Papers

Planning collision-free motion for large robot fleets is difficult because collision avoidance induces strong inter-agent coupling that grows rapidly with team size. We consider omnidirectional floating robots on water, where choreographies are specified by sparse keyframes and an interactive tool must generate trajectories within seconds, even when transitions span minutes and thousands of time steps. We propose a scalable pipeline that builds a collision graph from an initialization, decomposes the coupled problem into interaction clusters, and solves clusters independently (and in parallel) with robustness mechanisms for common decomposition pathologies. We validate the approach in simulations up to 500 robots. The synthesized trajectories have also been deployed in two real-world demonstrations, on Lake Zürich with a fleet of 24 Way of Water crafts and at the Time Space Existence 2025 Venice Biennale.

The rapid expansion of AI globally has led to the proliferation of energy-intensive hyperscale data centres (DCs), making them as a structurally challenging component in power system planning and operation. Using a spatially explicit optimisation model of Europe across 21 AI growth scenarios, we systematically quantify additional demand, capacity requirements, emissions, and operational impacts of DCs. Results indicate that AI could drive 73-723 TWh of extra demand by 2050, risking cumulative emissions overshoots of 67-181 MtCO2 between 2030 and 2050. Our analysis indicates that after 2030, the geography of AI infrastructure will be shaped more by firm power and system flexibility than by the mere abundance of clean energy. In moderate scenarios, AI requires an additional of 200 hours of firm generation, which increases LCOE by 35 EUR/MWh in key hubs. We show that even under the pessimistic scenarios, existing infrastructure would require 70 GW additional capacity, while under managed growth pathways, this expansion could reach 226 GW. We further find DCs workload dynamics strongly shape energy dispatch, system flexibility, and emissions, while improved efficiency significantly reduces capacity needs, and system peaks. While our findings suggest that net-zero targets for 2050 may be achieved, critical emission risks may appear in the intermediate years, and the EU may compromise its carbon-neutral goals unless policies adapt to this accelerating digital transformation.

Target tracking is challenging when sensor detection thresholds cause state-dependent missed detections, particularly in multi-sensor scenarios with clutter and uncertain target existence. A recently developed missed detection framework models detection probability as a function of target state, sensor characteristics, and detection threshold, but it is limited to individual measurements and does not address the recursive tracking problem. This work extends the framework using a Bernoulli filter formulation to jointly handle recursive target tracking, clutter, and target existence uncertainty. A Bernoulli particle filter is evaluated in a simulated 2D multi-sensor tracking scenario with nonlinear measurements, clutter, and detection uncertainty. Incorporating accurate detection threshold knowledge reduces the generalized optimal subpattern assignment (GOSPA) metric by 53.9% compared to a conventional BF with fixed detection probability, and 35.7% compared to a BF with unknown detection probability, while better balancing missed detections and false alarms.

In this work, we analyze the ability of NCSN++ U-Net based audio dereverberation models to capture global room characteristics in their intermediate representations. Through an empirical study of both a state-of-the-art diffusion-based model and a discriminative counterpart, we show that deeper layers encode structured room impulse response (RIR)-dependent embeddings. Moreover, the discriminative ability of this implicit room representation correlates with dereverberation performance across objective metrics. Motivated by this observation, we propose a training strategy that explicitly conditions the network on pre-trained RIR embeddings, obtained via self-supervised contrastive learning. Incorporating RIR conditioning improves representation quality, accelerates convergence, and enhances dereverberation performance, while significantly reducing the number of reverse diffusion steps required by the diffusion-based model during inference.

This paper presents a method for controlling traffic via the use of connected and automated vehicles (CAVs) acting as moving bottlenecks. Current methods for moving bottleneck control use a couple PDE-ODE model, based on the Lighthill-Whitham-Richard (LWR) model, to represent the influence of the CAV. Control of the CAV is normally achieved by designing the control on the ODE which models the speed of the moving bottleneck. The proposed method in this paper instead looks to reduce the computational burden of controlling multiple CAVs by designing the moving bottleneck controller first on the PDE. The original control designed on the PDE is a linear quadratic regulator (LQR) that determines the optimal variable speed limit (VSL) for the entire length of freeway in order to regulate density to a desired setpoint. Then, a continuification approach is utilized to determine the input speed for each CAV. Results show that multiple CAVs can be controlled via this method, with minimal computational burden, and that as the number of CAVs increases the solution approaches the global optimal solution determined by the LQR.

