Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Electrical Engineering and Systems Science

eess Watch Electrical Engineering and Systems Science

Sunday 4 January

Systems and Control · Cross-listed from cs.MA

CONSENT: A Negotiation Framework for Leveraging User Flexibility in Vehicle-to-Building Charging under Uncertainty

Rishav Sen, Fangqi Liu, Jose Paolo Talusan et al. (+5 more)

The growth of Electric Vehicles (EVs) creates a conflict in vehicle-to-building (V2B) settings between building operators, who face high energy costs from uncoordinated charging, and drivers, who prioritize convenience and a full charge. To resolve this, we propose a negotiation-based framework that, by design, guarantees voluntary participation, strategy-proofness, and budget feasibility. It transforms EV charging into a strategic resource by offering drivers a range of incentive-backed options for modest flexibility in their departure time or requested state of charge (SoC). Our framework is calibrated with user survey data and validated using real operational data from a commercial building and an EV manufacturer. Simulations show that our negotiation protocol creates a mutually beneficial outcome: lowering the building operator's costs by over 3.5% compared to an optimized, non-negotiating smart charging policy, while simultaneously reducing user charging expenses by 22% below the utility's retail energy rate. By aligning operator and EV user objectives, our framework provides a strategic bridge between energy and mobility systems, transforming EV charging from a source of operational friction into a platform for collaboration and shared savings.
Read the full abstract

All authors Rishav Sen, Fangqi Liu, Jose Paolo Talusan, Ava Pettet, Yoshinori Suzue, Mark Bailey, Ayan Mukhopadhyay, Abhishek Dubey

Audio and Speech Processing · Cross-listed from cs.SD

MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning

Chunyu Qiang, Jun Wang, Xiaopeng Wang et al. (+2 more)

Joint audio-video generation aims to synthesize synchronized multisensory content, yet current unified models struggle with fine-grained acoustic control, particularly for identity-preserving speech. Existing approaches either suffer from temporal misalignment due to cascaded generation or lack the capability to perform zero-shot voice cloning within a joint synthesis framework. In this work, we present MM-Sonate, a multimodal flow-matching framework that unifies controllable audio-video joint generation with zero-shot voice cloning capabilities. Unlike prior works that rely on coarse semantic descriptions, MM-Sonate utilizes a unified instruction-phoneme input to enforce strict linguistic and temporal alignment. To enable zero-shot voice cloning, we introduce a timbre injection mechanism that effectively decouples speaker identity from linguistic content. Furthermore, addressing the limitations of standard classifier-free guidance in multimodal settings, we propose a noise-based negative conditioning strategy that utilizes natural noise priors to significantly enhance acoustic fidelity. Empirical evaluations demonstrate that MM-Sonate establishes new state-of-the-art performance in joint generation benchmarks, significantly outperforming baselines in lip synchronization and speech intelligibility, while achieving voice cloning fidelity comparable to specialized Text-to-Speech systems.
Read the full abstract

All authors Chunyu Qiang, Jun Wang, Xiaopeng Wang, Kang Yin, Yuxin Guo

Audio and Speech Processing · Cross-listed from cs.SD

MOSS Transcribe Diarize Technical Report

MOSI.AI: Donghua Yu, Zhengyuan Lin, Hanfu Chen et al. (+21 more)

Speaker-Attributed, Time-Stamped Transcription (SATS) aims to transcribe what is said and to precisely determine the timing of each speaker, which is particularly valuable for meeting transcription. Existing SATS systems rarely adopt an end-to-end formulation and are further constrained by limited context windows, weak long-range speaker memory, and the inability to output timestamps. To address these limitations, we present MOSS Transcribe Diarize, a unified multimodal large language model that jointly performs Speaker-Attributed, Time-Stamped Transcription in an end-to-end paradigm. Trained on extensive real wild data and equipped with a 128k context window for up to 90-minute inputs, MOSS Transcribe Diarize scales well and generalizes robustly. Across comprehensive evaluations, it outperforms state-of-the-art commercial systems on multiple public and in-house benchmarks.
Read the full abstract

All authors MOSI.AI: Donghua Yu, Zhengyuan Lin, Hanfu Chen, Chen Yang, Yiyang Zhang, Jingqi Chen, Ke Chen, Liwei Fan, Yi Jiang, Jie Zhu, Muchen Li, Wenxuan Wang, Yang Wang, Zhe Xu, Botian Jiang, Yitian Gong, Yuqian Zhang, Wenbo Zhang, Songlin Wang, Zhiyu Wu, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu

Image and Video Processing

Sim2Real SAR Image Restoration: Metadata-Driven Models for Joint Despeckling and Sidelobes Reduction

Antoine De Paepe, Pascal Nguyen, Michael Mabelle et al. (+3 more)

Synthetic aperture radar (SAR) provides valuable information about the Earth's surface under all weather and illumination conditions. However, the inherent phenomenon of speckle and the presence of sidelobes around bright targets pose challenges for accurate interpretation of SAR imagery. Most existing SAR image restoration methods address despeckling and sidelobes reduction as separate tasks. In this paper, we propose a unified framework that jointly performs both tasks using neural networks (NNs) trained on a realistic SAR simulated dataset generated with MOCEM. Inference can then be performed on real SAR images, demonstrating effective simulation to real (Sim2Real) transferability. Additionally, we incorporate acquisition metadata as auxiliary input to the NNs, demonstrating improved restoration performance.
Read the full abstract

