Signal Processing
Calibration-Free Induced Magnetic Field Indoor and Outdoor Positioning via Data-Driven Modeling
Qiushi Guo, Matthias Tschoepe, Mengxi Liu et al. (+2 more)
Induced
magnetic field (IMF)-based localization offers a robust alternative to wave-based positioning technologies due to its resilience to non-line-of-sight conditions, environmental dynamics, and wireless interference. However, existing
magnetic localization systems typically rely on analytical field inversion, manual calibration, or environment-specific fingerprinting, limiting their scalability and transferability. This paper presents a data-driven IMF localization framework that directly maps induced
magnetic field measurements to spatial coordinates using supervised learning, eliminating explicit environment-specific calibration. By replacing explicit field modeling with learning-based inference, the proposed approach captures nonlinear field interactions and environmental effects. An orientation-invariant feature representation enables rotation-independent deployment. The system is evaluated across multiple indoor environments and an outdoor deployment. Benchmarking against classical and deep learning baselines shows that a Random Forest regressor achieves sub-20 cm accuracy in 2D and sub-30 cm in 3D localization. Cross-environment validation demonstrates that models trained indoors generalize to outdoor environments without retraining. We further analyze scalability by varying transmitter spacing, showing that coverage and accuracy can be balanced through deployment density. Overall, this work demonstrates that data-driven IMF localization is a scalable and transferable solution for real-world positioning.
Read the full abstract ▾
All authors Qiushi Guo, Matthias Tschoepe, Mengxi Liu, Sizhen Bian, Paul Lukowicz
Systems and Control
Cognitive-Flexible Control via Latent Model Reorganization with Predictive Safety Guarantees
Thanana Nuchkrua and Sudchai Boonto
Learning-enabled control systems must maintain safety when system dynamics and sensing conditions change abruptly. Although
stochastic latent-state models enable uncertainty-aware control, most existing approaches rely on fixed internal representations and can degrade significantly under distributional shift. This letter proposes a cognitive-flexible control framework in which latent belief representations adapt online, while the control law remains explicit and safety-certified. We introduce a Cognitive-Flexible Deep
Stochastic State-Space Model (CF–DeepSSSM) that reorganizes latent representations subject to a bounded Cognitive Flexibility Index (CFI), and embeds the adapted model within a
Bayesian model predictive control (MPC) scheme. We establish guarantees on bounded posterior drift, recursive feasibility, and closed-loop stability. Simulation results under abrupt changes in system dynamics and observations demonstrate safe representation adaptation with rapid performance recovery, highlighting the benefits of learning-enabled, rather than learning-based, control for nonstationary cyber–physical systems.
Read the full abstract ▾
Systems and Control
Modeling and Control of Hybrid Distribution Transformers for Simultaneous Grid Services
Martin Doff-Sotta, Florian Cech, Rishabh Manjunatha et al. (+3 more)
Hybrid distribution
transformers (HDTs) integrate conventional
transformers with partially rated power electronic converters to improve power quality, enable advanced ancillary services and increase penetration of renewable energy sources in the national power grid. In this paper, we present an averaged mathematical model of a three-phase HDT equipped with two back-to-back voltage source converters connected in a series-shunt configuration. Cascaded PI controllers are designed in the synchronously rotating dq0 reference frame to regulate load voltage, compensate reactive power, achieve grid frequency regulation, and perform load phase balancing. Simulation results implemented in Python confirm that these simple yet effective control mechanisms allow HDTs to offer simultaneous grid services without introducing complexity. The complete model, control architecture, and implementation steps are detailed, enabling further validation and adoption.