The split covariance intersection filter (Split CIF) is a useful tool for general data fusion and has the potential to be applied in a variety of engineering tasks. The w-optimization problem involved in the Split CIF concerns the performance and implementation efficiency of the Split CIF. It is known that the w-optimization problem enjoys the desirable property of convexity (or more clearly, the second-order convexity in this paper's context). This paper proves that the w-optimization problem further enjoys a more desirable property namely the fourth-order convexity, thanks to which a guaranteed fast implementation of the Split CIF can be realized. The new implementation is coined as the nested Newton method, which is also presented in this paper.

Distributed radio frequency sensing in contested tactical environments demands collaborative learning across mobile nodes. In ad-hoc networks, learning must occur without persistent backhaul, ground truth labels, or reliable communication links. Traditional federated learning approaches assume either ideal link conditions or supervised training objectives, neither of which holds in practice for deployed MANET platforms. This paper presents a hierarchical federated learning framework for unsupervised waveform classification over tactical MANETs subject to Rayleigh fading, random waypoint mobility, and multi-hop routing loss. Each node trains a local denoising convolutional autoencoder on raw IQ observations without label exchange, learning compact representations through a self-supervised reconstruction objective. A two-stage aggregation protocol elects connectivity-based relay aggregators consistent with OLSR multipoint relay selection, compressing cluster-level model updates before forwarding to a mobile server proxy. Across five random seeds, in-network aggregation reduces attempted transmission bits by 16% on average relative to relay-forward federated averaging at comparable classification performance. Despite mean per-round update drop rates of 21% (hierarchical) and 34% (flat), hierarchical MANET FL attains the highest mean unsupervised representation quality of the three federated conditions tested while also showing substantially lower run-to-run variance than either flat MANET FedAvg or ideal FedAvg; flat routing itself shows no consistent benefit or penalty relative to ideal FedAvg. Performance is assessed using KMeans normalized mutual information and linear probe accuracy on the learned latent embeddings.

We study an idealized information model for Doppler-only positioning with low earth orbit (LEO) signals of opportunity from a stationary receiver. Motivated by the observation that Doppler measurements from a satellite pass provide information primarily within the associated orbital plane, we model each satellite contribution as a weighted projection onto that plane. Under this model, the combined information matrix from multiple satellites is a sum of orbital-plane projection operators. Closed-form expressions are derived for the eigenvalues, condition number, and worst-case Cramer-Rao lower bound. For two satellites, the conditioning is governed by the dihedral angle between orbital planes and the relative information strengths of the two links. Monte Carlo evaluation of pass-integrated Doppler Fisher information matrices demonstrates that the proposed surrogate captures the dominant conditioning trends associated with orbital-plane diversity. The results provide a simple geometric framework for understanding the role of constellation geometry in Doppler-only positioning systems.

Phase contrast MRI (PC MRI) enables quantitative assessment of tissue motion and strain. Although it is increasingly used, standardized, vendor-agnostic pipelines for accelerated acquisitions remain scarce. We present a fully open-source 4D flow PC-MRI pipeline integrating a compressed sensing-accelerated sequence implemented in PyPulseq, BART-based reconstruction, and strain analysis. Additionally, a gradient probing sequence was developed to ensure correct velocity sign assignment across scanner orientations and vendors. The pipeline was validated across two Siemens MRI systems (3T MAGNETOM Prisma and 3T Vida Fit) in two anatomical applications: forearm (Flexor Digitorum Superficialis, n=9) and thigh (Vastus Lateralis, n=10) during Neuromuscular Electrical Stimulation (NMES)-induced contractions. Compressed sensing reduced acquisition times from 35 and 80 minutes to 5 and 11 minutes for the arm and leg acquisitions, respectively. Muscle strain maps and sigmoid-fitted strain curves enabled extraction of peak strain, mean strain, and buildup rate. Strains in the Vastus Lateralis were approximately one order of magnitude higher than in the Flexor Digitorum Superficialis (median peak strain 0.49 vs. 0.063, mean strain 0.31 vs. 0.031). The pipeline demonstrates multi-platform compatibility and provides a reproducible, open framework for quantitative muscle imaging.

