Signal Processing
LO-Free Joint Communication and Sensing via Inter-Antenna Cross-Correlation and Graph-Based Spatial Phase Inference
Hasan Atalay Günel, Mohaned Chraiti and Ali Görçin
Joint communication and sensing (JCAS) typically rely on coherent downconversion to recover the phase relationships required for array processing. Meanwhile, Local Oscillators (LOs) are a major source of cost, power consumption, and implementation complexity in millimeter-wave (mmWave) and sub-THz receivers. Existing LO-free receiver designs are typically based on envelope detection or related non-coherent operations that do not preserve inter-branch phase information, which limits their applicability to JCAS. This work proposes an LO-free JCAS receiver architecture that leverages pairwise inter-branch correlation processing to suppress the common carrier component and to synthesize relative-phase observables across the
antenna array, enabling both data communication and Direction-of-Arrival (DoA) estimation. The transmitted symbols are designed to induce distinct phase-difference patterns, such that the resulting correlation phases contain both a data-dependent component and a DoA-dependent component. We formulate recovery as inference over a correlation graph, where branches are nodes and pairwise correlations are edges, and show that the resulting cycle-consistent redundancy enables robust relative-phase recovery under noise and perturbations. We further derive a
topology-aware Cramér-Rao lower bound for DoA estimation under a locally unwrapped approximation. Numerical results confirm that increasing graph connectivity improves both bit-error rate and DoA accuracy, with sensing performance approaching the derived bound.
Read the full abstract ▾
Signal Processing
RA-LWLM: Retrieval-Augmented In-Context Localization with Wireless Foundation Models
Guangjin Pan, Hui Chen, Hei Victor Cheng et al. (+1 more)
Wireless localization is a fundamental capability of sixth-generation (6G) networks. Conventional model-based methods require accurate modeling of the propagation environment and degrade in complex multipath and non-line-of-sight scenarios, while learning-based methods couple model parameters tightly to the training scene, requiring costly retraining whenever the base station (BS) configuration or propagation environment changes. In this paper, we propose RA-LWLM, a
retrieval-augmented in-context localization framework that achieves training-free cross-scene adaptation by externalizing scene-specific information into a per-scene fingerprint database rather than encoding it in model weights. The framework consists of three components: a frozen wireless foundation model (FM) encoder that maps raw channel state information into a scene-agnostic representation; a
retrieval module that selects the most informative references from the per-scene database via similarity search in the representation space; and a
transformer-based in-context learning (ICL) module that fuses the query with the retrieved references to predict the user equipment (UE) position. To accommodate varying
retrieval quality and propagation complexity across queries, the ICL module adopts a mixture-of-experts design in which experts specialize in different context sizes and are softly combined by a learnable selector. Extensive ray-tracing-based experiments across heterogeneous scenes with diverse BS configurations show that RA-LWLM achieves nearly identical accuracy on seen and unseen scenes without any per-scene retraining, substantially outperforming end-to-end and FM-based baselines. These results validate the proposed
retrieval-augmented in-context paradigm as a scalable solution for cross-scene localization in 6G networks.
Read the full abstract ▾
All authors Guangjin Pan, Hui Chen, Hei Victor Cheng, Henk Wymeersch
Signal Processing
Channel Estimation and Reconstruction in Fluid Antenna Multiple Access: Myths, Misconceptions and Critical Questions
Taissir Y. Elganimi, Pablo Ramírez-Espinosa, David Morales-Jiménez et al. (+1 more)
Fluid
antenna systems (FAS) represent a paradigm shift in which
antenna elements (ports) emulate the illusion of motion or fluidity within a spatial aperture to optimize performance. One of FAS's key use cases is the provision of open-loop fluid
antenna multiple access (FAMA), enabling multiplexing gains through spatial interference nulling without requiring channel state information (CSI) at the transmitter side. However, this comes at the price of requiring a precise channel reconstruction at the receiver to successfully identify the optimal port. Current research efforts map this sensing task to a legacy
MIMO-style estimation problem focused on minimizing global reconstruction errors such as normalized mean-squared error (NMSE). In this work, we argue that because FAS is inherently selection-based, NMSE-like approaches often lead to excessive training overhead and reduced net throughput. We revisit the problem of channel estimation and reconstruction in FAS, challenging some prevalent myths related to (i) the adequacy of global error metrics; (ii) the convenience of reconstructing channels or aggregate interference; (iii) the need for spatial oversampling; and (iv) the impact of port selection accuracy. We also identify four critical questions that must be answered for successfully enabling FAMA deployments: (i) the definition of a selection-optimal sampling law; (ii) the identification of proper reconstruction methodologies; (iii) the inherent trade-offs between multi-port sensing and selection gain; and (iv) the challenges introduced when moving towards electronically reconfigurable FAS.