Read the full abstract ▾
All authors Martin Doff-Sotta, Florian Cech, Rishabh Manjunatha, Costantino Citro, Matthew Williams, Thomas Morstyn
Signal Processing
Denoising deterministic networks using iterative Fourier transforms
H. Robert Frost
We detail a novel
Fourier-based approach (IterativeFT) for identifying deterministic network structure in the presence of both edge
pruning and Gaussian noise. This technique involves the iterative execution of forward and inverse 2D discrete
Fourier transforms on a target network adjacency
matrix. The denoising ability of the method is achieved via the application of a sparsification operation to both the real and frequency domain representations of the adjacency
matrix with
algorithm convergence achieved when the real domain sparsity pattern stabilizes. To demonstrate the effectiveness of the approach, we apply it to noisy versions of several deterministic models including Kautz,
lattice, tree and bipartite networks. For contrast, we also evaluate preferential attachment networks to illustrate the behavior on
stochastic graphs. We compare the performance of IterativeFT against simple real domain and frequency domain thresholding, reduced rank reconstruction and locally adaptive network sparsification. Relative to the comparison network denoising approaches, the proposed IterativeFT method provides the best overall performance for
lattice and Kuatz networks with competitive performance on tree and bipartite networks. Importantly, the InterativeFT technique is effective at both filtering noisy edges and recovering true edges that are missing from the observed network.
Read the full abstract ▾
Signal Processing
Comparative Analysis of Differential and Collision Entropy for Finite-Regime QKD in Hybrid Quantum Noisy Channels
Mouli Chakraborty, Subhash Chandra, Avishek Nag et al. (+3 more)
In this work, a comparative study between three fundamental entropic measures, differential
entropy,
quantum Renyi
entropy, and
quantum collision
entropy for a hybrid
quantum channel (HQC) was investigated, where hybrid
quantum noise (HQN) is characterized by both discrete and continuous variables (CV) noise components. Using a Gaussian mixture model (GMM) to statistically model the HQN, we construct as well as visualize the corresponding pointwise entropic functions in a given 3D probabilistic landscape. When integrated over the relevant state space, these entropic surfaces yield values of the respective global
entropy. Through analytical and numerical evaluation, it is demonstrated that the differential
entropy approaches the
quantum collision
entropy under certain mixing conditions, which aligns with the Renyi
entropy for order $\alpha = 2$. Within the HQC framework, the results establish a theoretical and computational equivalence between these measures. This provides a unified perspective on quantifying uncertainty in hybrid
quantum communication systems. Extending the analysis to the operational domain of finite key QKD, we demonstrated that the same $10\%$ approximation threshold corresponds to an order-of-magnitude change in Eves success probability and a measurable reduction in the secure key rate.
Read the full abstract ▾
All authors Mouli Chakraborty, Subhash Chandra, Avishek Nag, Trung Q. Duong, Merouane Debbah, Anshu Mukherjee
Signal Processing
CMANet: Channel-Masked Attention Network for Cooperative Multi-Base-Station 3D Positioning
Tong An, Huan Lu, Jiayang Shi et al. (+5 more)
Achieving ubiquitous high-accuracy localization is crucial for next-generation wireless systems, yet remains challenging in multipath-rich urban environments. By exploiting the fine-grained multipath characteristics embedded in channel state information (CSI), more reliable and precise localization can be achieved. To address this, we present CMANet, a multi-BS cooperative positioning architecture that performs feature-level fusion of raw CSI using the proposed Channel Masked
Attention (CMA) mechanism. The CMA encoder injects a physically grounded prior–per-BS channel gain–into the
attention weights, thus emphasizing reliable links and suppressing spurious multipath. A lightweight LSTM decoder then treats subcarriers as a sequence to accumulate frequency-domain evidence into a final 3D position estimate. In a typical 5G NR-compliant urban simulation, CMANet achieves less than 0.5m median error and 1.0m 90th-percentile error, outperforming state-of-the-art
benchmarks. Ablations verify the necessity of CMA and frequency accumulation. CMANet is edge-deployable and exemplifies an Integrated Sensing and Communication (
ISAC)-aligned, cooperative paradigm for multi-BS CSI positioning.