This paper presents a novel framework to track the effective surface area of non-convex satellites, enabling the use of aerodynamic drag in low Earth orbit for orbital control. The proposed framework enables the satellite to track the effective surface area while simultaneously performing other maneuvers. We introduce this framework through a backstepping control algorithm, and exemplify its advantages with an extension, to simultaneously maximize solar panel exposure. The equilibria of the closed-loop systems are shown to be asymptotically stable, and simulation results confirm the effectiveness of the proposed framework.

The emerging AC/multi-terminal DC grids are regarded as a promising solution for accommodating the increasing integration of renewable energy sources. This work proposes an optimization framework to address transmission switching (TS) problems arising in practical operational scenarios, such as maintenance scheduling, contingency management, and fault restoration. Unlike most existing studies, the proposed framework considers the role of communication networks in TS operations and develops an optimal information-power flow (OIPF) model. The OIPF model captures the impact of information flows on circuit breaker actions while incorporating communication-related costs, thereby better reflecting practical operational decision-making processes. To ensure computational tractability, the resulting optimization problem is formulated as a mixed-integer second-order cone programming (MISOCP) model through convex relaxations, polygonal approximations, and Big-M reformulations. Numerical case studies illustrate the applicability of the proposed OIPF model and indicate its potential in supporting transmission switching decisions.

This paper introduces a novel class of delayed functional observers specifically designed to reconstruct delayed control laws under severe output measurement lags, directly complementing recent literature \cite{trinhnn26, trinhnam26}. By systematically mitigating simultaneous, unequal delays across both the actuator and sensor channels, the proposed architecture resolves dual-channel latency without requiring full-state estimation or computationally intensive real-time distributed integration. Ultimately, this work provides a powerful, low-order framework that bridges the gap between idealized control theory and the practical constraints of modern networked engineering systems.

Alternating current (AC)/multi-terminal direct current (MTDC) hybrid power systems (HPSs) play a crucial role in enabling long-distance power transmission and flexible interconnections between AC grids. However, the challenges that HPSs encountered are numerous, with stability and harmonic issues being particularly prominent. Traditional electromagnetic transient (EMT) tools have struggled to accommodate small-signal stability problems and the potential issues of the optimal interactions among converters. To address this gap, HARMONY ("HARMONic stabilitY assessment of PE-penetrated power systems") has been developed for the advanced simulation and analysis of interconnected AC/MTDC HPSs as a comprehensive mathematical framework based on C++ programming language. The primary goals of Harmony are to provide faster and trusted stability analyses, and address the analytical difficulties associated with converter control dynamics, converter-driven stability, and interoperability in HPSs. This framework is intended to be open source, therefore broadening collaboration for researchers, and to contribute to the community of power systems engineers. In this paper, we demonstrate two core functionalities featured in HARMONY, that are optimal power flow (OPF) and harmonic stability analyses (HAS). The underlying analysis models and computational methodologies for both functionalities are presented in detail to help future readers and users gain a clear understanding of mathematical fundamentals of HARMONY. Furthermore, we introduce the integrated framework of OPF and HAS designed in HARMONY, along with representative printed analysis results, to demonstrate the appealing capabilities of HARMONY.