Read the full abstract ▾
All authors Taissir Y. Elganimi, Pablo Ramírez-Espinosa, David Morales-Jiménez, F. Javier López-Martínez
Image and Video Processing
Face Liveness Detection Using RGB and Thermal Image Fusion
Merve Erşan, Melike Girgin and Tayfun Akgül
Face detection with visible-spectrum cameras can capture facial features, but it often fails to distinguish live subjects from spoof sources such as photographs, masks, or statues. Previous approaches based on texture, motion, or physiological cues are sensitive to illumination changes and show limited robustness against spoofing attacks. Thermal imaging helps overcome these limitations by detecting heat emissions, naturally excluding spoof faces. This study proposes a hybrid approach that fuses the edge information of RGB images with corresponding thermal images using a custom ARISTOF
dataset containing live and spoof faces. The fused images are first evaluated using the YOLOv8-Face model to compare face detection performance across RGB, thermal, and fused modalities. The results show that the proposed method enhances the face detection accuracy of thermal images. The fused images are subsequently used to train a YOLOv8-Face model for live and spoof classification, demonstrating that the proposed
multimodal fusion effectively supports robust face liveness detection.
Read the full abstract ▾
Image and Video Processing · Cross-listed from cs.CV
Hist2Style: Histogram-Guided Stylization with Bilateral Grids
Dekel Galor, Adam Pikielny, Zhoutong Zhang et al. (+4 more)
Photorealistic style transfer aims to match the color and tone of an input image to that of a style target while preserving the content and details of the original scene. Although existing large image models can facilitate these kinds of appearance edits, their high computational demands, potential for
hallucinations, and limited user control make them unsuitable for high-resolution, real-time workflows. We introduce Hist2Style, a bilateral-grid formulation for fast, edge-aware stylization that preserves visual fidelity by constraining operations to locally affine transforms in bilateral space. Our model distills a large image editing model into a lightweight network by training on a large supervised corpus generated with
language and
vision-
language models, targeting spatially varying color edits. The network conditions on a histogram-based
embedding of the style target to provide an interpretable interface for adjusting the output style by modifying the target color distribution. Overall, Hist2Style maintains content structure by construction, avoids
hallucinations, and supports real-time, high-resolution photorealistic stylization with interactive user-controllable color and tone adjustments.
Read the full abstract ▾
All authors Dekel Galor, Adam Pikielny, Zhoutong Zhang, Ke Wang, Laura Waller, Jiawen Chen, Ilya Chugunov
Audio and Speech Processing
SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
Hanlin Zhang, Daxin Tan, Dehua Tao et al. (+3 more)
Instruction-guided
speech editing requires a model to modify specified
speech attributes while preserving non-target characteristics. Despite rapid progress in
Speech Large
Language Models (
Speech LLMs), systematic evaluation of this capability remains challenging, as existing
benchmarks are fragmented across isolated editing tasks. To bridge this gap, we introduce SpeechEditBench, a bilingual multi-attribute
benchmark for instruction-guided
speech editing. SpeechEditBench encompasses seven atomic editing tasks, as well as compositional editing tasks that integrate multiple operations within a single instruction. We propose an anchor-based evaluation protocol that separately assesses the edit success of target attributes and the preservation of non-target linguistic content, leading to three metrics: target success, preservation success, and joint success. Using this
benchmark, we evaluate mainstream
Speech LLMs and specialized
speech editing systems. The results reveal three key findings: (1) no single model performs well across all editing dimensions; (2) closed-source
Speech LLMs generally outperform open-source models; (3) compositional editing poses a significant challenge, with even the most advanced models struggling to achieve high joint success. SpeechEditBench provides a rigorous diagnostic framework to identify bottlenecks in
Speech LLMs, thereby facilitating the development of next-generation models with more precise instruction-guided editing capabilities. Data and code are available at https://github.com/daxintan-cuhk/SpeechEditBench.
