Papers

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

Electrical Engineering and Systems Science

eess Watch Electrical Engineering and Systems Science

Wednesday 15 October

Systems and Control

Multipolar dynamics of social segregation: Data validation on Swedish vaccination statistics

Luka Baković, David Ohlin and Emma Tegling

We perform a validation analysis on the multipolar model of opinion dynamics. A general methodology for using the model on datasets of two correlated variables is proposed and tested using data on the relationship between COVID-19 vaccination rates and political participation in Sweden. The model is shown to successfully capture the opinion segregation demonstrated by the data and spatial correlation of biases is demonstrated as necessary for the result. A mixing of the biases on the other hand leads to a more homogeneous opinion distribution, and greater penetration of the majority opinion, which here corresponds to a decision to vote or vaccinate.

Read the full abstract

Systems and Control · Cross-listed from quant-ph

Performance Comparison of Gate-Based and Adiabatic Quantum Computing for AC Power Flow Problem

Zeynab Kaseb, Matthias Moller, Peter Palensky et al. (+1 more)

We present the first direct comparison between gate-based quantum computing (GQC) and adiabatic quantum computing (AQC) paradigms for solving the AC power flow (PF) equations. The PF problem is reformulated as a combinatorial optimization problem. For the GQC approach, the Quantum Approximate Optimization Algorithm (QAOA) is employed, while for the AQC approach, the problem is formulated as an Ising model. Numerical experiments on a 4-bus test system evaluate solution accuracy and computational performance. Results obtained using QAOA are benchmarked against those produced by D-Wave's Advantage system and Fujitsu's latest-generation Digital Annealer, implemented through the Quantum-Inspired Integrated Optimization (QIIO) software. The findings provide quantitative insights into the performance trade-offs, scalability, and practical viability of GQC and AQC paradigms for PF analysis, highlighting the potential of quantum optimization algorithms to address the computational challenges associated with the operation of modern electricity grids in the fault-tolerant era.

Read the full abstract

All authors Zeynab Kaseb, Matthias Moller, Peter Palensky, Pedro P. Vergara

Audio and Speech Processing

Towards Multimodal Query-Based Spatial Audio Source Extraction

Chenxin Yu, Hao Ma, Xu Li et al. (+4 more)

Query-based audio source extraction seeks to recover a target source from a mixture conditioned on a query. Existing approaches are largely confined to single-channel audio, leaving the spatial information in multi-channel recordings underexploited. We introduce a query-based spatial audio source extraction framework for recovering dry target signals from first-order ambisonics (FOA) mixtures. Our method accepts either an audio prompt or a text prompt as condition input, enabling flexible end-to-end extraction. The core of our proposed model lies in a tri-axial Transformer that jointly models temporal, frequency, and spatial channel dependencies. The model uses contrastive language-audio pretraining (CLAP) embeddings to enable unified audio-text conditioning via feature-wise linear modulation (FiLM). To eliminate costly annotations and improve generalization, we propose a label-free data pipeline that dynamically generates spatial mixtures and corresponding targets for training. The result of our experiment with high separation quality demonstrates the efficacy of multimodal conditioning and tri-axial modeling. This work establishes a new paradigm for high-fidelity spatial audio separation in immersive applications.

Read the full abstract

All authors Chenxin Yu, Hao Ma, Xu Li, Xiao-Lei Zhang, Mingjie Shao, Chi Zhang, Xuelong Li

Audio and Speech Processing

Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses

Sungnyun Kim, Kangwook Jang, Sungwoo Cho et al. (+3 more)

This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR) that reasons over modality-specific evidences directly in the language space. Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models. To maximize the effectiveness of DualHyp, we further introduce RelPrompt, a noise-aware guidance mechanism that provides modality-grounded prompts to the LLM. RelPrompt offers the temporal reliability of each modality stream, guiding the model to dynamically switch its focus between ASR and VSR hypotheses for an accurate correction. Under various corruption scenarios, our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain. To facilitate research within our DualHyp framework, we release the code and the dataset comprising ASR and VSR hypotheses at https://github.com/sungnyun/dualhyp.

Read the full abstract

All authors Sungnyun Kim, Kangwook Jang, Sungwoo Cho, Joon Son Chung, Hoirin Kim, Se-Young Yun

Systems and Control

Partitioned Scheduling for DAG Tasks Considering Probabilistic Execution Time

Fuma Omori, Atsushi Yano and Takuya Azumi

Autonomous driving systems, critical for safety, require real-time guarantees and can be modeled as DAGs. Their acceleration features, such as caches and pipelining, often result in execution times below the worst-case. Thus, a probabilistic approach ensuring constraint satisfaction within a probability threshold is more suitable than worst-case guarantees for these systems. This paper considers probabilistic guarantees for DAG tasks by utilizing the results of probabilistic guarantees for single processors, which have been relatively more advanced than those for multi-core processors. This paper proposes a task set partitioning method that guarantees schedulability under the partitioned scheduling. The evaluation on randomly generated DAG task sets demonstrates that the proposed method schedules more task sets with a smaller mean analysis time compared to existing probabilistic schedulability analysis for DAGs. The evaluation also compares four bin-packing heuristics, revealing Item-Centric Worst-Fit-Decreasing schedules the most task sets.