Large language models (LLMs) provide a powerful reasoning backbone for speech understanding, but integrating continuous acoustic signals into a pretrained LLM remains challenging. A central design question is how to tie speech representations to the LLM's text input space while preserving the continuous variation needed for different speech tasks. In this work, we propose Convex Gate (C-Gate), a speech-LLM bridge that represents each frame as a convex combination of frozen token embeddings. This architectural convex-hull constraint fixes the output codebook while allowing continuous mixtures learned from task supervision. With a Whisper-large-v3 encoder, a partially adapted Qwen2.5-7B-Instruct decoder, and joint training on speech recognition, emotion recognition, and spoken reasoning, C-Gate performs accurate transcription and emotion recognition, our representative semantic and acoustic tasks, through one shared decoder. On text-only benchmarks, the adapted decoder loses instruction-following and MMLU accuracy and matches or exceeds the original model on GSM8K and HellaSwag. We further design analyses and interventions on the trained model to examine where the bridge sequence carries task information and how the decoder reads it. These findings show how fixed text embeddings can support both semantic and acoustic readouts through continuous speech-conditioned mixtures.

Transformer-based architectures have led to significant improvements in Automatic Speech Recognition (ASR), often at the cost of substantially increased model sizes. A promising approach to address this issue is layer sharing through depth recursion, commonly referred to as the Recursive-Transformer, which involves repeatedly applying the same layers within the model. Despite its potential shown in other fields, this technique remains relatively unexplored in ASR. In this paper, we present an experimental study of the Recursive-Transformer applied to ASR encoder architectures. We systematically investigate the impact of recursion depth and layer allocation within the Recursive-based Transformer. Our results demonstrate that the Recursive-Transformer is a viable alternative, especially when recurrence is applied in the latent space with a restricted number of loops, obtaining comparable performance while reducing the parameter count by 66%.

Automatic Speech Recognition (ASR) systems are widely deployed across linguistically diverse regions, yet their ability to generalize across fine-grained geographic variation remains underexplored. We present a systematic study of cross-district ASR generalization for Indian languages, analyzing the impact of regional variation on performance. Using finetuning as a controlled probe, we train models on speech from a single district and evaluate them on other districts within the same language. We examine trends across multiple train test district pairs and quantify performance differences. To assess geographic effects, we analyze the correlation between WER and inter district distance using two distance measures. Our results show consistent correlations between geographic distance and WER, highlighting the challenges of regional generalization and the need for geographically diverse speech data in ASR development and evaluation in India.

Speech foundation models enable strong general-purpose ASR and are attractive for downstream adaptation. However, their size and the catastrophic forgetting induced by sequential fine-tuning demand parameter-efficient and regularized training methods, motivating parameter-efficient continual learning (PECL). While PECL has been widely studied in NLP and vision, it has received less attention in ASR. In this paper, we propose a simple yet effective PECL method based on recent advances in parameter-efficient fine-tuning for ASR. We partition pretrained weight matrices into head and tail subspaces according to singular values and restrict adaptation to approximate rotations within the low-energy tail subspace, preserving dominant components and reducing forgetting. For subsequent tasks, rotations are combined via weight averaging to further improve retention. Experiments on two benchmarks demonstrate reduced forgetting and superior overall performance compared to recent PECL baselines.

ASR performance varies across languages, speakers, and recording conditions, yet systematic analysis for Indic languages remain limited. We present a large-scale study of decoded outputs from multiple open-source ASR models evaluated on diverse Indian speech datasets in zero-shot settings. We analyze linguistic, speaker-level, and acoustic factors across Hindi, Bengali, Kannada, Telugu, and Marathi. We examine correlations between WER and speaker traits such as average word length, speaking rate, and utterance duration across multiple model dataset pairs. For Hindi, we further analyze audio factors including telephone codecs, bit depth, resampling, and background noise. Results reveal both cross lingual patterns and language-specific sensitivities, showing how speaker behavior and signal processing choices affect ASR robustness in real world Indic scenarios.