Read the full abstract ▾
All authors Hanlin Zhang, Daxin Tan, Dehua Tao, Xiao Chen, Haochen Tan, Linqi Song
Image and Video Processing
MoRE: A Mixture-of-Experts-Based Task-Adaptive End-to-End Network for Multimodal MRI Reconstruction
Yuyang Li, Yipin Deng, Wenlei Shang et al. (+4 more)
Although accelerated MRI reconstruction has advanced rapidly through end-to-end learning, deploying a single unified network that generalizes across diverse anatomies and contrasts under constrained computational resources remains challenging. In this paper, we introduce MoRE, a sparsely activated mixture-of-experts (MoE) module integrated into an end-to-end variational network. MoRE couples a shared encoder with sample-wise, unsupervised routing to activate a minimal subset of expert decoders while strictly preserving physics-based data consistency. Evaluated on the fastMRI multi-coil
brain and knee
datasets under 8x undersampling, MoRE achieves highly stable SSIM and PSNR performance across multi-contrast
datasets. Furthermore, t-SNE visualization of the routing
embeddings reveals interpretable, modality-aware expert specialization. The sparse conditional computation mechanism ensures that the architectural overhead remains modest. These results demonstrate that MoE-style capacity scaling can significantly enhance general-purpose MRI reconstruction without requiring proportional increases in computational power.
Read the full abstract ▾
All authors Yuyang Li, Yipin Deng, Wenlei Shang, Juncen Wu, Xin Bai, Zijian Zhou, Peng Hu
Signal Processing
A 32-Channel 3.53-{\mu}W Per Channel Brain-Machine Interface SoC Featuring Dual-Threshold Delta-modulation, In-Memory Spike Detection and Bi-SNN Based Motor Decoding
Ye Ke, Zhengnan Fu, Pao-Sheng Vincent Sun et al. (+8 more)
With the scaling of sensor channel counts, systems confront challenges in frontend data sensing and on-implant data processing. This work presents a 32-channel fully event-based iBMI SoC in 65nm CMOS for an efficient neuromorphic signal processing pipeline. The SoC integrates a 32-channel dual-threshold delta modulation (DTDM) frontend array that provides up to 26x data compression at the frontend, an in-
memory computing (IMC) spike detector (SPD) for efficient in-pixel spike detection, and a bipolar LIF-based spiking neural network (Bi-SNN) decoder for on-chip motor intention decoding (MID). Consuming only 3.53 {\mu}W per channel and achieving ~0.62 decoding R2 with a compact 0.034 mm2 per-channel area, the chip enables high-efficiency signal recording, processing, and decoding for implantable devices.
Read the full abstract ▾
All authors Ye Ke, Zhengnan Fu, Pao-Sheng Vincent Sun, An Guo, Shuai Dong, Junyi Yang, Yahan Yang, Abdelrahman B. M. Eldaly, Xin Si, Leanne Chan, Arindam Basu
Signal Processing
Satellite NOMA for Direct-to-Cell Communications: Fundamentals, Protocols, and Opportunities
Xiangyu Li, Bodong Shang, Junchao Ma et al. (+3 more)
Direct-to-
cell (DTC) satellite communication is regarded as one of the most recent technologies that provides global connectivity. However, with the growing number of wireless users and devices, the design of DTC communications must satisfy the requirements of high-scale capabilities and efficient spectrum utilization. To this end, integrating satellite communications with advanced multiple-access techniques, such as non-orthogonal multiple access (NOMA), has attracted considerable interest in developing NOMA-DTC communications. In this article, we first introduce the fundamentals of NOMA-DTC communications, including architectural fundamentals, system design aspects, and potential applications. Given the various cooperative modes and the still-evolving satellite network (SatNet) architectures, such as cooperative SatNets and multi-tier SatNets, we explore protocols that suit future SatNets and enhance system performance. Furthermore, a case study is conducted to investigate the benefits of NOMA schemes for DTC communications and to compare them with OMA schemes. Finally, to inspire further research, several opportunities for NOMA-DTC communications are presented.