Read the full abstract ▾
All authors Tong An, Huan Lu, Jiayang Shi, Kai Yu, Rongrong Zhu, Bin Zheng, Jiwei Zhao, Haibo Zhou
Signal Processing · Cross-listed from cs.LG
Three-Way Emotion Classification of EEG-based Signals using Machine Learning
Ashna Purwar, Gaurav Simkar, Madhumita et al. (+1 more)
Electroencephalography (
EEG) is a widely used technique for measuring
brain activity.
EEG-based signals can reveal a persons emotional state, as they directly reflect activity in different
brain regions.
Emotion-aware systems and
EEG-based
emotion recognition are a growing research area. This paper presents how machine learning (ML) models categorize a limited
dataset of
EEG signals into three different classes, namely Negative, Neutral, or Positive. It also presents the complete workflow, including data preprocessing and comparison of ML models. To understand which ML classification model works best for this kind of problem, we train and test the following three commonly used models: logistic regression (LR), support vector machine (SVM), and random forest (RF). The performance of each is evaluated with respect to accuracy and F1-score. The results indicate that ML models can be effectively utilized for three-way
emotion classification of
EEG signals. Among the three ML models trained on the available
dataset, the RF model gave the best results. Its higher accuracy and F1-score suggest that it is able to capture the emotional patterns more accurately and effectively than the other two models. The RF model also outperformed the existing state-of-the-art classification models in terms of the accuracy parameter.
Read the full abstract ▾
All authors Ashna Purwar, Gaurav Simkar, Madhumita, Sachin Kadam
Signal Processing
Fronthaul-Efficient Distributed Cooperative 3D Positioning with Quantized Latent CSI Embeddings
Tong An, Jiwei Zhao, Jiayang Shi et al. (+5 more)
High-precision three-dimensional (3D) positioning in dense urban non-line-of-sight (NLOS) environments benefits significantly from cooperation among multiple distributed base stations (BSs). However, forwarding raw CSI from multiple BSs to a central unit (CU) incurs prohibitive fronthaul overhead, which limits scalable cooperative positioning in practice. This paper proposes a learning-based edge-cloud cooperative positioning framework under limited-capacity fronthaul constraints. In the proposed architecture, a neural network is deployed at each BS to compress the locally estimated CSI into a quantized representation subject to a fixed fronthaul payload. The quantized CSI is transmitted to the CU, which performs cooperative 3D positioning by jointly processing the compressed CSI received from multiple BSs. The proposed framework adopts a two-stage training strategy consisting of self-supervised local training at the BSs and end-to-end joint training for positioning at the CU. Simulation results based on a 3.5~GHz 5G NR compliant urban ray-tracing scenario with six BSs and 20~MHz bandwidth show that the proposed method achieves a mean 3D positioning error of 0.48~m and a 90th-percentile error of 0.83~m, while reducing the fronthaul payload to 6.25% of lossless CSI forwarding. The achieved performance is close to that of cooperative positioning with full CSI exchange.
Read the full abstract ▾
All authors Tong An, Jiwei Zhao, Jiayang Shi, Bin Zheng, Kai Yu, Maged Elkashlan, George K. Karagiannidis, Hongsheng Chen
Audio and Speech Processing
Solving Room Impulse Response Inverse Problems Using Flow Matching with Analytic Wiener Denoiser
Kyung Yun Lee, Nils Meyer-Kahlen, Vesa Välimäki et al. (+1 more)
Room impulse response (RIR) estimation naturally arises as a class of inverse problems, including denoising and deconvolution. While recent approaches often rely on supervised learning or learned generative priors, such methods require large amounts of training data and may generalize poorly outside the training distribution. In this work, we present RIRFlow, a training-free
Bayesian framework for RIR inverse problems using flow matching. We derive a flow-consistent analytic prior from the statistical structure of RIRs, eliminating the need for data-driven priors. Specifically, we model RIR as a Gaussian process with exponentially decaying variance, which yields a closed-form minimum mean squared error (MMSE) Wiener denoiser. This analytic denoiser is integrated as a prior in an existing flow-based inverse solver, where inverse problems are solved via guided posterior sampling. Furthermore, we extend the solver to nonlinear and non-Gaussian inverse problems via a local Gaussian approximation of the guided posterior, and empirically demonstrate that this approximation remains effective in practice. Experiments on real RIRs across different inverse problems demonstrate robust performance, highlighting the effectiveness of combining a classic RIR model with the recent flow-based generative inference.