Read the full abstract

Image and Video Processing

DIGITWISE: Digital Twin-based Modeling of Adaptive Video Streaming Engagement

Emanuele Artioli, Farzad Tashtarian and Christian Timmerer

As the popularity of video streaming entertainment continues to grow, understanding how users engage with the content and react to its changes becomes a critical success factor for every stakeholder. User engagement, i.e., the percentage of video the user watches before quitting, is central to customer loyalty, content personalization, ad relevance, and A/B testing. This paper presents DIGITWISE, a digital twin-based approach for modeling adaptive video streaming engagement. Traditional adaptive bitrate (ABR) algorithms assume that all users react similarly to video streaming artifacts and network issues, neglecting individual user sensitivities. DIGITWISE leverages the concept of a digital twin, a digital replica of a physical entity, to model user engagement based on past viewing sessions. The digital twin receives input about streaming events and utilizes supervised machine learning to predict user engagement for a given session. The system model consists of a data processing pipeline, machine learning models acting as digital twins, and a unified model to predict engagement. DIGITWISE employs the XGBoost model in both digital twins and unified models. The proposed architecture demonstrates the importance of personal user sensitivities, reducing user engagement prediction error by up to 5.8% compared to non-user-aware models. Furthermore, DIGITWISE can optimize content provisioning and delivery by identifying the features that maximize engagement, providing an average engagement increase of up to 8.6%.

Read the full abstract

Audio and Speech Processing

Acoustic Teleportation via Disentangled Neural Audio Codec Representations

Philipp Grundhuber, Mhd Modar Halimeh and Emanuël A. P. Habets

This paper presents an approach for acoustic teleportation by disentangling speech content from acoustic environment characteristics in neural audio codec representations. Acoustic teleportation transfers room characteristics between speech recordings while preserving content and speaker identity. We build upon previous work using the EnCodec architecture, achieving substantial objective quality improvements with non-intrusive ScoreQ scores of 3.03, compared to 2.44 for prior methods. Our training strategy incorporates five tasks: clean reconstruction, reverberated reconstruction, dereverberation, and two variants of acoustic teleportation. We demonstrate that temporal downsampling of the acoustic embedding significantly degrades performance, with even 2x downsampling resulting in a statistically significant reduction in quality. The learned acoustic embeddings exhibit strong correlations with RT60. Effective disentanglement is demonstrated using t-SNE clustering analysis, where acoustic embeddings cluster by room while speech embeddings cluster by speaker.

Read the full abstract

Signal Processing · Cross-listed from cs.IT

Movable and Reconfigurable Antennas for 6G: Unlocking Electromagnetic-Domain Design and Optimization

Lipeng Zhu, Haobin Mao, Ge Yan et al. (+3 more)

The growing demands of 6G mobile communication networks necessitate advanced antenna technologies. Movable antennas (MAs) and reconfigurable antennas (RAs) enable dynamic control over antenna's position, orientation, radiation, polarization, and frequency response, introducing rich electromagnetic-domain degrees of freedom for the design and performance enhancement of wireless systems. This article overviews their application scenarios, hardware architectures, and design methods. Field test and simulation results highlight their performance benefits over conventional fixed/non-reconfigurable antennas.

Read the full abstract

All authors Lipeng Zhu, Haobin Mao, Ge Yan, Wenyan Ma, Zhenyu Xiao, Rui Zhang

Image and Video Processing

Approximate Bilevel Graph Structure Learning for Histopathology Image Classification

Sudipta Paul, Amanda W. Lund, George Jour et al. (+2 more)

The structural and spatial arrangements of cells within tissues represent their functional states, making graph-based learning highly suitable for histopathology image analysis. Existing methods often rely on fixed graphs with predefined edges, limiting their ability to capture the true biological complexity of tissue interactions. In this work, we propose ABiG-Net (Approximate Bilevel Optimization for Graph Structure Learning via Neural Networks), a novel framework designed to learn optimal interactions between patches within whole slide images (WSI) or large regions of interest (ROI) while simultaneously learning discriminative node embeddings for the downstream image classification task. Our approach hierarchically models the tissue architecture at local and global scales. At the local scale, we construct patch-level graphs from cellular orientation within each patch and extract features to quantify local structures. At the global scale, we learn an image-level graph that captures sparse, biologically meaningful connections between patches through a first-order approximate bilevel optimization strategy. The learned global graph is optimized in response to classification performance, capturing the long-range contextual dependencies across the image. By unifying local structural information with global contextual relationships, ABiG-Net enhances interpretability and downstream performance. Experiments on two histopathology datasets demonstrate its effectiveness: on the Extended CRC dataset, ABiG-Net achieves 97.33 $\pm$ 1.15 % accuracy for three-class colorectal cancer grading and 98.33 $\pm$ 0.58 % for binary classification; on the melanoma dataset, it attains 96.27 $\pm$ 0.74 % for tumor-lymphocyte ROI classification.

