust on unseen loading levels and topologies. These results show that a single model can capture the basic operation of a power network and serve several analysis tasks at once, a first step toward a foundation model for power systems.

Practical orthogonal frequency division multiplexing (OFDM) communication frames contain both deterministic pilots and random data payloads, motivating the joint ambiguity function (AF) analysis of the two components when the entire frame is reused for integrated sensing and communication (ISAC). This paper characterizes two discrete AF formulations for different Doppler regimes, namely the discrete periodic AF (DP-AF) and fast-slow-time AF (FST-AF), and derives closed-form expressions for their expected squared values. For the FST-AF, the expected sidelobe level (ESL) is uniform over the delay-Doppler plane and depends only on the pilot count, constellation kurtosis and total number of time-frequency resources, but not on the pilot symbols or pattern. For the DP-AF, we establish attainable lower and upper ESL bounds and show that no pilot design can minimize all sidelobes simultaneously. We further prove that attaining the lower bound at non-zero Doppler requires a periodic pilot pattern, while equally spaced chirp pilots, including Zadoff-Chu (ZC) sequences, maximize the numbers of sidelobes attaining the lower and upper bounds simultaneously. Two representative ZC pilot patterns widely encountered in communication frames are then examined: contiguous placement produces delay-Doppler ridges described by squared Dirichlet kernels, whereas equally spaced placement generates periodic peak-and-notch structures. Both regular patterns exhibit pronounced high sidelobes, suggesting that communication-oriented pilot patterns should be re-designed for delay-Doppler estimation in the context of ISAC. Numerical results validate the analysis and show that irregular pilot placement can suppress high sidelobes and improve target estimation performance.

In ischemic stroke, changes in cerebral hemodynamics during both the ischemic and reperfusion phases strongly influence stroke outcomes. However, these hemodynamic changes remain incompletely understood. To address this challenge, we devised an imaging platform that enables time-resolved ultrasound microvascular imaging during the experimental induction of ischemia and reperfusion in a mouse model. The platform leverages our previous ultrasound imaging framework combined with continuous mechanical scanning, which acquires whole-brain blood-flow signals within 5 s. The experiments demonstrated that the proposed platform can visualize both local and whole-brain hemodynamic responses to the induction of ischemia and reperfusion, suggesting its potential for rapid and continuous whole-brain hemodynamic assessment in small-animal models.

Electrocardiogram (ECG) signals are essential for arrhythmia diagnosis. With the growing adoption of long-term monitoring via wearable and portable devices, energy-efficient acquisition has become critical, motivating the development of ECG super-resolution (SR) techniques to reconstruct high-resolution signals from low-sampling-rate inputs. While recent SR methods based on discriminative neural networks have shown strong performance, their robustness under distribution shift remains uncertain, which poses a key challenge for real-world deployment. In this study, we propose DiSR-ECG, a residual shifting conditional diffusion framework for robust ECG SR. The model integrates residual shifting with Mamba-based temporal modeling and conditional guidance to enable accurate multi-lead reconstruction. Experiments on two large-scale ECG databases, PTB-XL for in-domain evaluation and Chapman Shaoxing for cross-dataset evaluation, demonstrate that DiSR ECG achieves state-of-the-art performance in both settings, with particularly strong generalization under distribution shift. These results highlight the potential of DiSR-ECG to provide reliable and clinically applicable ECG reconstruction for real-world monitoring.

3GPP TR 38.901 Rel-19 introduces antenna-element-level spherical-wave modeling, while NR Type-I and enhanced Type-II (eType-II) CSI codebooks continue to use plane-wave DFT beams. Whether this mismatch materially degrades finite-feedback multilayer precoding in standardized multipath channels remains unclear. To isolate its impact, we evaluate both codebooks over strictly paired far-field (FF) and near-field (NF) 3GPP channels that share user locations, multipath parameters, polarization, and link budgets and differ only in their wavefront models. Simulations cover Rank 1-4 transmission in 7-GHz UMi and 24-GHz InH-linear scenarios. We find no systematic FF/NF shift in singular-mode gains or equal-power SVD (SVD-EP) rates. Instead, spherical-wave phases reorder multipath projections onto plane-wave candidates and thereby alter codeword selection. For Rank-4 InH-linear users at 0.1 normalized Rayleigh distance, given FF-selected Type-I and eType-II codewords incur median direct mismatch losses of 2.28% and 5.34% on the NF channel, respectively; codebook reselection identifies better-matched codewords and reduces these losses to 0.770% and 3.28%. Nested candidate-set comparisons further show that relaxing Type-I interlayer constraints improves the SVD-EP-normalized rate by 20.7 percentage points, whereas finite-range sampling adds only 0.579 points. These results support prioritizing multilayer multibeam representation in large-aperture NR CSI codebooks, with range states providing complementary refinement.