Structural heart disease (SHD) is a primary driver of heart failure and cardiovascular mortality, yet early detection remains constrained by the limited accessibility of echocardiography. While single-lead electrocardiogram (ECG) is ubiquitous through wearables, existing AI screening models often depend on 12-lead inputs, generalize poorly across institutions, or require massive, condition-specific labeled datasets. Recent work has demonstrated the feasibility of contrastive pre-training between single-lead ECGs and echocardiography reports within a single health system. Here, we present AnyECG-Echo, a framework that advance this paradigm toward clinical translation through three key developments: (1) evaluation in a geographically independent external cohort (n = 16,621); (2) diagnostic coverage of 13 fine-grained SHD subtypes spanning myocardial, chamber, valvular, and great-vessel pathologies; and (3) dual-axis mechanistic interpretability combining electrophysiology-grounded Shapley attribution with emergent correlations to quantitative measurements. Across validation cohorts totaling n = 25,222, the model demonstrated high AUROC for high-impact subtypes, including reduced left ventricular systolic function (AUROC 0.866-0.924), global heart enlargement (0.877-0.931), and mitral stenosis (0.836-0.906). Furthermore, we successfully validated the alignment of model outputs with established medical physiological traits, thereby enhancing interpretability. Notably, we discovered that AnyECG-Echo's outputs function as physiologically grounded digital biomarkers that accurately track objective metrics such as LVEF and myocardial wall thickness. These findings prove that wearable single-lead ECGs can effectively detect fine-grained structural heart disease, offering a practical solution for population-scale screening.

Extended Reality (XR) applications demand intensive computation and low latency, especially for real-time rendering tasks. In this letter, we present an edge-aided XR rendering testbed that dynamically offloads rendering workloads between the XR client and the edge server built upon network conditions and latency constraints. The testbed integrates a Microsoft HoloLens 2 headset, a GPU-enabled edge server, and a customized remote rendering toolkit based on the HOLO Stream SDK, enabling seamless switching between local and edge rendering modes in real time. To overcome the limitations of pixel-level quality metrics under head movements and asynchronous frame arrivals, we propose a perceptual evaluation metric based on deep feature embeddings and cosine similarity, which remains robust to spatial and temporal misalignments. Furthermore, we design a contextual bandit learning controller to adapt rendering placement decisions in real time by jointly optimizing perceptual quality and latency. Experimental results demonstrate the feasibility and performance of our testbed, validating its effectiveness in delivering high-quality and interactive XR experiences.

Spoken language identification (LID) for Indian languages is a challenging problem due to the large number of languages, significant phonetic overlap among related varieties, and the scarcity of labeled data for many low-resource languages. In this work, we present a systematic comparative study of two pre-trained speech encoders – Whisper and FastConformer – combined with a linear classifier for large-scale Indic LID spanning 42 languages across four linguistic families. We evaluate both encoders in frozen (linear probing) and fine-tuned settings, and compare three training objectives: cross-entropy (CE), supervised contrastive loss with cross entropy (CE + supCon), and hierarchical softmax (HSM). Models are trained on the Vaani dataset and evaluated in a cross-corpus setting on Vaani-Test (held-out), FLEURS, and Kathbath, providing insights into domain generalization. The frozen FastConformer encoder achieves over 90% macro accuracy on FLEURS and Kathbath without any task-specific adaptation, substantially outperforming Whisper on out-of-domain benchmarks, while fine-tuned Whisper yields stronger in-domain performance. HSM consistently outperforms CE and CE+SupCon for both encoders across all benchmarks, with the largest gains on out-of-domain test sets. CE+SupCon degrades FastConformer's cross-corpus generalization, suggesting that the contrastive objective over-specializes representations to in-domain conditions. Per-family analysis shows that Central Indo-Aryan varieties are the hardest to discriminate, with Hindi–Urdu and the Sadri–Chhattisgarhi–Surgujia cluster being the dominant confusion pairs.