Read the full abstract ▾
All authors Kyung Yun Lee, Nils Meyer-Kahlen, Vesa Välimäki, Sebastian J. Schlecht
Audio and Speech Processing
High-Fidelity Generative Audio Compression at 0.275kbps
Hao Ma, Ruihao Jing, Shansong Liu et al. (+4 more)
High-fidelity general audio compression at ultra-low bitrates is crucial for applications ranging from low-bandwidth communication to generative audio-
language modeling. Traditional audio compression methods and contemporary neural codecs are fundamentally designed for waveform reconstruction. As a result, when operating at ultra-low bitrates, these methods degrade rapidly and often fail to preserve essential information, leading to severe acoustic artifacts and pronounced semantic distortion. To overcome these limitations, we introduce Generative Audio Compression (GAC), a novel paradigm shift from signal fidelity to task-oriented effectiveness. Implemented within the AI Flow framework, GAC is theoretically grounded in the Law of Information Capacity. These foundations posit that abundant computational power can be leveraged at the receiver to offset extreme communication bottlenecks–exemplifying the More Computation, Less Bandwidth philosophy. By integrating semantic understanding at the transmitter with scalable generative synthesis at the receiver, GAC offloads the information burden to powerful model priors. Our 1.8B-parameter model achieves high-fidelity reconstruction of 32kHz general audio at an unprecedented bitrate of 0.275kbps. Even at 0.175kbps, it still preserves a strong intelligible audio transmission capability, which represents an about 3000x compression ratio, significantly outperforming current state-of-the-art neural codecs in maintaining both perceptual quality and semantic consistency.
Read the full abstract ▾
All authors Hao Ma, Ruihao Jing, Shansong Liu, Cheng Gong, Chi Zhang, Xiao-Lei Zhang, Xuelong Li
Systems and Control · Cross-listed from cs.LG
On the Equilibrium between Feasible Zone and Uncertain Model in Safe Exploration
Yujie Yang, Zhilong Zheng and Shengbo Eben Li
Ensuring the safety of environmental exploration is a critical problem in reinforcement learning (RL). While limiting exploration to a feasible zone has become widely accepted as a way to ensure safety, key questions remain unresolved: what is the maximum feasible zone achievable through exploration, and how can it be identified? This paper, for the first time, answers these questions by revealing that the goal of safe exploration is to find the
equilibrium between the feasible zone and the environment model. This conclusion is based on the understanding that these two components are interdependent: a larger feasible zone leads to a more accurate environment model, and a more accurate model, in turn, enables exploring a larger zone. We propose the first
equilibrium-oriented safe exploration framework called safe
equilibrium exploration (SEE), which alternates between finding the maximum feasible zone and the least uncertain model. Using a graph formulation of the uncertain model, we prove that the uncertain model obtained by SEE is monotonically refined, the feasible zones monotonically expand, and both converge to the
equilibrium of safe exploration. Experiments on classic control tasks show that our
algorithm successfully expands the feasible zones with zero constraint violation, and achieves the
equilibrium of safe exploration within a few iterations.