Read the full abstract

All authors Sudipta Paul, Amanda W. Lund, George Jour, Iman Osman, Bülent Yener

Systems and Control

Safe Driving in Occluded Environments

Zhuoyuan Wang, Tongyao Jia, Pharuj Rajborirug et al. (+5 more)

Ensuring safe autonomous driving in the presence of occlusions poses a significant challenge in its policy design. While existing model-driven control techniques based on set invariance can handle visible risks, occlusions create latent risks in which safety-critical states are not observable. Data-driven techniques also struggle to handle latent risks because direct mappings from risk-critical objects in sensor inputs to safe actions cannot be learned without visible risk-critical objects. Motivated by these challenges, in this paper, we propose a probabilistic safety certificate for latent risk. Our key technical enabler is the application of probabilistic invariance: It relaxes the strict observability requirements imposed by set-invariance methods that demand the knowledge of risk-critical states. The proposed techniques provide linear action constraints that confine the latent risk probability within tolerance. Such constraints can be integrated into model predictive controllers or embedded in data-driven policies to mitigate latent risks. The proposed method is tested using the CARLA simulator and compared with a few existing techniques. The theoretical and empirical analysis jointly demonstrate that the proposed methods assure long-term safety in real-time control in occluded environments without being overly conservative and with transparency to exposed risks.

Read the full abstract

All authors Zhuoyuan Wang, Tongyao Jia, Pharuj Rajborirug, Neeraj Ramesh, Hiroyuki Okuda, Tatsuya Suzuki, Soummya Kar, Yorie Nakahira

Signal Processing

Constellation Design in OFDM-ISAC over Data Payloads: From MSE Analysis to Experimentation

Kawon Han, Kaitao Meng, Alexandra Chatzicharistou et al. (+1 more)

Orthogonal frequency division multiplexing (OFDM) is one of the most widely adopted waveforms for integrated sensing and communication (ISAC) systems, owing to its high spectral efficiency and compatibility with modern communication standards. This paper investigates the sensing performance of OFDM-based ISAC for multi-target delay (range) estimation under specific radar receiver processing schemes. An estimation-theoretic framework is developed to characterize sensing performance with random communication payloads. We establish the fundamental limit of delay estimation accuracy by deriving the closed-form expression of the mean-square error (MSE) achieved using matched filtering (MF) and reciprocal filtering (RF) receivers. The results show that, in multi-target scenarios, the impact of signal constellations on the delay estimation MSE differs across receivers: MF performance depends on the fourth-order moment of the zero-mean, unit-power constellation in the presence of multiple targets, whereas RF performance depends on its inverse second-order moment, irrespective of the number of targets. Building on this analysis, we present a ISAC constellation design under specific receiver architecture that brings a receiver-dependent flexible trade-off between sensing and communication in OFDM-ISAC systems. The theoretical findings are validated through simulations and proof-of-concept experiments, and also the sensing and communication performance trade-off is experimentally shown with the proposed constellation design.

Read the full abstract

All authors Kawon Han, Kaitao Meng, Alexandra Chatzicharistou, Christos Masouros

Systems and Control

Decision-dependent Robust Charging Infrastructure Planning for Light-duty Truck Electrification at Industrial Sites

Yifu Ding, Ruicheng Ao, Pablo Duenas-Martinez et al. (+1 more)

Many industrial sites and digital logistics platforms rely on diesel-powered light-duty trucks to transport workers and small-scale facilities, which results in a significant amount of greenhouse gas emissions (GHGs). To address this, we develop a robust model for planning charging infrastructure to electrify light-duty trucks at industrial sites. The model is formulated as a mixed-integer linear program (MILP) that optimizes the charging infrastructure selection (across multiple charger types and locations) and determines charging schedules for each truck based on the selected infrastructure. Given the strict stop times and schedules at industrial sites, we introduce a scheduling-with-abandonment problem in which trucks forgo charging if their waiting time exceeds a maximum threshold. We further incorporate the impacts of overnight charging and range anxiety on drivers' waiting and abandonment behaviors. To model stochastic, heterogeneous parking durations, we classified trucks using machine learning (ML) methods based on contextual and time-location features. We then constructed decision-dependent, feature-driven robust uncertainty sets in which parking-time variability varies flexibly with drivers' charging choices. These feature-driven sets are applied to two robust optimization formulations with decision-dependent uncertainty (RO-DDU), resulting in distinct outcomes and managerial implications. We conduct a case study at an open-pit mining site to plan charger installations across eight charging zones, serving approximately 200 trucks. By decomposing the problem into a short rolling horizon or using a heuristic approach for the full-year or representative-day dataset, the model achieves an optimality gap of less than 0.1% under diverse uncertainty scenarios.