Read the full abstract ▾
All authors Xiangyu Li, Bodong Shang, Junchao Ma, Yuzheng Ren, Haijun Zhang, Pingyi Fan
Signal Processing
Scalable GNN-Based Power Allocation for Rate-Splitting Cell-Free Massive MIMO Systems
Ruomeng Wang, Yin Xu, Aimin Tang et al. (+5 more)
Cell-free massive multiple-input multiple-output (CF-mMIMO) systems provide enhanced coverage and capacity for next-generation wireless networks. However, CF-mMIMO systems face significant challenges in downlink power allocation (PA) due to imperfect channel state information (CSI), severe multi-user interference (MUI), and high computational complexity. To address these issues, rate-splitting multiple access (RSMA) is adopted as a robust interference management strategy. Accordingly, this paper proposes an unsupervised and scalable graph neural network (GNN) framework for PA in rate-splitting CF-mMIMO (RS-CF-mMIMO) systems, relying exclusively on large-scale fading (LSF) coefficients without instantaneous CSI. To resolve the dimensionality mismatch in dynamic networks, we introduce a slice-based adaptive layer that projects variable-dimension features into a fixed latent space. This mechanism enables a unified model to generalize across diverse
topologies without retraining. Within this architecture, the sum spectral efficiency (SE) is maximized under per-AP power constraints, assuming maximum-ratio precoding for common streams and regularized zero-forcing precoding for private streams. We also derive a weighted minimum mean-square error-alternating direction method of multipliers (WMMSE-ADMM)
algorithm as a performance upper bound. Extensive simulations verify that the proposed GNN framework achieves near-optimal SE and outperforms unsupervised deep neural networks (DNNs) across diverse system sizes and pilot assignment schemes. Furthermore, the scalable variant maintains robust performance while reducing the trainable parameter count by over 57% relative to DNNs and decreasing inference latency by up to three orders of magnitude compared with WMMSE-ADMM.
Read the full abstract ▾
All authors Ruomeng Wang, Yin Xu, Aimin Tang, Xiaowu Ou, Jun Zhu, Dazhi He, Lifeng Wang, Wenjun Zhang
Systems and Control · Cross-listed from cs.RO
FlipItRight: Stable Pose-Targeted Throw-Flip Across Diverse Objects
Axel Dawne and Shinkyu Park
We propose FlipItRight, a framework for stable planar pose-targeted throw-flip with a high-DoF manipulator. The task is decomposed into an object-level planner, which generates candidate release states satisfying the desired landing pose, and a
robot-level planner, which evaluates executability and constructs a feasible swing motion. Treating the release state as an explicit intermediate representation enables principled candidate filtering, adaptive selection of release and pre-swing configurations, and structured near-release motion design – in particular, approximately constant end-effector velocities during the final swing phase to improve robustness to release-timing uncertainty. We validate on a real platform across objects of varying shape, size, and mass, achieving a 90% success rate across 120 trials. Ablation studies confirm that each design choice contributes to throwing performance, and the framework requires no prior data or learned model, enabling direct deployment on new objects and targets without environment-specific calibration or data collection.
Read the full abstract ▾
Audio and Speech Processing
Kinship Verification Using Voice
Jagabandhu Mishra and Tomi H. Kinnunen
Kinship verification (KV) from voice, the task of determining whether two speakers are biologically related, has received only little
attention. Our work establishes a foundational basis for this emerging frontier, contributing to both performance evaluation and detection methodologies. First, leveraging the
speech recordings of the large-scale audio-visual
dataset, KAN-AV, we propose a revised evaluation protocol that controls for various confounders and adopts a family-disjoint train–test split to address open-set KV. Second, we analyze the close connection between speaker verification and KV, showing that genealogical similarity of speaker pairs plays opposite roles in the two tasks. Third, we tackle KV using three neural speaker
embedding extractors (ECAPA-TDNN, WavLM-ECAPA, and ReDimNet) combined with various back-ends. In zero-shot KV including same-speaker target trials, ReDimNet achieves the lowest equal error rate (EER) of $20.8\%$; however, performance degrades to $39.7\%$ under strict kin trials, where same-speaker target trials are excluded. Our best trainable back-end, which applies asymmetric processing of the
embedding pair to mitigate age-difference effects, obtains an EER of $32.0\%$ ($18.6\%$ with speaker target trials included). These results highlight the difficulty of KV while showing that speaker
embeddings encode familial cues, offering a promising foundation for voice-based kinship analysis.