Read the full abstract ▾
Systems and Control
Model-Based Data-Efficient and Robust Reinforcement Learning
Ludvig Svedlund, Constantin Cronrath, Jonas Fredriksson et al. (+1 more)
A data-efficient learning-based control design method is proposed in this paper. It is based on learning a system dynamics model that is then leveraged in a two-level procedure. On the higher level, a simple but powerful optimization procedure is performed such that, for example, energy consumption in a vehicle can be reduced when hard state and action constraints are also introduced. Load disturbances and model errors are compensated for by a feedback controller on the lower level. In that regard, we briefly examine the robustness of both model-free and model-based learning approaches, and it is shown that the model-free approach greatly suffers from the inclusion of unmodeled dynamics. In evaluating the proposed method, it is assumed that a path is given, while the velocity and acceleration can be modified such that energy is saved, while still keeping speed limits and completion time. Compared with two well-known actor-critic reinforcement learning strategies, the suggested learning-based approach saves more energy and reduces the number of evaluated time steps by a factor of 100 or more.
Read the full abstract ▾
All authors Ludvig Svedlund, Constantin Cronrath, Jonas Fredriksson, Bengt Lennartson
Audio and Speech Processing · Cross-listed from cs.SD
The TMU System for the XACLE Challenge: Training Large Audio Language Models with CLAP Pseudo-Labels
Ayuto Tsutsumi, Kohei Tanaka and Sayaka Shiota
In this paper, we propose a submission to the x-to-audio
alignment (XACLE) challenge. The goal is to predict semantic
alignment of a given general audio and text pair. The proposed system is based on a large audio
language model (LALM) architecture. We employ a three-stage training pipeline: automated audio captioning pretraining, pretraining with CLAP pseudo-labels, and fine-tuning on the XACLE
dataset. Our experiments show that pretraining with CLAP pseudo-labels is the primary performance driver. On the XACLE test set, our system reaches an SRCC of 0.632, significantly outperforming the baseline system (0.334) and securing third place in the challenge team ranking. Code and models can be found at https://github.com/shiotalab-tmu/tmu-xacle2026
Read the full abstract ▾
Audio and Speech Processing · Cross-listed from cs.CL
Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling
Zhijie Huang, Stephen McIntosh, Daisuke Saito et al. (+1 more)
A good
language model starts with a good tokenizer. Tokenization is especially important for
speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A
speech tokenizer should extract phonetics and prosody, suppress linguistically irrelevant information like speaker identity, and enable high-quality synthesis. We present Kanade, a single-layer disentangled
speech tokenizer that realizes this ideal. Kanade separates out acoustic constants to create a single stream of
tokens that captures rich phonetics and prosody. It does so without the need for auxiliary methods that existing disentangled codecs often rely on. Experiments show that Kanade achieves state-of-the-art speaker disentanglement and lexical availability, while maintaining excellent reconstruction quality.
Read the full abstract ▾
All authors Zhijie Huang, Stephen McIntosh, Daisuke Saito, Nobuaki Minematsu
Audio and Speech Processing · Cross-listed from cs.SD
Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
Ke Xue, Rongfei Fan, Kai Li et al. (+3 more)
Diffusion models have recently set new
benchmarks in
Speech Enhancement (SE). However, most existing score-based models treat
speech spectrograms merely as generic 2D images, applying uniform processing that ignores the intrinsic structural sparsity of audio, which results in inefficient spectral representation and prohibitive computational complexity. To bridge this gap, we propose DVPD, an extremely lightweight Dual-View Predictive
Diffusion model, which uniquely exploits the dual nature of spectrograms as both visual textures and physical frequency-domain representations across both training and inference stages. Specifically, during training, we optimize spectral utilization via the Frequency-Adaptive Non-uniform Compression (FANC) encoder, which preserves critical low-frequency harmonics while
pruning high-frequency redundancies. Simultaneously, we introduce a Lightweight Image-based Spectro-Awareness (LISA) module to capture features from a visual perspective with minimal overhead. During inference, we propose a Training-free Lossless Boost (TLB) strategy that leverages the same dual-view priors to refine generation quality without any additional fine-tuning. Extensive experiments across various