All authors Antoine De Paepe, Pascal Nguyen, Michael Mabelle, Cédric Saleun, Antoine Jouadé, Jean-Christophe Louvigne

Systems and Control · Cross-listed from math.OC

Lyapunov Functions can Exactly Quantify Rate Performance of Nonlinear Differential Equations

Declan S. Jagt and Matthew M. Peet

Pointwise-in-time stability notions for Ordinary Differential Equations (ODEs) provide quantitative metrics for system performance by establishing bounds on the rate of decay of the system state in terms of initial condition – allowing stability to be quantified by e.g. the maximum provable decay rate. Such bounds may be obtained by finding suitable Lyapunov functions using, e.g. Sum-of-Squares (SOS) optimization. While Lyapunov tests have been proposed for numerous pointwise-in-time stability notions, including exponential, rational, and finite-time stability, it is unclear whether these characterizations are able to provide accurate bounds on system performance. In this paper, we start by proposing a generalized notion of rate performance – with exponential, rational, and finite-time decay rates being special cases. Then, for any such notion and rate, we associate a Lyapunov condition which is shown to be necessary and sufficient for a system to achieve that rate. Finally, we show how the proposed conditions can be enforced using SOS programming in the case of exponential, rational, and finite-time stability. Numerical examples in each case demonstrate that the corresponding SOS test can achieve tight bounds on the rate performance with accurate inner bounds on the associated regions of performance.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.CL

Bridging the gap: A comparative exploration of Speech-LLM and end-to-end architecture for multilingual conversational ASR

Yuxiang Mei, Dongxing Xu, Jiaen Liang et al. (+1 more)

The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive parallel-speech-encoder architecture that integrated Whisper and mHuBERT with an LLM. However, it faced two challenges: simple feature concatenation may not fully exploit complementary information, and the performance gap between LLM-based ASR and end-to-end(E2E) encoder-decoder ASR remained unexplored. In this work, we present an enhanced LLM-based ASR framework that combines fine-tuned Whisper and mHuBERT encoders with an LLM to enrich speech representations. We first evaluate E2E Whisper models with LoRA and full fine-tuning on the MLC-SLM ASR task, and then propose cross-attention-based fusion mechanisms for the parallel-speech-encoder. On the official evaluation set of the MLC-SLM Challenge, our system achieves a CER/WER of 10.69%, ranking on par with the top-ranked Track 1 systems, even though it uses only 1,500 hours of baseline training data compared with their large-scale training sets. Nonetheless, we find that our final LLM-based ASR still does not match the performance of a fine-tuned E2E Whisper model, providing valuable empirical guidance for future Speech-LLM design. Our code is publicly available at https://github.com/1535176727/MLC-SLM.
Read the full abstract

All authors Yuxiang Mei, Dongxing Xu, Jiaen Liang, Yanhua Long

Audio and Speech Processing · Cross-listed from cs.SD

OV-InstructTTS: Towards Open-Vocabulary Instruct Text-to-Speech

Yong Ren, Jiangyan Yi, Jianhua Tao et al. (+5 more)

Instruct Text-to-Speech (InstructTTS) leverages natural language descriptions as style prompts to guide speech synthesis. However, existing InstructTTS methods mainly rely on a direct combination of audio-related labels or their diverse rephrasings, making it difficult to handle flexible, high-level instructions. Such rigid control is insufficient for users such as content creators who wish to steer generation with descriptive instructions. To address these constraints, we introduce OV-InstructTTS, a new paradigm for open-vocabulary InstructTTS. We propose a comprehensive solution comprising a newly curated dataset, OV-Speech, and a novel reasoning-driven framework. The OV-Speech dataset pairs speech with open-vocabulary instructions, each augmented with a reasoning process that connects high-level instructions to acoustic features. The reasoning-driven framework infers emotional, acoustic, and paralinguistic information from open-vocabulary instructions before synthesizing speech. Evaluations show that this reasoning-driven approach significantly improves instruction-following fidelity and speech expressiveness. We believe this work can inspire the next user-friendly InstructTTS systems with stronger generalization and real-world applicability. The dataset and demos are publicly available on our project page.
Read the full abstract

All authors Yong Ren, Jiangyan Yi, Jianhua Tao, Haiyang Sun, Zhengqi Wen, Hao Gu, Le Xu, Ye Bai

Systems and Control

Context-Aware Information Transfer via Digital Semantic Communication in UAV-Based Networks

Poorvi Joshi and Mohan Gurusamy

In smart cities, bandwidth-constrained Unmanned Aerial Vehicles (UAVs) often fail to relay mission-critical data in time, compromising real-time decision-making. This highlights the need for faster and more efficient transmission of only the most relevant information. To address this, we propose DSC-UAV model, leveraging a context-adaptive Digital Semantic Communication (DSC) framework. This model redefines aerial data transmission through three core components: prompt-aware encoding, dynamic UAV-enabled relaying, and user mobility-optimized reinforcement learning. Ground users transmit context-driven visual content. Images are encoded via Vision Transformer combined with a prompt-text encoder to generate semantic features based on the desired context (generic or object-specific). These features are then quantized and transmitted over a UAV network that dynamically relays the data. Joint trajectory and resource allocation are optimized using Truncated Quantile Critic (TQC)-aided reinforcement learning technique, which offers greater stability and precision over standard SAC and TD3 due to its resistance to overestimation bias. Simulations demonstrate significant performance improvement, up to 22% gain in semantic-structural similarity and 14% reduction in Age of Information (AoI) compared to digital and prior UAV-semantic communication baselines. By integrating mobility control with context-driven visual abstraction, DSC-UAV advances resilient, information-centric surveillance for next-generation UAV networks in bandwidth-constrained environments.
Read the full abstract