Read the full abstract ▾
Signal Processing
Physics-Aware Linearized ADMM and Its Unrolling
Satoshi Takabe, Shunta Arai and Tadashi Wadayama
Recently, partial differential equations (PDEs) have been used to directly model the measurement process in signal processing, although their evaluation is costly. In this paper, we propose a novel alternating direction method of multipliers (ADMM)-based
algorithm called physics-aware linearized ADMM (PA-LADMM) for inverse problems from PDE-based measurement processes. The key idea is the linearization of the subproblem with PDEs, leading to a cost-efficient update rule that calls only a PDE solver and its gradient evaluation per iteration. The
algorithm has a theoretical convergence guarantee under certain conditions. In addition, we combine it with deep unfolding to unroll the PA-LADMM and train its internal parameters using supervised data. Two distinct experiments, compressed sensing with optical fiber communication and image restoration from noisy anisotropic
diffusion, demonstrated the effectiveness of the proposed
algorithms.
Read the full abstract ▾
Audio and Speech Processing
RRP-Voice: A Longitudinal Dataset and Benchmark for Recurrent Respiratory Papillomatosis Detection
Wenze Ren, Ke-Han Lu, Kai-Wei Chang et al. (+8 more)
Deep learning has advanced pathological voice detection rapidly, yet rare laryngeal diseases remain underexplored due to data scarcity. Recurrent Respiratory Papillomatosis (RRP) exemplifies this gap: an HPV-induced disease of the larynx in which patients oscillate between recurrence and post-
surgical remission over the years. RRP demands continuous voice monitoring that existing cross-sectional corpora cannot support. We introduce the first longitudinal voice
dataset for RRP, comprising recordings from 26 patients with up to ten years of follow-up. Each session pairs sustained vowels with sentence-level utterances, which are annotated by otolaryngologists and confirmed synchronously with laryngoscopy. Building on this resource, we establish a systematic
benchmark spanning handcrafted features, end-to-end deep networks, self-supervised pretrained models, and recent audio large
language models, all evaluated under session-level cross-validation with patient-level audit. Per-subject longitudinal analyses further confirm that the cross-sectional discriminative signal reflects laryngoscopic disease state rather than stable speaker attributes. This work lays a foundation for rare longitudinal pathological voice tasks in low-resource clinical settings.
Read the full abstract ▾
All authors Wenze Ren, Ke-Han Lu, Kai-Wei Chang, Tiantian Feng, Ching Fang, Zhi-Chi Liao, Dao Thi Hai Yen, Syu-Siang Wang, Yu Tsao, Chi-Te Wang, Shih-Hau Fang
Image and Video Processing
Regularized joint reconstruction and slab combination for accelerated three-dimensional multi-slab diffusion-weighted imaging using multi-scale energy models
Reza Ghorbani, Jyothi Rikhab Chand, Chu-Yu Lee et al. (+2 more)
This work presents Energy-based Profile Encoding, EPEN, a joint reconstruction framework for high-resolution
diffusion-weighted MRI from undersampled 3D multi-slab k-space acquisitions, designed to suppress slab-boundary artifacts while preserving fine anatomical detail. EPEN formulates the multi-slab acquisition process using a bilinear forward model in which both the
diffusion-weighted image volume and slab excitation profiles are treated as unknown variables. Reconstruction is posed as a maximum a posteriori optimization problem with three components: a Gaussian data-fidelity term enforcing consistency with the acquired k-space measurements, a CNN-based deep energy prior that represents the negative log distribution of clean
diffusion-weighted images, and a quadratic regularization term that constrains the estimated slab profiles toward an initial profile estimate. The gradient of the learned energy prior guides accelerated reconstruction toward an artifact-free image distribution. The resulting nonconvex objective is solved using alternating minimization, with image-volume updates performed through a majorize-minimize scheme using conjugate-gradient optimization and slab-profile updates estimated by regularized least squares. Across multiple acceleration factors and slab configurations, EPEN substantially reduced slab-boundary artifacts compared with conventional slab-boundary correction methods, while improving structural consistency and preserving
diffusion-weighted contrast. These results demonstrate that EPEN enables robust joint 3D multi-slab
diffusion MRI reconstruction and slab-profile correction within a unified optimization framework supported by deep energy-based image priors.