benchmarks demonstrate that DVPD achieves state-of-the-art performance while requiring only 35% of the parameters and 40% of the inference MACs compared to SOTA lightweight model, PGUSE. These results highlight DVPD's superior ability to balance high-fidelity
speech quality with extreme architectural efficiency. Code and audio samples are available at the anonymous website: {https://anonymous.4open.science/r/dvpd_demo-E630}
Read the full abstract ▾
All authors Ke Xue, Rongfei Fan, Kai Li, Shanping Yu, Puning Zhao, Jianping An
Audio and Speech Processing · Cross-listed from cs.SD
Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards
Yong Ren, Jiangyan Yi, Jianhua Tao et al. (+3 more)
Imperceptible text-based
speech editing modifies spoken content through transcript manipulation while preserving acoustic continuity. Prior acoustic-space approaches suffer from content-style
entanglement, causing unstable generation and boundary artifacts. We introduce a framework guided by the principle of "Edit Content, Preserve Acoustics". Editing is conducted in a stable semantic space, while acoustic realization is handled by a Flow Matching decoder. To ensure perceptual consistency, we propose Self-Consistency Rewards Group Relative Policy Optimization, which leverages a pre-trained Text-to-
Speech model as an implicit critic, together with intelligibility and duration constraints. Experiments demonstrate consistent improvements over state-of-the-art autoregressive and non-autoregressive baselines in intelligibility, robustness, and perceptual quality.
Read the full abstract ▾
All authors Yong Ren, Jiangyan Yi, Jianhua Tao, Tao Wang, Le Xu, Zhengqi Wen
Systems and Control · Cross-listed from cs.LG
AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models
Apurba Prasad Padhy, Fernando Camacho and Saibal Mukhopadhyay
State space models (SSMs) often sacrifice capacity, search space, or stability to offset the
memory and compute costs of large state dimensions. We introduce a structured post-training
pruning method for SSMs – AIRE-Prune (Asymptotic Impulse-Response Energy for State PRUN(E)) – that reduces each layer's state dimension by directly minimizing long-run output-energy distortion. AIRE-Prune assigns every state a closed-form asymptotic impulse-response energy-based score, i.e., the total impulse-response energy it contributes over an infinite horizon (time), and normalizes these scores layer-wise to enable global cross-layer comparison and selection. This extends modal truncation from single systems to deep stacks and aligns
pruning with asymptotic response energy rather than worst-case gain. Across diverse sequence
benchmarks, AIRE-Prune reveals substantial redundancy in SISO and
MIMO SSMs with average
pruning of 60.8%, with average accuracy drop of 0.29% without retraining, while significantly lowering compute. Code: https://github.com/falcon-arrow/AIRE-Prune.
Read the full abstract ▾
Image and Video Processing
Recent Advances of End-to-End Video Coding Technologies for AVS Standard Development
Xihua Sheng, Xiongzhuang Liang, Chuanbo Tang et al. (+8 more)
Video coding standards are essential to enable the interoperability and widespread adoption of efficient
video compression technologies. In pursuit of greater
video compression efficiency, the AVS
video coding working group launched the standardization exploration of end-to-end intelligent
video coding, establishing the AVS End-to-End Intelligent
Video Coding Exploration Model (AVS-EEM) project. A core design principle of AVS-EEM is its focus on practical deployment, featuring inherently low computational complexity and requiring strict adherence to the common test conditions of conventional
video coding. This paper details the development history of AVS-EEM and provides a systematic introduction to its key technical framework, covering model architectures, training strategies, and inference optimizations. These innovations have collectively driven the project's rapid performance
evolution, enabling continuous and significant gains under strict complexity constraints. Through over two years of iterative refinement and collaborative effort, the coding performance of AVS-EEM has seen substantial improvement. Experimental results demonstrate that its latest model achieves superior compression efficiency compared to the conventional AVS3 reference software, marking a significant step toward a deployable intelligent
video coding standard.