Systems and Control

Reliable Grid Forecasting: State Space Models for Safety-Critical Energy Systems

Sunki Hong and Jisoo Lee

Accurate grid load forecasting is safety-critical: under-predictions risk supply shortfalls, while symmetric error metrics can mask this operational asymmetry. We introduce an operator-legible evaluation framework – Under-Prediction Rate (UPR), tail $\text{Reserve}_{99.5}^{\%}$ requirements, and explicit inflation diagnostics ($\text{Bias}_{24h}$/OPR) – to quantify one-sided reliability risk beyond MAPE. Using this framework, we evaluate five neural architectures – two state space models (S-Mamba, PowerMamba), two Transformers (iTransformer, PatchTST), an LSTM, and a probabilistic SSM variant (Mamba-ProbTSF) – on a weather-aligned California Independent System Operator (CAISO) dataset spanning Nov 2023–Nov 2025 (84,498 hourly records across 5 regional transmission areas) under a rolling-origin walk-forward backtest. We develop and evaluate thermal-lag-aligned weather fusion strategies matched to each architecture's inductive bias. Our results demonstrate that standard accuracy metrics are insufficient proxies for operational safety: models with comparable MAPE can imply materially different tail reserve requirements ($\text{Reserve}_{99.5}^{\%}$). We show that explicit weather integration narrows error distributions, with the magnitude of improvement being architecturally determined – iTransformer's cross-variate attention benefits significantly more than PatchTST's channel-independent design. Crucially, we identify a widespread susceptibility to "fake safety" in risk-averse forecasting: while probabilistic calibration reduces upper-tail errors, it achieves this by systematically inflating schedules (e.g., increasing bias by over 1,700 MW in severe cases) if left unconstrained. To solve this, we introduce Bias/OPR-constrained objectives that enable auditable trade-offs between minimizing tail risk and preventing trivial over-forecasting.
Read the full abstract

Systems and Control

Sampling Strategy Design for Model Predictive Path Integral Control on Legged Robot Locomotion

Chuyuan Tao, Fanxin Wang, Haolong Jiang et al. (+3 more)

Model Predictive Path Integral (MPPI) control has emerged as a powerful sampling-based optimal control method for complex, nonlinear, and high-dimensional systems. However, directly applying MPPI to legged robotic systems presents several challenges. This paper systematically investigates the role of sampling strategy design within the MPPI framework for legged robot locomotion. Based upon the idea of structured control parameterization, we explore and compare multiple sampling strategies within the framework, including both unstructured and spline-based approaches. Through extensive simulations on a quadruped robot platform, we evaluate how different sampling strategies affect control smoothness, task performance, robustness, and sample efficiency. The results provide new insights into the practical implications of sampling design for deploying MPPI on complex legged systems.
Read the full abstract

All authors Chuyuan Tao, Fanxin Wang, Haolong Jiang, Jia He, Yiyang Chen, Qinglei Bu

Audio and Speech Processing · Cross-listed from cs.SD

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning

Peidong Wang, Zhiming Ma, Xin Dai et al. (+8 more)

Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose SAFE-QAQ, an end-to-end comprehensive framework for audio-based slow-thinking fraud detection. First, the SAFE-QAQ framework eliminates the impact of transcription errors on detection performance. Secondly, we propose rule-based slow-thinking reward mechanisms that systematically guide the system to identify fraud-indicative patterns by accurately capturing fine-grained audio details, through hierarchical reasoning processes. Besides, our framework introduces a dynamic risk assessment framework during live calls, enabling early detection and prevention of fraud. Experiments on the TeleAntiFraud-Bench demonstrate that SAFE-QAQ achieves dramatic improvements over existing methods in multiple key dimensions, including accuracy, inference efficiency, and real-time processing capabilities. Currently deployed and analyzing over 70,000 calls daily, SAFE-QAQ effectively automates complex fraud detection, reducing human workload and financial losses. Code: https://anonymous.4open.science/r/SAFE-QAQ.
Read the full abstract

All authors Peidong Wang, Zhiming Ma, Xin Dai, Yongkang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang

Audio and Speech Processing

Bayesian Negative Binomial Regression of Afrobeats Chart Persistence

Ian Jacob Cabansag and Paul Ntegeka

Afrobeats songs compete for attention on streaming platforms, where chart visibility can influence both revenue and cultural impact. This paper examines whether collaborations help songs remain on the charts longer, using daily Nigeria Spotify Top 200 data from 2024. Each track is summarized by the number of days it appears in the Top 200 during the year and its total annual streams in Nigeria. A Bayesian negative binomial regression is applied, with days on chart as the outcome and collaboration status (solo versus multi-artist) and log total streams as predictors. This approach is well suited for overdispersed count data and allows the effect of collaboration to be interpreted while controlling for overall popularity. Posterior inference is conducted using Markov chain Monte Carlo, and results are assessed using rate ratios, posterior probabilities, and predictive checks. The findings indicate that, after accounting for total streams, collaboration tracks tend to spend slightly fewer days on the chart than comparable solo tracks.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.SD

UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models

Qundong Shi, Jie Zhou, Biyuan Lin et al. (+8 more)

The development of audio foundation models has accelerated rapidly since the emergence of GPT-4o. However, the lack of comprehensive evaluation has become a critical bottleneck for further progress in the field, particularly in audio generation. Current audio evaluation faces three major challenges: (1) audio evaluation lacks a unified framework, with datasets and code scattered across various sources, hindering fair and efficient cross-model comparison;(2) audio codecs, as a key component of audio foundation models, lack a widely accepted and holistic evaluation methodology; (3) existing speech benchmarks are heavily reliant on English, making it challenging to objectively assess models' performance on Chinese. To address the first issue, we introduce UltraEval-Audio, a unified evaluation framework for audio foundation models, specifically designed for both audio understanding and generation tasks. UltraEval-Audio features a modular architecture, supporting 10 languages and 14 core task categories, while seamlessly integrating 24 mainstream models and 36 authoritative benchmarks. To enhance research efficiency, the framework provides a one-command evaluation feature, accompanied by real-time public leaderboards. For the second challenge, UltraEval-Audio adopts a novel comprehensive evaluation scheme for audio codecs, evaluating performance across three key dimensions: semantic accuracy, timbre fidelity, and acoustic quality. To address the third issue, we propose two new Chinese benchmarks, SpeechCMMLU and SpeechHSK, designed to assess Chinese knowledge proficiency and language fluency. We wish that UltraEval-Audio will provide both academia and industry with a transparent, efficient, and fair platform for comparison of audio models. Our code, benchmarks, and leaderboards are available at https://github.com/OpenBMB/UltraEval-Audio.
Read the full abstract

All authors Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu

Systems and Control

Neural-network-based Self-triggered Observed Platoon Control for Autonomous Vehicles

Zihan Li, Ziming Wang, Chenning Liu et al. (+1 more)

This paper investigates autonomous vehicle (AV) platoon control under uncertain dynamics and intermittent communication, which remains a critical challenge in intelligent transportation systems. To address these issues, this paper proposes an adaptive consensus tracking control framework for nonlinear multi-agent systems (MASs). The proposed approach integrates backstepping design, a nonlinear sampled-data observer, radial basis function neural networks, and a self-triggered communication mechanism. The radial basis function neural networks approximate unknown nonlinearities and time-varying disturbances, thereby enhancing system robustness. A distributed observer estimates neighboring states based on limited and intermittent measurements, thereby reducing dependence on continuous communication. Moreover, self-triggered mechanism is developed to determine triggering instants, guaranteeing a strictly positive minimum inter-event time and preventing Zeno behavior. The theoretical analysis proves that all closed-loop signals are uniformly ultimately bounded (UUB), and tracking errors converge to a compact set. Simulation results demonstrate that the proposed approach achieves high robustness, adaptability, and communication efficiency, making it suitable for real-world networked vehicle systems.
Read the full abstract

All authors Zihan Li, Ziming Wang, Chenning Liu, Xin Wang

Image and Video Processing · Cross-listed from cs.CV

LinMU: Multimodal Understanding Made Linear

Hongjie Wang and Niraj K. Jha

Modern Vision-Language Models (VLMs) achieve impressive performance but are limited by the quadratic complexity of self-attention, which prevents their deployment on edge devices and makes their understanding of high-resolution images and long-context videos prohibitively expensive. To address this challenge, we introduce LinMU (Linear-complexity Multimodal Understanding), a VLM design that achieves linear complexity for the language model decoder without using any quadratic-complexity modules while maintaining the performance of global-attention-based VLMs. LinMU replaces every self-attention layer in the language model decoder with an M-MATE block: a dual-branch module that combines a bidirectional state-space model for global context (Flex-MA branch) with localized Swin-style window attention (Local-Swin branch) for adjacent correlations. To transform a pre-trained VLM into the LinMU architecture, we propose a three-stage distillation framework that (i) initializes both branches with self-attention weights and trains the Flex-MA branch alone, (ii) unfreezes the Local-Swin branch and fine-tunes it jointly with the Flex-MA branch, and (iii) unfreezes the remaining blocks and fine-tunes them using LoRA adapters, while regressing on hidden states and token-level logits of the frozen VLM teacher. On MMMU, TextVQA, LongVideoBench, Video-MME, and other benchmarks, LinMU matches the performance of teacher models, yet reduces Time-To-First-Token (TTFT) by up to 2.7$\times$ and improves token throughput by up to 9.0$\times$ on minute-length videos. Ablations confirm the importance of each distillation stage and the necessity of the two branches of the M-MATE block. The proposed framework demonstrates that state-of-the-art multimodal reasoning can be achieved without quadratic attention, thus opening up avenues for long-context VLMs that can deal with high-resolution images and long videos.
Read the full abstract

Saturday 3 January

Systems and Control

Simple yet Effective Anti-windup Techniques for Amplitude and Rate Saturation: An Autonomous Underwater Vehicle Case Study