Read the full abstract

All authors Yifu Ding, Ruicheng Ao, Pablo Duenas-Martinez, Thomas Magnanti

Signal Processing · Cross-listed from cs.LG

A Semi-amortized Lifted Learning-to-Optimize Masked (SALLO-M) Transformer Model for Scalable and Generalizable Beamforming

Yubo Zhang, Xiao-Yang Liu and Xiaodong Wang

We develop an unsupervised deep learning framework for real-time scalable and generalizable downlink beamforming in multi-user multiple-input single-output (MU-MISO) systems. The proposed semi-amortized lifted learning-to-optimize (SALLO) framework employs a multi-layer Transformer to iteratively refine an auxiliary variable and the beamformer solution, with a few projected gradient ascent steps at each layer. A key feature of our SALLO Transformer model is that it can handle varying numbers of users and antennas, enabled by a user-antenna dual tokenization and a structured sample/attention masking scheme, leading to generalization across different configurations without retraining. To improve convergence and robustness, we introduce three training strategies: (a) sliding-window training to stabilize gradient propagation, (b) curriculum learning with random masking to enable user-antenna configuration generalization and prevent poor early-stage convergence, and (c) sample replay to mitigate catastrophic forgetting during multi-stage training. Ablation studies validate several key architecture designs and show that the enhanced training scheme improves both generalizability and solution quality. Simulation results over both Gaussian and sparse channels show that the proposed scheme consistently outperforms existing deep learning baselines across diverse system configurations and channel conditions. The performance gain becomes more pronounced in overloaded regimes, highlighting improved robustness under challenging scenarios. Furthermore, our scheme surpasses the WMMSE benchmark in underloaded systems and even in overloaded systems when the overloading factor is below certain threshold. These gains are achieved with fast inference and a substantially more lightweight model than wireless foundation models.

Read the full abstract

Systems and Control · Cross-listed from cs.LG

Time-Varying Optimization for Streaming Data Via Temporal Weighting

Muhammad Faraz Ul Abrar, Nicolò Michelusi and Erik G. Larsson

Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data through a time-varying optimization lens. Unlike prior works that focus on generic formulations, we introduce a structured, weight-based formulation that explicitly captures the streaming-data origin of the time-varying objective, where at each time step, an agent aims to minimize a weighted average loss over all the past data samples. We focus on two specific weighting strategies: (1) uniform weights, which treat all samples equally, and (2) discounted weights, which geometrically decay the influence of older data. For both schemes, we derive tight bounds on the “tracking error” (TE), defined as the deviation between the model parameter and the time-varying optimum at a given time step, under gradient descent (GD) updates. We show that under uniform weighting, the TE vanishes asymptotically with a $\mathcal{O}(1/t)$ decay rate, whereas discounted weighting incurs a nonzero error floor controlled by the discount factor and the number of gradient updates performed at each time step. Our theoretical findings are validated through numerical simulations.

Read the full abstract

Tuesday 14 October

Signal Processing

StrikeWatch: Wrist-worn Gait Recognition with Compact Time-series Models on Low-power FPGAs

Tianheng Ling, Chao Qian, Peter Zdankin et al. (+2 more)

Running offers substantial health benefits, but improper gait patterns can lead to injuries, particularly without expert feedback. While prior gait analysis systems based on cameras, insoles, or body-mounted sensors have demonstrated effectiveness, they are often bulky and limited to offline, post-run analysis. Wrist-worn wearables offer a more practical and non-intrusive alternative, yet enabling real-time gait recognition on such devices remains challenging due to noisy Inertial Measurement Unit (IMU) signals, limited computing resources, and dependence on cloud connectivity. This paper introduces StrikeWatch, a compact wrist-worn system that performs entirely on-device, real-time gait recognition using IMU signals. As a case study, we target the detection of heel versus forefoot strikes to enable runners to self-correct harmful gait patterns through visual and auditory feedback during running. We propose four compact DL architectures (1D-CNN, 1D-SepCNN, LSTM, and Transformer) and optimize them for energy-efficient inference on two representative embedded Field-Programmable Gate Arrays (FPGAs): the AMD Spartan-7 XC7S15 and the Lattice iCE40UP5K. Using our custom-built hardware prototype, we collect a labeled dataset from outdoor running sessions and evaluate all models via a fully automated deployment pipeline. Our results reveal clear trade-offs between model complexity and hardware efficiency. Evaluated across 12 participants, 6-bit quantized 1D-SepCNN achieves the highest average F1 score of 0.847 while consuming just 0.350 microjoule per inference with a latency of 0.140 ms on the iCE40UP5K running at 20 MHz. This configuration supports up to 13.6 days of continuous inference on a 320 mAh battery. All datasets and code are available in the GitHub repository https://github.com/tianheng-ling/StrikeWatch.