Modern networked control systems (NCSs), cyber-physical systems (CPSs), and complex multi-agent network systems (CNSs) increasingly rely on large language models (LLMs) for high-level decision-making. However, the slow, stochastic nature of LLMs directly conflicts with the strict stability and safety guarantees required by these physical systems. This survey presents a unified analysis of how LLMs can be admitted into the control loop of NCS, CPS, and CNS without compromising closed-loop guarantees. We organize this around a core principle: the LLM operates as a slow supervisor adjusting high-level goals and constraints, while a fast, certified inner loop maintains physical stability. Under this framework, LLM integration maps directly to classical networked control challenges, where inference latency acts as delay, API failures as packet dropouts, tokenization as quantization, and hallucinations as bounded disturbances. We assess current developments across all these three domains, highlighting that rising model capabilities are frequently accompanied by a drop in formal safety assurances. Finally, we propose concrete future research directions, identifying the widespread lack of formal stability proofs as the field's central open problem.

This paper proposes an environment-aware diffusion based channel estimation in massive multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. The high dimensionality of massive MIMO channels combined with limited pilot resources makes accurate estimation challenging. To address this issue, we exploit the spatial variability of wireless channels by training a diffusion model to learn the location-conditioned distribution of channel state information, which provides an environment-aware prior for channel estimation. Based on this learned prior, a posterior inference algorithm is developed to incorporate pilot observations into the reverse diffusion process, enabling Bayesian channel estimation by combining the received-signal likelihood with the learned channel prior. By jointly leveraging location information and measurement data, the proposed approach improves estimation accuracy under limited pilot resources. Simulation results based on ray-tracing channel datasets demonstrate that the proposed method consistently outperforms conventional estimators and existing learning-based approaches across various signal-to-noise ratios and pilot configurations.

Age of information (AoI) has become a standard design objective for timely monitoring as it measures the freshness of the latest update at a receiver. AoI alone, however, is insufficient in goal-oriented applications where decisions depend on consecutive observations. Age dispersion complements AoI by measuring the generation-time separation between consecutive updates. In this paper, we study joint freshness and dispersion control for a generate-at-will status update link modeled as a finite-state Markov wireless channel. The objective is to minimize the long-run probability that either AoI or age dispersion exceeds a prescribed threshold under an average transmission rate constraint. For channel-dependent randomized transmission policies, we derive exact matrix expressions for the stationary joint distribution of AoI and dispersion. For reversible channels, mean dispersion is lower bounded by the reciprocal of the delivery throughput, and the difference is an explicit non-negative variance term for which we establish the exact equality condition. We then formulate the adaptive joint-threshold control problem as a constrained Markov decision process and prove that it admits an exact finite-state representation whose size scales linearly with the number of channel states and the threshold levels. Simulation results show that the controller reduces joint threshold violations by 37.3% relative to adaptive AoI-only control under the same transmission budget, while increasing mean AoI by 8.3%.

Extremum seeking (ES) is a real-time optimization strategy, thus transmission delays in the feedback loop of ES have big impact on its stability. How big delay that ES control systems are able to withstand? This paper provides a potential answer to this problem. We focus on gradient-based ES for nonlinear static maps subject to known constant delays plus a small time-varying delay uncertainty. We also consider the measurement to be subject to a small disturbance. Different from a majority of existing literature addressing quadratic maps with delays by predictor feedback, this paper deals with a wider class of non-quadratic maps without any predictor or observer for delay compensation. Dither signals in modulation and demodulation are carefully designed to handle constant delays and time-varying delay uncertainties. When the nonlinear map is unknown, we offer a rigorously analytical framework of ES convergence and delay-robustness. When some a prior knowledge of nonlinear maps is available, we are able to provide a quantitative estimation on upper bounds of time delay and dither periods to keep ES systems to remain stable. A suitable choice of ES parameters guarantees practical stability for any large known constant delay.