Pouria Sarhadi

Actuator amplitude and rate saturation (A&RSat), together with their consequent windup problem, have long been recognised as challenges in control systems. Anti-windup (AW) solutions have been developed over the past decades, which can generally be categorised into two main groups: classical and modern anti-windup (CAW and MAW) approaches. Classical methods have provided simple and effective results, mainly addressing amplitude saturation. In contrast, modern approaches offer powerful and theoretically sound solutions capable of handling both amplitude and rate saturations. However, MAW's derivation process often imposes restrictive conditions and can be complex to apply in practical engineering problems. Nevertheless, the literature has paid limited attention (if not entirely ignored) to the potential of simple yet effective CAW schemes that can operate in the presence of both A&RSat elements. This paper revisits this issue and proposes modifications to two well-known controllers: PID and LQI. The obtained results, benchmarked on the REMUS AUV yaw control problem and compared with constrained MPC, indicate that these classical techniques can still provide simple yet effective solutions with comparable performance, at least for SISO systems. These findings may stimulate further research into solutions that achieve comparable performance with only one (or a limited number of) additional tuning parameters and straightforward implementation.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.SD

Diffusion Timbre Transfer Via Mutual Information Guided Inpainting

Ching Ho Lee, Javier Nistal, Stefan Lattner et al. (+2 more)

We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise injection that targets latent channels most informative of instrument identity, and (ii) an early-step clamping mechanism that re-imposes the input's melodic and rhythmic structure during reverse diffusion. The method operates directly on audio latents and is compatible with text/audio conditioning (e.g., CLAP). We discuss design choices,analyze trade-offs between timbral change and structural preservation, and show that simple inference-time controls can meaningfully steer pre-trained models for style-transfer use cases.
Read the full abstract

All authors Ching Ho Lee, Javier Nistal, Stefan Lattner, Marco Pasini, George Fazekas

Signal Processing

Pinching Antennas in Blockage-Aware Environments: Modeling, Design, and Optimization

Ximing Xie, Fang Fang, Zhiguo Ding et al. (+1 more)

Pinching-antenna (PA) systems have recently emerged as a promising member of the flexible-antenna family due to their ability to dynamically establish line-of-sight (LoS) links. While most existing studies assume ideal environments without obstacles, practical indoor deployments are often obstacle-rich, where LoS blockage significantly degrades performance. This paper investigates pinching-antenna systems in blockage-aware environments by developing a deterministic model for cylinder-shaped obstacles that precisely characterizes LoS conditions without relying on stochastic approximations. Based on this model, a special case is first studied where each PA serves a single user and can only be deployed at discrete positions along the waveguide. In this case, the waveguide-user assignment is obtained via the Hungarian algorithm, and PA positions are refined using a surrogate-assisted block-coordinate search. Then, a general case is considered where each PA serves all users and can be continuously placed along the waveguide. In this case, beamforming and PA positions are jointly optimized by a weighted minimum mean square error integrated deep deterministic policy gradient (WMMSE-DDPG) approach to address non-smooth LoS transitions. Simulation results demonstrate that the proposed algorithms significantly improve system throughput and LoS connectivity compared with benchmark methods. Moreover, the results reveal that pinching-antenna systems can effectively leverage obstacles to suppress co-channel interference, converting potential blockages into performance gains.
Read the full abstract

All authors Ximing Xie, Fang Fang, Zhiguo Ding, Xianbin Wang

Systems and Control

An Energy-Efficient Smart Bus Transport Management System with Blind-Spot Collision Detection Ability

Md. Sadman Haque, Zobaer Ibn Razzaque, Robiul Awoul Robin et al. (+2 more)

Public bus transport systems in developing countries often suffer from a lack of real-time location updates and for users, making commuting inconvenient and unreliable for passengers. Furthermore, stopping at undesired locations rather than designated bus stops creates safety risks and contributes to roadblocks, often causing traffic congestion. Additionally, issues such as blind spots, along with a lack of following traffic laws, increase the chances of accidents. In this work, we address these challenges by proposing a smart public bus system along with intelligent bus stops that enhance safety, efficiency, and sustainability. Our approach includes a deep learning-based blind-spot warning system to help drivers avoid accidents with automated bus-stop detection to accurately identify bus stops, improving transit efficiency. We also introduce IoT-based solar-powered smart bus stops that show real-time passenger counts, along with an RFID-based card system to track where passengers board and exit. A smart door system ensures safer and more organised boarding, while real-time bus tracking keeps passengers informed. To connect all these features, we use an HTTP-based server for seamless communication between the interconnected network systems. Our proposed system demonstrated approximately 99% efficiency in real-time blind spot detection while stopping precisely at the bus stops. Furthermore, the server showed real-time location updates both to the users and at the bus stops, enhancing commuting efficiency. The proposed energy-efficient bus stop demonstrated 12.71kWh energy saving, promoting sustainable architecture. Full implementation and source code are available at: https://github.com/sadman-adib/MoveMe-IoT
Read the full abstract

All authors Md. Sadman Haque, Zobaer Ibn Razzaque, Robiul Awoul Robin, Fahim Hafiz, Riasat Azim

Image and Video Processing

Seamlessly Natural: Image Stitching with Natural Appearance Preservation

Gaetane Lorna N. Tchana, Damaris Belle M. Fotso, Antonio Hendricks et al. (+1 more)