Read the full abstract

All authors Tianheng Ling, Chao Qian, Peter Zdankin, Torben Weis, Gregor Schiele

Signal Processing

Cardi-GPT: An Expert ECG-Record Processing Chatbot

Koustav Mallick, Neel Singh and Mohammedreza Hajiarbabi

Interpreting and communicating electrocardiogram (ECG) findings are crucial yet challenging tasks in cardiovascular diagnosis, traditionally requiring significant expertise and precise clinical communication. This paper introduces Cardi-GPT, an advanced expert system designed to streamline ECG interpretation and enhance clinical communication through deep learning and natural language interaction. Cardi-GPT employs a 16-residual-block convolutional neural network (CNN) to process 12-lead ECG data, achieving a weighted accuracy of 0.6194 across 24 cardiac conditions. A novel fuzzification layer converts complex numerical outputs into clinically meaningful linguistic categories, while an integrated chatbot interface facilitates intuitive exploration of diagnostic insights and seamless communication between healthcare providers. The system was evaluated on a diverse dataset spanning six hospitals across four countries, demonstrating superior performance compared to baseline models. Additionally, Cardi-GPT achieved an impressive overall response quality score of 73%, assessed using a comprehensive evaluation framework that measures coverage, grounding, and coherence. By bridging the gap between intricate ECG data interpretation and actionable clinical insights, Cardi-GPT represents a transformative innovation in cardiovascular healthcare, promising to improve diagnostic accuracy, clinical workflows, and patient outcomes across diverse medical settings.

Read the full abstract

Audio and Speech Processing

Switchboard-Affect: Emotion Perception Labels from Conversational Speech

Amrit Romana, Jaya Narain, Tien Dung Tran et al. (+4 more)

Understanding the nuances of speech emotion dataset curation and labeling is essential for assessing speech emotion recognition (SER) model potential in real-world applications. Most training and evaluation datasets contain acted or pseudo-acted speech (e.g., podcast speech) in which emotion expressions may be exaggerated or otherwise intentionally modified. Furthermore, datasets labeled based on crowd perception often lack transparency regarding the guidelines given to annotators. These factors make it difficult to understand model performance and pinpoint necessary areas for improvement. To address this gap, we identified the Switchboard corpus as a promising source of naturalistic conversational speech, and we trained a crowd to label the dataset for categorical emotions (anger, contempt, disgust, fear, sadness, surprise, happiness, tenderness, calmness, and neutral) and dimensional attributes (activation, valence, and dominance). We refer to this label set as Switchboard-Affect (SWB-Affect). In this work, we present our approach in detail, including the definitions provided to annotators and an analysis of the lexical and paralinguistic cues that may have played a role in their perception. In addition, we evaluate state-of-the-art SER models, and we find variable performance across the emotion categories with especially poor generalization for anger. These findings underscore the importance of evaluation with datasets that capture natural affective variations in speech. We release the labels for SWB-Affect to enable further analysis in this domain.

Read the full abstract

All authors Amrit Romana, Jaya Narain, Tien Dung Tran, Andrea Davis, Jason Fong, Ramya Rasipuram, Vikramjit Mitra

Image and Video Processing

Millimeter Wave Inverse Pinhole Imaging

Akarsh Prabhakara, Yawen Liu, Aswin C. Sankaranarayanan et al. (+2 more)

Millimeter wave (mmWave) radars are popular for perception in vision-denied contexts due to their compact size. This paper explores emerging use-cases that involve static mount or momentarily-static compact radars, for example, a hovering drone. The key challenge with static compact radars is that their limited form-factor also limits their angular resolution. This paper presents Umbra, a mmWave high resolution imaging system, that introduces the concept of rotating mmWave "inverse pinholes" for angular resolution enhancement. We present the imaging system model, design, and evaluation of mmWave inverse pinholes. The inverse pinhole is attractive for its lightweight nature, which enables low-power rotation, upgrading static-mount radars. We also show how propellers in aerial vehicles act as natural inverse pinholes and can enjoy the benefits of high-resolution imaging even while they are momentarily static, e.g., hovering. Our evaluation shows Umbra resolving up to 2.5$^{\circ}$ with just a single antenna, a 5$\times$ improvement compared to 14$^{\circ}$ from a compact mmWave radar baseline.

Read the full abstract

All authors Akarsh Prabhakara, Yawen Liu, Aswin C. Sankaranarayanan, Anthony Rowe, Swarun Kumar

Image and Video Processing

Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion

Xiaojian Ding, Lin Zhao, Xian Li et al. (+1 more)

Incomplete multi-view data, where certain views are entirely missing for some samples, poses significant challenges for traditional multi-view clustering methods. Existing deep incomplete multi-view clustering approaches often rely on static fusion strategies or two-stage pipelines, leading to suboptimal fusion results and error propagation issues. To address these limitations, this paper proposes a novel incomplete multi-view clustering framework based on Hierarchical Semantic Alignment and Cooperative Completion (HSACC). HSACC achieves robust cross-view fusion through a dual-level semantic space design. In the low-level semantic space, consistency alignment is ensured by maximizing mutual information across views. In the high-level semantic space, adaptive view weights are dynamically assigned based on the distributional affinity between individual views and an initial fused representation, followed by weighted fusion to generate a unified global representation. Additionally, HSACC implicitly recovers missing views by projecting aligned latent representations into high-dimensional semantic spaces and jointly optimizes reconstruction and clustering objectives, enabling cooperative learning of completion and clustering. Experimental results demonstrate that HSACC significantly outperforms state-of-the-art methods on five benchmark datasets. Ablation studies validate the effectiveness of the hierarchical alignment and dynamic weighting mechanisms, while parameter analysis confirms the model's robustness to hyperparameter variations. The code is available at https://github.com/XiaojianDing/2025-NeurIPS-HSACC.