Speech synthesis systems are commonly narrated as a sequence of larger models, better tokenizers, and broader data. This technical retrospective offers a different account of the CosyVoice lineage, from CosyVoice through CosyVoice 2 and CosyVoice 3 to Qwen-Audio-3.0-TTS: progress came from repeatedly relocating the system's dominant bottleneck. Across the lineage, a stable decomposition separates an autoregressive language model that plans speech from a flow-matching model that renders acoustics. What changes is the contract between them. CosyVoice establishes supervised semantic tokens as a content-aligned interface; CosyVoice 2 makes that interface causally available for streaming and removes the utterance-level speaker embedding from the language model; CosyVoice 3 improves the learnability and coverage of the interface through multitask supervision, scaling, and differentiable reward optimization; and Qwen-Audio-3.0-TTS reduces token rate, conditions its renderer on continuous language-model hidden states instead of token embeddings, and progressively aligns the coupled system. We formalize this history through four interface dimensions—representation, ownership, availability, and gradient reach—and separate within-paper evidence from cross-paper comparison. The resulting synthesis connects discrete autoregressive, continuous non-autoregressive, hybrid, and continuous autoregressive speech-generation paradigms, and yields practical principles for diagnosing and training modular speech generators.

Locational marginal emissions (LMEs) give the sensitivity of total operating carbon emissions to nodal power demand. We show that this vector with $n$ entries has a much smaller intrinsic dimension under DC optimal power flow. Within a fixed active constraint set, the LME vector lies in the span of the uniform vector and the power transfer distribution factor rows of the binding lines. Its rank $r$ is therefore at most one more than the number of binding/congested lines. This structure makes $r$ independent scalar observations necessary and sufficient for exact recovery. Across ten systems with nonzero operating emissions, from 14 to 1,354 buses, $r$ ranges from 2 to 15. For instance, on a 300 bus system, 24 dispatch simulations recover all 300 LMEs. We also derive an emissions exceedance bound under uncertain demand. The bound separates variation while the nominal active set remains unchanged, the probability of an active set change, and estimation error. Numerical results show that its usable forecast error range depends on local active set geometry.

Audio moment retrieval (AMR) identifies temporal segments in long recordings that best match a free-form text query. Existing systems largely rely on fixed-slot DETR decoders that assign proposal-level confidence scores without explicitly normalizing over competing explanations of the full timeline. We propose segmental posterior decoding, which defines a globally normalized distribution over temporal segmentations and scores each candidate moment by its exact segment marginal posterior computed through forward-backward inference. We further expand the training segmentation space by treating a foreground span and its adjacent subdivisions as distinct hypotheses, thereby increasing competition among alternative segmentations. On CASTELLA, our method achieves 41.15% R1@0.7 and 34.68% mAP, outperforming the same network decoded with DETR slot confidence by 10.91 and 9.20 percentage points, respectively.

Warped Gaussian processes (GPs) handle non-Gaussian observations by mapping them into a latent standard GP via a parametric transformation called warping. Existing streaming variants, however, either optimize the warping parameters periodically or sacrifice analytical tractability for a higher model capacity. To bridge this gap, we show that the gradient of the instantaneous negative log-likelihood of a warped GP admits an exact recursive computation. Based on this result, we propose a novel online method for warped GPs that jointly updates the latent GP moments and optimizes the warping parameters.

Audio deepfake detectors need to transfer to languages absent from training, as multilingual speech synthesis outpaces labeled anti-spoofing resources. While detectors increasingly rely on self-supervised speech models (S3Ms), these backbones encode language-dependent structure that confounds spoof cues. We address this confound through language orthogonalization, a target-free ridge map that removes S3M variation projected onto continuous language-identification (LID) embeddings. Across six languages, six S3M backbones, and all Leave-N-Out settings, it consistently reduces EER across unseen languages. Cross-lingual EER correlates with LID-space distance, where orthogonalization yields larger gains for more distant transfers.

We solve the four-dimensional Hamilton-Jacobi-Bellman (HJB) equation for two diffusively coupled Stuart-Landau-like oscillators to obtain full-state optimal feedback control. A sweep over coupling strength reveals a sharp change in the numerically optimal strategy: below a threshold coupling value, the controller steers the phase difference toward anti-phase while keeping both oscillators near the limit cycle, as reduced-order models would suggest. Above this threshold, the HJB solution changes qualitatively; the controller transiently collapses one oscillator's amplitude to near zero, thereby enabling large phase repositioning near the origin before rebuilding its amplitude. Direct gradient-based and stochastic optimization do not recover this lower-cost collapse trajectory from the initializations considered, suggesting that it occupies a region of the control landscape that is difficult to access by direct search. A joint sweep over nonisochronicity and coupling shows that collapse can occur even for an isochronous oscillator: phase repositioning near the origin can favor an off-cycle strategy. Nonisochronicity provides an additional energetic benefit through a phase-velocity surplus at small amplitude, quantitatively accounting for the observed reduction in control cost. Comparisons with uncoupled and coupled phase-reduced baselines show that phase models become increasingly inaccurate and cost significantly more energy for strong coupling. Results for coupled Van der Pol oscillators further demonstrate that exploitation of off-cycle dynamics is not specific to the Stuart-Landau-like oscillators.