Reliable navigation in GPS-denied environments remains a fundamental challenge in robotics, aerospace, and autonomous vehicle applications. This paper presents a Dual Quaternion-Based Unscented Kalman Filter (DQUKF) equipped with a Visual Inertial Odometry (VIO) algorithm for accurate state estimation enabling navigation in GPS denied locations. The proposed framework formulates the DQUKF in an error state manner, where the nominal pose is represented by a unit dual quaternion and the local pose error is represented by a 6-dimensional twistor parameterization used for sigma point generation, covariance propagation, and measurement correction. In parallel, the VIO algorithm tracks features across image frames, synchronizes measurements between the IMU and camera, and provides visual constraints that complement inertial propagation. Simulation results on the EuRoC MAV dataset show that the proposed DQUKF converges under high initialization uncertainty and achieves a position RMSE of 0.2584~m in the difficult flight sequence, outperforming the benchmark filters.

Mesoscopic traffic flow models combines the merits of both macroscopic and microscopic models by capturing individual vehicle behavior in great detail and remaining the computational efficiency. At the time of this study, the mesoscopic model proposed by Eissfeldt (2004) is used in Simulation of Urban MObility (SUMO). The movement of vehicles is governed by dynamic headways between edges. However, the model does not fully comply with the principle of the Lighthill-Whitham-Richards (LWR) model. Several problems are identified, including the incomplete consideration of queue dynamics and the limited implementation of backward traveling spaces. Two case study scenarios demonstrate that the problems lead to unrealistic onset and recovery pattern of congestion. The magnitude of congestion is generally underestimated with this model. To address these drawbacks, a proper mesoscopic discrete-time implementation of link transmission model, which follows the LWR principle, is proposed. By explicitly incorporating backward traveling spaces to capture queue spillback phenomena, the proposed model provides a more precise representation of congestion dynamics. The link density outputs are consistent with the kinematic wave theory and the microscopic traffic simulation in SUMO, thus verifying its theoretical accuracy.

Functional ultrasound (fUS) has emerged as a powerful neuroimaging modality due to its high resolution in both space and time, low cost and potential portability. Nevertheless, fUS signals provide only indirect observations of neuronal activity through the neurovascular coupling, and hence require the blind separation of latent neuronal sources while also deconvolving their hemodynamic responses. In this work, we propose a data-driven convolutive block-term tensor decomposition-based model for multi-trial fUS measurements, where each source has a spatiotemporal representation comprising a low-rank spatial map and a piecewise-constant neuronal activation signal convolved with a trial- and source-dependent hemodynamic response function (HRF) with a physiologically plausible shape. We propose a constrained optimization framework for the model computation, which consists of alternating projected gradient descent iterations. Simulation results are reported that demonstrate accurate recovery of spatial maps and reliable estimation of activation temporal profiles across various noise levels, while confirming that HRF estimation remains the most challenging part of the problem.

Time-of-flight cameras are popular in robotics because they provide direct depth information and are compact, inexpensive, and less dependent on ambient visible light. However, their low spatial resolution and depth noise raise questions about their suitability for stabilizing fast, unstable dynamics. In this paper, we show that an inexpensive, low-resolution time-of-flight camera can provide angle feedback for reliable and precise balancing of an inverted pendulum on a cart, a canonical control benchmark. These results open the door to using compact, inexpensive, low-resolution time-of-flight cameras for precise feedback control of fast, unstable systems.

Recent progress in speech dialogue systems requires Text-to-Speech (TTS) models to be faster and more responsive. Modern speech dialogue systems impose two primary requirements on TTS models: low latency and support for streaming inputs and outputs. However, most existing single-codebook LLM-based TTS methods rely on multi-stage pipelines that lack native streaming capabilities. These systems typically suffer from high end-to-end latency due to slow autoregressive prediction and multi-step flow matching. To address these limitations, we propose FlashTTS, an open-source and low-latency streaming TTS framework. FlashTTS introduces a lagged multi-track architecture that natively processes streaming text and speech inputs, thereby eliminating the need for sentence-level buffering. To accelerate acoustic generation, we integrate parallel Multi-Token Prediction (MTP) with an X-pred mean flow matching decoder. This configuration achieves high-fidelity token-to-mel generation in exactly two function evaluations (2-NFE). By jointly optimizing input processing and decoding efficiency, FlashTTS offers a practical foundation for real-time speech dialogue systems. Experiments show that FlashTTS substantially reduces First-Packet Latency to 325ms compared to robust streaming baselines, all while preserving strong zero-shot voice cloning and cross-lingual intelligibility. Speech samples are available. The model code and checkpoints will be released as open source.