This paper introduces SENA (SEamlessly NAtural), a geometry-driven image stitching approach that prioritizes structural fidelity in challenging real-world scenes characterized by parallax and depth variation. Conventional image stitching relies on homographic alignment, but this rigid planar assumption often fails in dual-camera setups with significant scene depth, leading to distortions such as visible warps and spherical bulging. SENA addresses these fundamental limitations through three key contributions. First, we propose a hierarchical affine-based warping strategy, combining global affine initialization with local affine refinement and smooth free-form deformation. This design preserves local shape, parallelism, and aspect ratios, thereby avoiding the hallucinated structural distortions commonly introduced by homography-based models. Second, we introduce a geometry-driven adequate zone detection mechanism that identifies parallax-minimized regions directly from the disparity consistency of RANSAC-filtered feature correspondences, without relying on semantic segmentation. Third, building upon this adequate zone, we perform anchor-based seamline cutting and segmentation, enforcing a one-to-one geometric correspondence across image pairs by construction, which effectively eliminates ghosting, duplication, and smearing artifacts in the final panorama. Extensive experiments conducted on challenging datasets demonstrate that SENA achieves alignment accuracy comparable to leading homography-based methods, while significantly outperforming them in critical visual metrics such as shape preservation, texture integrity, and overall visual realism.
Read the full abstract

All authors Gaetane Lorna N. Tchana, Damaris Belle M. Fotso, Antonio Hendricks, Christophe Bobda

Systems and Control

Multi-Objective Operational Optimization of Energy Storage Systems in User-Side Microgrids

Jinzhou Xu, Yuanxin Zhuo and Paola Tapia

An operational optimization strategy for microgrid energy storage systems (ESSs) is developed to address practical user-oriented application requirements, and its effectiveness is validated using real-world operational data. First, a fundamental ESS model is established to characterize system dynamics and operational constraints, providing a theoretical basis for optimization. Subsequently, a multi-objective operational optimization framework is formulated to simultaneously minimize electricity cost, reduce carbon emissions, and enhance renewable energy utilization. To ensure computational efficiency and scalability, the commercial optimization solver Gurobi is employed. The proposed strategy is evaluated using actual microgrid operational data, demonstrating that the developed ESS model accurately represents real system constraints. Compared with existing user operational strategies, the proposed approach achieves an average reduction of 13.47% in electricity cost. Moreover, by dynamically adjusting the weighting factors of the multi-objective formulation, the strategy enables flexible operational modes and significantly improves adaptability to varying operating scenarios. In addition, the proposed framework provides decision support for user-side microgrids participating in surplus electricity feed-in policies. The main contribution of this work lies in its user-centric optimization design, which enhances operational flexibility and scenario adaptability through multi-objective weight allocation, offering a practical and scalable solution for real-world microgrid ESS operation.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.SD

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection

Jiajie Zhu, Xia Du, Xiaoyuan Liu et al. (+4 more)

The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its widespread integration across various applications. However, this surge in usage also highlights a critical issue: audio data is highly vulnerable to unauthorized exposure and analysis, posing significant privacy risks for businesses and individuals. This paper introduces an Information-Obfuscation Reversible Adversarial Example (IO-RAE) framework, the pioneering method designed to safeguard audio privacy using reversible adversarial examples. IO-RAE leverages large language models to generate misleading yet contextually coherent content, effectively preventing unauthorized eavesdropping by humans and Automatic Speech Recognition (ASR) systems. Additionally, we propose the Cumulative Signal Attack technique, which mitigates high-frequency noise and enhances attack efficacy by targeting low-frequency signals. Our approach ensures the protection of audio data without degrading its quality or our ability. Experimental evaluations demonstrate the superiority of our method, achieving a targeted misguidance rate of 96.5% and a remarkable 100% untargeted misguidance rate in obfuscating target keywords across multiple ASR models, including a commercial black-box system from Google. Furthermore, the quality of the recovered audio, measured by the Perceptual Evaluation of Speech Quality score, reached 4.45, comparable to high-quality original recordings. Notably, the recovered audio processed by ASR systems exhibited an error rate of 0%, indicating nearly lossless recovery. These results highlight the practical applicability and effectiveness of our IO-RAE framework in protecting sensitive audio privacy.
Read the full abstract

All authors Jiajie Zhu, Xia Du, Xiaoyuan Liu, Jizhe Zhou, Qizhen Xu, Zheng Lin, Chi-Man Pun

Signal Processing

A 2.5 $\mu$W 30 nV/$\surd$Hz Instrumentation Amplifier for Bioimpedance Sensors with Source Degenerated Current Mirror and DTMOS Transistor

Yu Xue and Kwantae Kim

This paper proposes a low-power and low-noise instrumentation amplifier (IA) tailored for bioimpedance sensing applications. The design originates from a gain-boosted flipped voltage follower (FVF) transconductance (TC) stage and integrates two complementary circuit techniques to improve the noise performance. To achieve an optimal balance between input-referred noise and available voltage headroom, a source-degenerated current mirror (SDCM) is adopted, resulting in reducing the input-referred noise by 7.95% compared with a conventional current mirror structure. In addition, a dynamic threshold MOSFET (DTMOS) scheme is employed to enhance the effective transconductance, leading to a further 11.66% reduction in input-referred noise. Simulated in a 28 nm CMOS process demonstrate that the proposed IA achieves an input-referred noise floor of 30 nV/$\surd$Hz and a bandwidth of 1.44 MHz, while consuming only 2.5 $\mu$W from a 0.8 V supply. Compared to the baseline design, the proposed approach achieves a 32.4% reduction in power consumption without degrading noise performance. The complete design parameters are open-sourced in this paper, to ensure reproducibility and facilitate future developments.
Read the full abstract