Read the full abstract ▾
All authors Reza Ghorbani, Jyothi Rikhab Chand, Chu-Yu Lee, Mathews Jacob, Merry Mani
Audio and Speech Processing
Description and Discussion on DCASE 2026 Challenge Task 2: Noise-aware Unsupervised Anomalous Sound Detection for Machine Condition Monitoring
Tomoya Nishida, Noboru Harada, Daiki Takeuchi et al. (+6 more)
This paper presents an overview of DCASE 2026 Challenge Task 2, titled "Noise-aware unsupervised anomalous sound detection (UASD) for machine condition monitoring." The task aims to advance noise-robust anomalous sound detection for machine condition monitoring under the unsupervised setting, where only normal machine sounds are available for training. Reliable detection under noisy conditions is crucial for practical deployment, but previous DCASE Task 2 settings provided limited information about environmental noise, potentially limiting UASD performance in highly noisy situations. To address this limitation, DCASE 2026 allows participants to exploit two-channel audio samples simultaneously captured at locations near and far from the target machine. Since the distant microphone is expected to contain relatively stronger environmental noise and weaker direct machine sounds, it may help distinguish environmental noise components from the target machine sounds. After the challenge submission deadline, challenge results and an analysis of the submitted systems will be added.
Read the full abstract ▾
All authors Tomoya Nishida, Noboru Harada, Daiki Takeuchi, Daisuke Niizumi, Keisuke Imoto, Kota Dohi, Harsh Purohit, Takashi Endo, Yohei Kawaguchi
Signal Processing
A Hybrid Near-field Indoor Channel Model for THz Bands Based on Surface Scattering Characteristics
Yongchao He, Taihao Zhang, Cunhua Pan et al. (+6 more)
Terahertz (THz) communication and extremely large-scale
MIMO (XL-
MIMO) are essential for achieving ultra-high data rates in future 6G systems. However, at sub-millimeter wavelengths, typical indoor materials exhibit significant roughness that invalidates conventional ideal smooth surface assumptions, while massive array apertures introduce pronounced near-field effects and spatial non-stationarity. To address these challenges, this paper proposes a hybrid near-field channel model utilizing surface scattering characteristics based on distinct measurement campaigns. First, based on typical indoor materials scattering measurements across the 260-400 GHz band, an improved Beckmann-Kirchhoff (B-K) model is developed to accurately characterize surface roughness and diffuse scattering behavior. The model independently analyzes single-bounce (SB) and multi-bounce (MB) clusters by applying deterministic rough surface scattering theory and geometry-statistical approach, respectively. Then, using near-field spatial non-stationarity measurements from a 630-element virtual array in the 330-360 GHz band, a Dual-Gaussian Mixture Model (DMM) and a Negative Binomial (NB) distribution are adopted to describe the lengths and the number of spatial visibility regions (VRs), respectively. Additionally, a Weibull distribution is employed to model the intra-region power fluctuations. Finally, comprehensive XL-
MIMO channel evaluations within the same band demonstrate that the proposed model aligns closely with measured results in terms of the spatial cross-correlation function (SCCF), frequency cross-correlation function (FCF), and channel capacity. By reproducing the spatial sparsity of THz band, the proposed model overcomes the limitation of conventional standard models, such as 3GPP 38.901 and WINNER II, in significantly overestimating channel capacity.
Read the full abstract ▾
All authors Yongchao He, Taihao Zhang, Cunhua Pan, Hong Ren, Chenzhou Lin, Tian Qiu, Bingchang Hua, Cheng-Xiang Wang, Jiangzhou Wang
Image and Video Processing
PINNOCHIO: Physics-Informed Neural Network for Coupled Hyperelastic Interface-Volume Simulation in Orthognathic Surgery
Jungwook Lee, Daeseung Kim, Kevin Gu et al. (+6 more)
Predicting patient-specific facial soft-tissue deformation is critical for iterative orthognathic surgery planning. However, current computational methods face a strict accuracy-efficiency trade-off: high-fidelity Finite Element Methods (FEM) are computationally prohibitive, whereas pure deep learning models often produce biomechanically inconsistent results. While Physics-Informed Neural Networks (PINNs) offer a promising avenue, learning the complex heterogeneous mechanics of bone–soft-tissue interactions with only partial clinical supervision (i.e., outer facial surfaces) remains highly unstable. To overcome these challenges, we present PINNOCHIO, a novel physics-informed framework for facial soft-tissue simulation. PINNOCHIO introduces a hybrid sequential decomposition that explicitly decouples discontinuous bone–soft-tissue interface movements from continuous volumetric hyperelastic deformation. This structural separation enables stable training and facilitates a physics-enabled sim-to-real adaptation strategy, ensuring internal biomechanical consistency without requiring volumetric ground truth. Evaluated on a 40-patient clinical cohort, PINNOCHIO outperforms existing baselines in both surface accuracy and physical validity. Furthermore, it achieves a substantial speedup over FEM, successfully resolving the accuracy-efficiency trade-off to provide a highly reliable and practical tool for interactive
surgical planning.