Read the full abstract

All authors Xiaojian Ding, Lin Zhao, Xian Li, Xiaoying Zhu

Image and Video Processing · Cross-listed from q-bio.QM

Physics-Informed autoencoder for DSC-MRI Perfusion post-processing: application to glioma grading

Pierre Fayolle, Alexandre Bône, Noëlie Debs et al. (+4 more)

DSC-MRI perfusion is a medical imaging technique for diagnosing and prognosing brain tumors and strokes. Its analysis relies on mathematical deconvolution, but noise or motion artifacts in a clinical environment can disrupt this process, leading to incorrect estimate of perfusion parameters. Although deep learning approaches have shown promising results, their calibration typically rely on third-party deconvolution algorithms to generate reference outputs and are bound to reproduce their limitations. To adress this problem, we propose a physics-informed autoencoder that leverages an analytical model to decode the perfusion parameters and guide the learning of the encoding network. This autoencoder is trained in a self-supervised fashion without any third-party software and its performance is evaluated on a database with glioma patients. Our method shows reliable results for glioma grading in accordance with other well-known deconvolution algorithms despite a lower computation time. It also achieved competitive performance even in the presence of high noise which is critical in a medical environment.

Read the full abstract

All authors Pierre Fayolle, Alexandre Bône, Noëlie Debs, Mathieu Naudin, Pascal Bourdon, Remy Guillevin, David Helbert

Systems and Control · Cross-listed from cs.NI

Towards xApp Conflict Evaluation with Explainable Machine Learning and Causal Inference in O-RAN

Pragya Sharma, Shihua Sun, Shachi Deshpande et al. (+2 more)

The Open Radio Access Network (O-RAN) architecture enables a flexible, vendor-neutral deployment of 5G networks by disaggregating base station components and supporting third-party xApps for near real-time RAN control. However, the concurrent operation of multiple xApps can lead to conflicting control actions, which may cause network performance degradation. In this work, we propose a framework for xApp conflict management that combines explainable machine learning and causal inference to evaluate the causal relationships between RAN Control Parameters (RCPs) and Key Performance Indicators (KPIs). We use model explainability tools such as SHAP to identify RCPs that jointly affect the same KPI, signaling potential conflicts, and represent these interactions as a causal Directed Acyclic Graph (DAG). We then estimate the causal impact of each of these RCPs on their associated KPIs using metrics such as Average Treatment Effect (ATE) and Conditional Average Treatment Effect (CATE). This approach offers network operators guided insights into identifying conflicts and quantifying their impacts, enabling more informed and effective conflict resolution strategies across diverse xApp deployments.

Read the full abstract

All authors Pragya Sharma, Shihua Sun, Shachi Deshpande, Angelos Stavrou, Haining Wang

Systems and Control · Cross-listed from cs.LG

Information Shapes Koopman Representation

Xiaoyuan Cheng, Wenxuan Yuan, Yiming Yang et al. (+4 more)

The Koopman operator provides a powerful framework for modeling dynamical systems and has attracted growing interest from the machine learning community. However, its infinite-dimensional nature makes identifying suitable finite-dimensional subspaces challenging, especially for deep architectures. We argue that these difficulties come from suboptimal representation learning, where latent variables fail to balance expressivity and simplicity. This tension is closely related to the information bottleneck (IB) dilemma: constructing compressed representations that are both compact and predictive. Rethinking Koopman learning through this lens, we demonstrate that latent mutual information promotes simplicity, yet an overemphasis on simplicity may cause latent space to collapse onto a few dominant modes. In contrast, expressiveness is sustained by the von Neumann entropy, which prevents such collapse and encourages mode diversity. This insight leads us to propose an information-theoretic Lagrangian formulation that explicitly balances this tradeoff. Furthermore, we propose a new algorithm based on the Lagrangian formulation that encourages both simplicity and expressiveness, leading to a stable and interpretable Koopman representation. Beyond quantitative evaluations, we further visualize the learned manifolds under our representations, observing empirical results consistent with our theoretical predictions. Finally, we validate our approach across a diverse range of dynamical systems, demonstrating improved performance over existing Koopman learning methods. The implementation is publicly available at https://github.com/Wenxuan52/InformationKoopman.