Signal Processing

NeuroSSM: Multiscale Differential State-Space Modeling for Context-Aware fMRI Analysis

Furkan Genç, Boran İsmet Macun, Sait Sarper Özaslan et al. (+2 more)

Accurate fMRI analysis requires sensitivity to temporal structure across multiple scales, as BOLD signals encode cognitive processes that emerge from fast transient dynamics to slower, large-scale fluctuations. Existing deep learning (DL) approaches to temporal modeling face challenges in jointly capturing these dynamics over long fMRI time series. Among current DL models, transformers address long-range dependencies by explicitly modeling pairwise interactions through attention, but the associated quadratic computational cost limits effective integration of temporal dependencies across long fMRI sequences. Selective state-space models (SSMs) instead model long-range temporal dependencies implicitly through latent state evolution in a dynamical system, enabling efficient propagation of dependencies over time. However, recent SSM-based approaches for fMRI commonly operate on derived functional connectivity representations and employ single-scale temporal processing. These design choices constrain the ability to jointly represent fast transient dynamics and slower global trends within a single model. We propose NeuroSSM, a selective state-space architecture designed for end-to-end analysis of raw BOLD signals in fMRI time series. NeuroSSM addresses the above limitations through two complementary design components: a multiscale state-space backbone that captures fast and slow dynamics concurrently, and a parallel differencing branch that increases sensitivity to transient state changes. Experiments on clinical and non-clinical datasets demonstrate that NeuroSSM achieves competitive performance and efficiency against state-of-the-art fMRI analysis methods.
Read the full abstract

All authors Furkan Genç, Boran İsmet Macun, Sait Sarper Özaslan, Emine U. Saritas, Tolga Çukur

Image and Video Processing · Cross-listed from cs.CV

Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity

Zhang Chen, Shuai Wan, Yuezhe Zhang et al. (+3 more)

The unstructured and irregular nature of points poses a significant challenge for accurate point cloud quality assessment (PCQA), particularly in establishing accurate perceptual feature correspondence. To tackle this, we propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM). Unlike traditional point-to-point matching, MS-ISSM utilizes radial basis function (RBF) to represent local features continuously, transforming distortion measurement into a comparison of implicit function coefficients. This approach effectively circumvents matching errors inherent in irregular data. Additionally, we propose a ResGrouped-MLP quality assessment network, which robustly maps multi-scale feature differences to perceptual scores. The network architecture departs from traditional flat multi-layer perceptron (MLP) by adopting a grouped encoding strategy integrated with residual blocks and channel-wise attention mechanisms. This hierarchical design allows the model to preserve the distinct physical semantics of luma, chroma, and geometry while adaptively focusing on the most salient distortion features across High, Medium, and Low scales. Experimental results on multiple benchmarks demonstrate that MS-ISSM outperforms state-of-the-art metrics in both reliability and generalization. The source code is available at: https://github.com/ZhangChen2022/MS-ISSM.
Read the full abstract

All authors Zhang Chen, Shuai Wan, Yuezhe Zhang, Siyu Ren, Fuzheng Yang, Junhui Hou

Signal Processing · Cross-listed from cs.IT

On the Structure of the Optimal Detector for Sub-THz Multi-Hop Relays with Unknown Prior: Over-the-Air Diffusion

Ozgur Ercetin and Mohaned Chraiti

Amplify and forward (AF) relaying is a viable strategy to extend the coverage of sub-terahertz (sub-THz) links, but inevitably propagates noise, leading to cumulative degradation across multiple hops. At the receiver, optimal decoding is desirable, yet challenging under non-Gaussian input distributions (video, voice, etc), for which neither the Minimum Mean Square Error (MMSE) estimator nor the mutual information admits a closed form. A further open question is whether knowledge of Channel State Information (CSI) and noise statistics at the intermediate relays is necessary for optimal detection. Aiming for an optimal decoder, this paper introduces a new framework that interprets the AF relay chain as a variance-preserving diffusion process and employs denoising diffusion implicit models (DDIMs) for signal recovery. We show that each AF hop is mathematically equivalent to a diffusion step with hop-dependent attenuation and noise injection. Consequently, the entire multi-hop chain collapses to an equivalent Gaussian channel fully described by only three real scalars per block: the cumulative complex gain and the effective noise variance. At the receiver, these end-to-end sufficient statistics define a matched reverse schedule that guides the DDIM-based denoiser, enabling near-optimal Bayesian decoding without per-hop CSI. We establish the information-theoretic foundation of this equivalence, proving that decoding performance depends solely on the final effective Signal-to-Noise-Ratio (SNR), regardless of intermediate noise/channel allocation or prior distribution. Simulations under AWGN and Rician fading confirm that the proposed AF-DDIM decoder reduces mean-squared error, symbol error rate, and bit error rate, particularly at moderate SNRs and for higher-order constellations.
Read the full abstract

Systems and Control

Adaptive Scheduling: A Reinforcement Learning Whittle Index Approach for Wireless Sensor Networks