This work presents a modal formulation for flexible rectangular plates, accounting for nonlinear geometric effects arising from in-plane foreshortening and centrifugal stiffening. The model is linearized with respect to elastic deformations while retaining the full dependence on spacecraft angular velocities and accelerations. System matrices depend nonlinearly on spacecraft states through squared and cross-product terms, capturing gyroscopic coupling and dynamic stiffening phenomena for arbitrary rotational maneuvers. Polynomial approximation of mode shapes enables efficient computation while preserving accuracy. Model predictions are validated against finite element simulations and literature data for transient response under prescribed hub motion.

Future artificial intelligence (AI)-native 6G networks require wireless systems that move beyond reactive optimization toward autonomous, predictive, and continuously adaptive intelligence. Most existing digital twin (DT) frameworks use AI only to improve modeling, data generation, or isolated optimization tasks, leaving the DT itself in a passive, synchronization-only role. This article redefines the DT as a predictive decision engine, which is model-agnostic framework that fuses continuous synchronization, predictive reasoning, autonomous decision-making, and closed-loop wireless control into a single system. Reasoning over synchronized network state, the framework anticipates future conditions and acts autonomously before performance degrades, using generative adversarial networks (GANs), large language models (LLMs), diffusion models, or other learning-based engines interchangeably as the underlying predictor. An illustrative unmanned aerial vehicle (UAV)-assisted non-terrestrial network (NTN) deployment, using a lightweight conditional generative adversarial network (cGAN) as one illustrative predictor, demonstrates the practical effectiveness of the proposed framework by achieving considerable energy savings over reactive baselines while maintaining reliable quality of service (QoS) under highly dynamic conditions.

Video dubbing is a cornerstone of multimedia content creation, aiming to synthesize synchronized acoustic sequences for visual streams. While Text-to-Speech (TTS) and Text-to-Audio (TTA) generation have each achieved remarkable progress, existing dubbing systems remain confined to isolated speech synthesis without incorporating sound effects and ambient audio, forcing practitioners to rely on fragmented workflows and laborious manual post-mixing. To address this limitation, we present HoliDubber, a holistic video dubbing framework that moves beyond speech-only generation by enabling the joint synthesis of speech and sound effects from a single text prompt. Specifically, HoliDubber adopts a patch-based autoregressive diffusion transformer architecture, where a causal language model autoregressively models aggregated patch embeddings to capture global temporal structure, and a Diffusion Transformer decoder generates high-fidelity continuous tokens within each patch, following a divide-and-conquer strategy. To achieve cross-modal alignment, visual features are encoded into patch-level representations and fused with audio patches via cross-attention, enabling the model to ground speech generation in the speaker's visual articulation dynamics. In addition, we introduce HoliDub-Bench, a benchmark curated from established datasets with synchronized video-text-audio triplets designed for holistic dubbing evaluation. Extensive experiments demonstrate that HoliDubber significantly outperforms existing methods across multiple benchmarks in speech quality, synchronization, and speaker similarity. Furthermore, results on HoliDub-Bench validate the effectiveness of joint speech-and-sound generation, establishing a new paradigm for holistic video dubbing in complex acoustic scenes. \footnote{The demo page of the project is https://holidubber.github.io}

This letter investigates a rate-splitting multiple access (RSMA)-enabled multi-user pinching antenna system (PASS). A fairness-aware sum-rate maximization problem is formulated to jointly optimize pinching antenna locations and common/private stream power allocation. The resulting mixed discrete-continuous non-convex problem is addressed using an alternating optimization framework that combines greedy antenna placement with successive convex approximation (SCA)-based power allocation. Numerical results demonstrate that the proposed RSMA-enabled PASS significantly improves achievable sum-rate, user fairness, and bit error rate (BER) performance compared with conventional non-RSMA PASS schemes.