Read the full abstract

All authors Xiaoyuan Cheng, Wenxuan Yuan, Yiming Yang, Yuanzhao Zhang, Sibo Cheng, Yi He, Zhuo Sun

Systems and Control

Data to Certificate: Guaranteed Cost Control with Quantization-Aware System Identification

Shahab Ataei, Dipankar Maity and Debdipta Goswami

Cloud-assisted system identification and control have emerged as practical solutions for low-power, resource-constrained control systems such as micro-UAVs. In a typical cloud-assisted setting, state and input data are transmitted from local agents to a central computer over low-bandwidth wireless links, leading to quantization. This paper investigates the impact of state and input data quantization on a linear time invariant (LTI) system identification, derives a worst-case bound on the identification error, and develops a robust controller for guaranteed cost control. We establish a fundamental bound on the model error that depends only on the quantized data and quantization resolution, and develop a linear matrix inequality (LMI) based guaranteed cost robust controller under this error bound.

Read the full abstract

Systems and Control

Comparison of Forced and Unforced Rendezvous, Proximity Operations, and Docking Under Model Mismatch

Robert Muldrow, Channing Ludden and Christopher Petersen

This paper compares the required fuel usage for forced and unforced motion of a chaser satellite engaged in Rendezvous, Proximity Operations, and Docking (RPOD) maneuvers. Improved RPOD models are vital, particularly as the space industry expands and demands for improved fuel efficiency, cost effectiveness, and mission life span increase. This paper specifically examines the Clohessy- Wiltshire (CW) Equations and the extent of model mismatch by comparing pre- dicted trajectories from this model with a more computationally complex, higher fidelity RPOD model. This paper assesses several test cases of similar mission parameters, in each case comparing natural motion circumnavigation (NMC) with comparable forced motion circumnavigation. The Guidance, Navigation, and Con- trol (GNC) impulse maneuvers required to maintain the supposedly zero fuel CW trajectories is representative of the extent of CW model mismatch. This paper demonstrates that unforced motions are not inherently more fuel efficient than forced motions, thus permitting extended orbital operations given the higher fuel efficiency.

Read the full abstract

Systems and Control

Identifying Best Candidates for Busbar Splitting

Giacomo Bastianel, Dirk Van Hertem, Hakan Ergun et al. (+1 more)

Rising electricity demand and the growing integration of renewables are intensifying congestion in transmission grids. Grid topology optimization through busbar splitting (BuS) and optimal transmission switching can alleviate grid congestion and reduce the generation costs in a power system. However, BuS optimization requires a large number of binary variables, and analyzing all the substations for potential new topological actions is computationally intractable, particularly in large grids. To tackle this issue, we propose a set of metrics to identify and rank promising candidates for BuS, focusing on finding buses where topology optimization can reduce generation costs. To assess the effect of BuS on the identified buses, we use a combined mixed-integer convex-quadratic BuS model to compute the optimal topology and test it with the non-linear non-convex AC optimal power flow (OPF) simulation to show its AC feasibility. By testing and validating the proposed metrics on test cases of different sizes, we show that they are able to identify busbars that reduce the total generation costs when their topology is optimized. Thus, the metrics enable effective selection of busbars for BuS, with no need to test every busbar in the grid, one at a time.

Read the full abstract

All authors Giacomo Bastianel, Dirk Van Hertem, Hakan Ergun, Line Roald

Audio and Speech Processing

Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs

Xinlu He, Swayambhu Nath Ray, Harish Mallidi et al. (+5 more)

Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations, which disregard the inherently continuous nature of speech and can lead to loss of fine-grained acoustic information. In this work, we investigate the TTS within the MLLM paradigm using continuous speech representations. We design a dual-head architecture and implement two complementary training strategies for a robust model. (1) A diffusion head generating continuous speech representations is added on the MLLM, which is on frame-level and strictly autoregressive. (2) The original language model head is retained to preserve multitask capability and to control the start and end of speech synthesis. (3) Masked training is employed to address exposure bias in autoregressive decoding. (4) To stabilize optimization, we propose a two-stage scheme where the LM is frozen in the second stage, ensuring the diffusion head learns from a fixed input distribution. Evaluations on LibriSpeech(PC) test-clean show that our approach achieves state-of-the-art autoregressive performance, with a WER of 1.95%, speaker similarity of 0.54, and UTMOS of 4.00. The two-stage training yields a 46% relative WER reduction over the one-stage training baseline. These results highlight the effectiveness of combining autoregressive modeling with continuous-token diffusion, supported by a two-stage training procedure.

Read the full abstract

All authors Xinlu He, Swayambhu Nath Ray, Harish Mallidi, Jia-Hong Huang, Ashwin Bellur, Chander Chandak, M. Maruf, Venkatesh Ravichandran

Signal Processing · Cross-listed from stat.ML

Simplicial Gaussian Models: Representation and Inference

Lorenzo Marinucci, Gabriele D'Acunto, Paolo Di Lorenzo et al. (+1 more)

Probabilistic graphical models (PGMs) are powerful tools for representing statistical dependencies through graphs in high-dimensional systems. However, they are limited to pairwise interactions. In this work, we propose the simplicial Gaussian model (SGM), which extends Gaussian PGM to simplicial complexes. SGM jointly models random variables supported on vertices, edges, and triangles, within a single parametrized Gaussian distribution. Our model builds upon discrete Hodge theory and incorporates uncertainty at every topological level through independent random components. Motivated by applications, we focus on the marginal edge-level distribution while treating node- and triangle-level variables as latent. We then develop a maximum-likelihood inference algorithm to recover the parameters of the full SGM and the induced conditional dependence structure. Numerical experiments on synthetic simplicial complexes with varying size and sparsity confirm the effectiveness of our algorithm.