Sokipriala Jonah, Seong Ki Yoo and Saurav Sthapit

We propose a reinforcement learning based scheduling framework for Restless Multi-Armed Bandit (RMAB) problems, centred on a Whittle Index Q-Learning policy with Upper Confidence Bound (UCB) exploration, referred to as WIQL-UCB. Unlike existing approaches that rely on fixed or adaptive epsilon-greedy strategies and require careful hyperparameter tuning, the proposed method removes problem-specific tuning and is therefore more generalisable across diverse RMAB settings. We evaluate WIQL-UCB on standard RMAB benchmarks and on a practical sensor scheduling application based on the Age of Incorrect Information (AoII), using an edge-based state estimation scheme that requires no prior knowledge of system dynamics. Experimental results show that WIQL-UCB achieves near-optimal performance while significantly improving computational and memory efficiency. For a representative problem size of N = 15 and M = 3, the proposed method requires only around 600 bytes of memory, compared with several kilobytes for tabular Q-learning and hundreds of kilobytes to megabytes for deep reinforcement learning baselines. In addition, WIQL-UCB achieves sub-millisecond per-decision runtimes and is several times faster than deep reinforcement learning approaches, while maintaining competitive performance. Overall, these results demonstrate that WIQL-UCB consistently outperforms both non-Whittle-based and Whittle-index learning baselines across a wide range of RMAB settings.
Read the full abstract

Systems and Control

Transient Power Allocation Control Scheme for Hybrid Hydrogen Electrolyzer-Supercapacitor System with Autonomous Inertia Response

Pengfeng Lin, Guangjie Gao, Jianjun Ma et al. (+3 more)

This paper proposes a hybrid hydrogen electrolyzer-supercapacitor system (HESS) with a novel control strategy for renewable-dominant power grids. The HESS consists of alkaline electrolyzers (AEL), proton exchange membrane electrolyzers (PEMEL), and supercapacitors (SC). The interfacing inverters between HESS and power grid are regulated by an inertia emulation control strategy. From HESS, AEL is with conventional DC power control, whereas PEMEL and SC are designed with the proposed dynamic inertia control and capacitive inertia control, respectively. Benefitting from the coordination of three controls, within the HESS, high-frequency transient power components are autonomously handled by SC, stable frequency power components are regulated by PEMEL, and low-frequency steady-state power is addressed by AEL, characterized by low operational gains and longer lifetimes. SC delivers transient power, significantly alleviating energy losses on electrolyzers and achieving adequate inertia recovery capabilities while requiring no additional communication. Implementing SOC recovery control enables the SC to withstand more than three times more stability discharge cycles compared to an SC without SOC recovery. Furthermore, a large-signal mathematical model based on mixed potential theory is established, providing clear stability boundaries for system parameters. Dynamic analyses theoretically verify system feasibility, and extensive hardware-in-the-loop experimental results fully validate the proposed HESS along with the corresponding transient power allocation controls.
Read the full abstract

All authors Pengfeng Lin, Guangjie Gao, Jianjun Ma, Miao Zhu, Xinan Zhang, Ahmed Abu-Siada

Systems and Control

Tube-based robust nonlinear model predictive control of anaerobic co-digestion

Davide Carecci, Laurent Dewasme, Alessio La Bella et al. (+2 more)

To match the growing demand for bio-methane production, anaerobic digesters need to embrace the co-digestion of different feedstocks; in addition, to improve the techno-economic performance, an optimal and time-varying adaptation of the input diet is required. These operation modes constitute a very hard challenge for the limited instrumentation and control equipment typically installed aboard full-scale plants. A model-based predictive approach may be able to handle such control problem, but the identification of reliable predictive models is limited by the low information content typical of the data available from full-scale plants' operations, which entail high parametric uncertainty. In this work, the application of a tube-based robust nonlinear model predictive control (NMPC) is proposed to regulate bio-methane production over a period of diet change in time, while warranting safe operation and dealing with uncertainties. In view of its upcoming validation on a true small pilot-scale plant, the NMPC capabilities are assessed via numerical simulations designed to resemble as much as possible the experimental setup, along with some practical final considerations.
Read the full abstract

All authors Davide Carecci, Laurent Dewasme, Alessio La Bella, Gianni Ferretti, Alain Vande Wouwer

Signal Processing

Towards a Theoretical Framework for Robust Node Deployment in Cooperative ISAC Networks

Haojin Li, Kaiqian Qu, Chen Sun et al. (+4 more)

This paper investigates node deployment strategies for robust multi-node cooperative localization in integrated sensing and communication (ISAC) networks.We first analyze how steering vector correlation across different positions affects localization performance and introduce a novel distance-weighted correlation metric to characterize this effect. Building upon this insight, we propose a deployment optimization framework that minimizes the maximum weighted steering vector correlation by optimizing simultaneously node positions and array orientations, thereby enhancing worst-case network robustness. Then, a genetic algorithm (GA) is developed to solve this min-max optimization, yielding optimized node positions and array orientations. Extensive simulations using both multiple signal classification (MUSIC) and neural-network (NN)-based localization validate the effectiveness of the proposed methods, demonstrating significant improvements in robust localization performance.
Read the full abstract

All authors Haojin Li, Kaiqian Qu, Chen Sun, Anbang Zhang, Xiaoxue Wang, Wenqi Zhang, Haijun Zhang