Video capsule endoscopy offers a non-invasive way to examine the small bowel, however, the rare but clinically important findings that appear only in less than 1% of labelled frames, provide very less signal for detection. As a result, while models can achieve high overall performance, they almost completely miss these rare findings. We condition each frame's decision on evidence from the rest of that patient's video, not on the frame's own posterior alone, supplying information a single frozen frame can never contain. Building upon Expected Gain Arbitration, a per-frame, macro-F1-optimal correction over the confusion matrix, we further compose it with video-disease-presence conditional resulting in our decoding method Hierarchical Conditional-Expected-gain (HCE). We evaluate HCE on two independent VCE datasets, Kvasir-Capsule and GALAR, against a static temporal-smoothing baseline and an optimal-transport (OT) frame-level correction. HCE significantly improves rare-class recall over a temporal-smoothing baseline on GALAR (2.7–3.1x; 95% CI excludes zero in both scopes) and shows a similar, though not statistically confirmed, gain on Kvasir-Capsule (up to 3.4x). Against OT, HCE still improves rare-class recall in all four evaluation settings (+0.016 to +0.029), and additionally improves macro-F1 and MCC.

We present Open-Qwen-Music, an open reconstruction of Qwen-Music and a fully specified research system for text-to-music generation that couples LLM-based semantic composition with diffusion-based acoustic rendering. The system comprises a 25 Hz single-codebook music tokenizer, a 3B-parameter autoregressive Music LLM, and a diffusion renderer producing 48 kHz stereo audio, following the cross-module interfaces reported by Qwen-Music. The strongest systems of this design remain closed, and prominent open music-generation projects release weights and inference code without their training corpora or end-to-end training implementations. This limits independent and controlled study of how information loss and prediction errors propagate from semantic representation through autoregressive planning to acoustic rendering. To our knowledge, Open-Qwen-Music is the first fully open release of an LLM-composition-plus-diffusion-rendering text-to-music system. Beyond model weights and inference code, the release includes the training datasets and provenance manifests, complete data-processing, annotation, training, inference, and evaluation pipelines, configurations, and pretrained weights for every learned module. Artifact manifests bind the identities of these artifacts across the complete workflow. Together, these artifacts establish a reproducible implementation of the modular architecture and provide an empirical basis for component-level analysis and future evaluation. We present the system as a transparent, executable research baseline and a starting point for the community, not as evidence of quality parity with Qwen-Music. Open-Qwen-Music is an ongoing effort, and we will continue to improve its generation quality, controllability, and robustness. All release artifacts are available at https://github.com/biang15343100-source/Open-Qwen-Music.

Underwater Optical Wireless Communication (UOWC) has emerged as a promising technology for high-speed underwater data transmission, offering significantly higher bandwidth and lower latency compared to acoustic and Radio Frequency (RF) technologies. However, the underwater medium introduces severe impairments that degrade link performance and limit communication range. The growing complexity of these challenges has increased research interest in Machine Learning (ML) and Deep Learning (DL) approaches, which offer powerful tools for channel modeling, signal processing, and system adaptation in ways that conventional analytical methods struggle to achieve. This survey provides a comprehensive review of ML methods applied across the full UOWC system pipeline, covering channel modeling, transmitter design, receiver detection and equalization, link alignment, and emerging applications, including wireless power transfer, semantic communication, object detection, optical sensing, and localization. Finally, we discuss open challenges and future research directions to motivate further work in this rapidly growing field.