Read the full abstract

All authors Lorenzo Marinucci, Gabriele D'Acunto, Paolo Di Lorenzo, Sergio Barbarossa

Signal Processing

Towards Spectrally Efficient and Physically Reconfigurable Architectures for Multibeam-Waveform Co-Design in Joint Communication and Sensing

Najme Ebrahimi, Arun Paidmarri, Alexandra Gallyas-Sanhueza et al. (+5 more)

Joint Communication and Sensing (JCAS) platforms are emerging as a foundation of next-generation mmWave (MMW) and sub-THz systems, enabling both high-throughput data transfer and angular localization within a shared signal path. This paper investigates multibeam architectures for JCAS that simultaneously optimize waveform shaping and beamforming across the time, frequency, code, and direct analog/ radio frequency (RF) domains. The paper compares Orthogonal Frequency-Division Multiplexing (OFDM), Frequency Modulated Arrays (FMA), Time-Modulated Arrays (TMA), direct RF/MMW modulation, and Code-Division Multiple Access (CDMA)-based systems with respect to spectral efficiency, beam orthogonality, latency, and Angle-of-Arrival (AoA) estimation accuracy. The results highlight architecture-specific tradeoffs among beam agility, efficiency, accuracy and resolution, and complexity. It also provides a framework for selecting JCAS front ends optimized for power, latency, inter-beam and multi-user interference, and rapid system reconfiguration

Read the full abstract

All authors Najme Ebrahimi, Arun Paidmarri, Alexandra Gallyas-Sanhueza, Yuan Ma, Haoling Li, Basem Abdelaziz Abdelmagid, Tzu-Yuan Huang, Hua Wang

Systems and Control

Competitive EV charging station location with queues

The Minh Nguyen, Nagisa Sugishita, Margarida Carvalho et al. (+1 more)

Electric vehicle (EV) public charging infrastructure planning faces significant challenges in competitive markets, where multiple service providers affect congestion and user behavior. This work extends existing modeling frameworks by incorporating the presence of competitors' stations and more realistic queueing systems. First, we analyze three finite queueing systems, M/M/1/K, M/M/s/K, and M/Er/s/K, with varying numbers of servers (charging outlets) and service time distributions, deriving analytic expressions for user behavior metrics. Second, we embed the queueing-based user behavior model into a bilevel program, where the upper level locates new charging stations to maximize accessibility (throughput), and the lower level captures users' station choices via a user equilibrium. Third, we apply a reformulation from competitive congested user-choice facility location models to approximately solve the bilevel problem and introduce a surrogate-based heuristic to enhance scalability. Fourth, we showcase our methodology on a real-world case study of an urban area in Montreal (Canada), offering managerial insights into how user-choice behavior assumptions and competition affect throughput and location decisions. The results demonstrate that our model yields (re)location strategies that outperform the existing network. More broadly, this approach provides a tool for incorporating charging service quality-through queueing metrics-and existing competition into station planning.

Read the full abstract

All authors The Minh Nguyen, Nagisa Sugishita, Margarida Carvalho, Amira Dems

Systems and Control

Model predictive control lowers barriers to adoption of heat-pump water heaters: A field study

Levi D. Reyes Premer, Elias N. Pergantis, Leo Semmelmann et al. (+2 more)

Electric heat-pump water heaters (HPWHs) could reduce the energy costs, emissions, and power grid impacts associated with water heating, the second-largest energy use in United States housing. However, most HPWHs today require 240 V circuits to power the backup resistance heating elements they use to maintain comfort during large water draws. Installing a 240 V circuit can increase the up-front cost of a HPWH by half or more. This paper develops and field-tests the first control system that enables a 120 V HPWH to efficiently maintain comfort without resistance heating elements. The novel model predictive control (MPC) system enables pre-heating in anticipation of large water draws, which it forecasts using an ensemble of machine learning predictors. By shifting electrical load over time, MPC also reduces energy costs on average by 23% and 28% under time-of-use pricing and hourly pricing, respectively, relative to a 240 V HPWH with standard controls. Compared to the increasingly common practice in 120 V HPWHs of storing water at a constant, high temperature (60 {\deg}C) to ensure comfort, MPC saves 37% energy on average. In addition to demonstrating MPC's benefits in a real, occupied house, this paper discusses implementation challenges and costs. A simple payback analysis suggests that a 120 V HPWH, operated by the MPC system developed here, would be economically attractive in most installation scenarios.

Read the full abstract

All authors Levi D. Reyes Premer, Elias N. Pergantis, Leo Semmelmann, Davide Ziviani, Kevin J. Kircher