Read the full abstract ▾
All authors Jungwook Lee, Daeseung Kim, Kevin Gu, Zhangfeng Hu, Tianshu Kuang, Finn Hopeman, Michael A.K. Liebschner, Jaime Gateno, Pingkun Yan
Signal Processing
Deconstructing the Composite Channel for Beyond Diagonal RIS: Channel Estimation and Beamforming Design
Fazal-E Asim, André L. F. de Almeida, Bruno Sokal et al. (+2 more)
As beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) gain increasing
attention in high-frequency wireless communications, accurate and scalable channel-estimation methods become essential. This paper develops a parametric channel-estimation and beamforming framework that deconstructs the composite BD-RIS channel into its generating directional factors, revealing the tensor structure induced jointly by propagation geometry and beyond-diagonal scattering. We propose two tensor-based
estimators: Fourth-Order Tucker Channel Estimation (FORTE), which models the partially structured channel as a fourth-order Tucker tensor, and Fourth-Order PARAFAC Channel Estimation (FORPE), which captures the fully structured channel through a fourth-order PARAFAC model. By exploiting partial and full channel geometry, the proposed methods achieve higher estimation accuracy than Least Squares and Block Tucker Kronecker Factorization
benchmarks. In particular, FORTE outperforms FORPE due to its more compact representation, attaining an NMSE of about 10^{-4} at 5 dB SNR. In contrast, FORPE provides essentially unique estimates of the composite-channel factor
matrices, whereas FORTE identifies their subspaces. The proposed deconstruction also provides a structured representation useful for sensing-oriented parameter extraction and tensor-structured system optimization. Finally, the Tensor Optimization Framework for Beamforming, Combining, and Scattering (TenFormer) achieves spectral efficiency comparable to the
benchmark design while significantly reducing computational complexity through parallel tensor-structured optimization.
Read the full abstract ▾
All authors Fazal-E Asim, André L. F. de Almeida, Bruno Sokal, Behrooz Makki, Gabor Fodor
Systems and Control
Making Aggregations Reliable: Realizability Guarantees for Battery Fleets with Heterogeneous Power and Energy Limits
Mazen Elsaadany and Mads R. Almassalkhi
Aggregated battery energy storage systems (BESS) enable large fleets of heterogeneous battery elements to participate in system-level optimization and electricity
markets. Scheduling each element independently is computationally impractical at scale. While many aggregate battery models rely on convex relaxations, they often ignore element complementarity constraints, leading to dispatch solutions that may be infeasible when implemented on individual battery elements. This paper develops a realizable composite battery model for parameter-heterogeneous BESS fleets that guarantees feasibility at the element-level while preserving computational tractability. We derive simple linear conditions under which aggregate charging and discharging trajectories can be safely disaggregated while respecting individual power limits, energy limits, and complementarity constraints under a priority-based controller. Numerical experiments in a unit-commitment setting demonstrate that the proposed realizable composite battery formulation produces feasible dispatch solutions. Solve times are effectively independent of system size, unlike micro-model mixed-integer formulations. Solutions obtained from the proposed formulation converge to the optimal
benchmark as control granularity is refined. Additional studies illustrate the robustness of the framework to moderate violations of key modeling assumptions, including heterogeneous power-to-energy ratios.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.LG
Everywhere Learning: Artificial Intelligence with Pointwise Constraints
Ignacio Boero, Ignacio Hounie, Luiz F.O. Chamon et al. (+1 more)
Everywhere learning is a new paradigm whereby Artificial Intelligence (AI) systems are trained to satisfy loss constraints with probability one over the data distribution. This is in contrast to the standard paradigm of training AI systems to minimize average losses. We develop an approximate duality theory to substantiate a generalization analysis that establishes the proximity between solutions of empirical and statistical everywhere learning problems. Our results show that dual variables reweigh the data distribution towards points in which loss constraints are more difficult to satisfy and that generalization is controlled by the mismatch between the concentration of mass of the data distribution and the concentration of mass on points where constraints are more difficult to satisfy. We further show that we can control generalization with a sparse L1 penalty on constraint relaxations. We illustrate the merits of everywhere learning with an experiment in agentic classification for
language model tasks.
Read the full abstract ▾
All authors Ignacio Boero, Ignacio Hounie, Luiz F.O. Chamon, Alejandro Ribeiro