Unmanned aerial vehicle (UAV) swarms deployed in mission-critical applications must simultaneously track a mobile aerial target and maintain reliable data links. However, active integrated sensing and communication (ISAC) operation imposes a dual energy burden on propulsion and transmission, threatening mission continuity through premature battery depletion. In this paper, we propose a two-tier UAV swarm architecture in which mission UAVs (MUAVs) execute cooperative ISAC for mobile aerial target tracking while dedicated charging UAVs (CUAVs), equipped with solar harvesting panels, replenish low-battery MUAVs via aerial UAV-to-UAV wireless power transfer (WPT). We formulate the joint minimization of the cooperative posterior Cramér-Rao bound (PCRB) over MUAV trajectories, per-slot sensing-communication time splits, WPT scheduling and admission, and CUAV rendezvous trajectories, subject to minimum uplink rate, dual-tier energy causality, WPT proximity, collision-avoidance, and speed constraints, yielding a non-convex mixed-integer program (MIP) that, to the best of our knowledge, is the first to jointly couple cooperative ISAC sensing quality with aerial WPT and dual-tier energy management. To solve it efficiently, we propose Receding-Horizon Alternating Optimization (RHAO), a four-block per-slot algorithm that decomposes the problem into: charging admission via the Hungarian algorithm, MUAV trajectory and time-split via successive convex approximation (SCA), CUAV rendezvous, and WPT power allocation, with monotone convergence guarantees. Simulation results demonstrate that RHAO reduces the mean PCRB by 16.8 times over a fixed-time-split baseline and 5.4 times over a static-trajectory scheme, while the aerial WPT subsystem sustains all MUAVs above the energy-critical threshold throughout the full mission horizon.

Wireless edge caching networks typically consist of many independent Base Stations (BSs), each facing its own request rate and content popularity profile. Training a Reinforcement Learning (RL) caching agent from scratch at every BS forces each agent to relearn, through slow trial and error, a decision problem that is structurally identical across the network. Meta-reinforcement learning removes this redundancy by learning a shared initialization that adapts to any BS in a few local updates; however, meta-training itself becomes the bottleneck at scale: the meta-gradient must be estimated from a small subset of BSs at each meta-iteration, and sampling this subset uniformly at random yields a high-variance estimate, an issue existing meta-RL caching frameworks leave unaddressed. This paper proposes a meta-reinforcement learning framework for caching across independent, non-overlapping BSs that directly targets this bottleneck. Each BS runs a local Proximal Policy Optimization (PPO) agent, formulated as a Semi-Markov Decision Process (SMDP) over content popularity, size, lifetime, and importance, while a shared meta-policy is learned via a Model-Agnostic Meta-Learning (MAML)-style loop. To scale meta-training and accelerate convergence, we introduce gradient-based clustering, which groups BSs by local gradient similarity and draws from every cluster, in proportion to its size, at each meta-iteration. We prove, via an Analysis of Variance (ANOVA)-style decomposition of gradient variance, that this strategy yields a strictly lower-variance meta-gradient estimator than uniform random sampling under BS heterogeneity.

Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous droplet transport through confined geometries of varying complexity remains an open challenge. Droplets exhibit contact-angle hysteresis, deformability, and capillary pinning, which make their response to actuation nonlinear and history dependent, that classical controllers and pre-programmed trajectories cannot cope in multi-turn environments. Here we demonstrate autonomous navigation of a liquid droplet through geometries of increasing complexity on a gravity driven (Labyrinth) platform using model-based reinforcement learning. A thin silicone oil film reduces contact-line pinning while two-axis tilt supplies the gravitational driving force, and an overhead camera tracks the droplet in real time. An offline-trained policy discovers effective tilt strategies from limited physical interaction data, without simulation or analytical droplet models. The system operates under partial observability, as oil-film thickness, instantaneous contact angle, and droplet deformation state remain hidden from the controller. Despite these challenges, the learned policy achieves reliable navigation across straight, right-angle, and curved-arc paths, including outside-corner geometries. We further demonstrate that a policy trained on a simpler geometry transfers to complex ones, succeeding zero-shot on right-angle and staircase paths and reaching full success on a curved arc with a fifth of the training data. The findings suggest promising avenues for enabling droplet based microfluidic systems to serve as intelligent chemical laboratories.

Electromagnetic navigation requires sufficient actuation at clinically relevant distances due to limited magnetic volumes and coil currents. We combine real-time pose feedback with constrained convex optimization, dynamic feedback, and repetitive control to achieve energy-efficient micro-guidewire steering inside realistic anatomical models. Experiments with a clinically oriented, three-coil electromagnetic navigation system and a 0.6 mm-diameter tip magnet demonstrate angular tracking with root-mean-square errors below 0.25 degrees at distances up to 55 cm from the coil cover. Nullspace current redistribution maintains accurate tracking under active 45 A coil-current constraints. Compared with conventional field alignment, we demonstrate that pose-dependent torque-based allocation substantially reduces current demand, with the efficiency benefit retained at a pose-feedback rate of 15 Hz. These results demonstrate how real-time state information and optimization can extend electromagnetic guidewire control toward clinically relevant working distances.