Read the full abstract ▾
All authors Xihua Sheng, Xiongzhuang Liang, Chuanbo Tang, Zhirui Zuo, Yifan Bian, Yutao Xie, Zhuoyuan Li, Yuqi Li, Hui Xiang, Li Li, Dong Liu
Systems and Control
Stealthy Coverage Control for Human-enabled Real-Time 3D Reconstruction
Reiji Terunuma, Yuta Nakamura, Takuma Abe et al. (+1 more)
In this paper, we propose a novel semi-autonomous image sampling strategy, called stealthy coverage control, for human-enabled 3D structure reconstruction. The present mission involves a fundamental problem: while the number of images required to accurately reconstruct a 3D model depends on the structural complexity of the target scene to be reconstructed, it is not realistic to assume prior knowledge of the spatially non-uniform structural complexity. We approach this issue by leveraging human flexible
reasoning and situational recognition capabilities. Specifically, we design a semi-autonomous system that leaves identification of regions that need more images and
navigation of the drones to such regions to a human operator. To this end, we first present a way to reflect the human intention in autonomous coverage control. Subsequently, in order to avoid operational conflicts between manual control and autonomous coverage control, we develop the stealthy coverage control that decouples the drone motion for efficient image sampling from
navigation by the human. Simulation studies on a Unity/ROS2-based simulator demonstrate that the present semi-autonomous system outperforms the one without human interventions in the sense of the reconstructed model quality.
Read the full abstract ▾
All authors Reiji Terunuma, Yuta Nakamura, Takuma Abe, Takeshi Hatanaka
Audio and Speech Processing · Cross-listed from cs.SD
RVCBench: Benchmarking the Robustness of Voice Cloning Across Modern Audio Generation Models
Ruinan Jin, Xinting Liao, Hanlin Yu et al. (+2 more)
Modern Voice Cloning (VC) can synthesize
speech that closely matches a target speaker from only seconds of reference audio, enabling applications such as personalized
speech interfaces and dubbing. In practical deployments, modern audio generation models inevitably encounter noisy reference audios, imperfect text
prompts,
multilingual and long-form generation settings, downstream post-processing, and
adversarial perturbations, all of which can significantly hurt robustness. Despite rapid progress in VC driven by autoregressive codec-
token language models and
diffusion-based models, robustness under realistic deployment shifts remains underexplored. This paper introduces RVCBench, a comprehensive
dataset and
benchmark that evaluates Robustness in Voice Clone. RVCBench contributes a large-scale, task-aligned robustness
dataset that instantiates realistic deployment shifts through controlled text-audio pairing,
multilingual and long-form scenarios, expressive
prompts, post-processing conditions, and passive or proactive audio perturbations. Covering 18 robustness evaluations, 204 unique speakers, and 14,370 utterance-level evaluation items, RVCBench enables unified evaluation of input sensitivity, generation stability, output resilience, and perturbation robustness. We evaluate 18 representative modern open-source VC models and reveal systematic vulnerabilities in content consistency, speaker similarity, long-form stability, post-processing resilience,
adversarial robustness, and detector-facing separability. We open-source the toolkit and
dataset to support reproducible evaluation and future research.
Read the full abstract ▾
All authors Ruinan Jin, Xinting Liao, Hanlin Yu, Deval Pandya, Xiaoxiao Li
Signal Processing
Reliable IoT Communications in 6G Non-Terrestrial Networks with Dual RIS
Muddasir Rahim and Soumaya Cherkaoui
The increasing demand for Internet of Things (IoT) applications has accelerated the need for robust resource allocation in sixth-generation (6G) networks. In this paper, we propose a reconfigurable intelligent surface (RIS)-assisted upper mid-band communication framework. To ensure robust connectivity under severe line-of-sight (LoS) blockages, we use a two-tier RIS structure comprising terrestrial RISs (TRISs) and high-altitude platform station (HAPS)-mounted RISs (HRISs). To maximize network sum rate, we formulate a joint beamforming, power allocation, and IoT device association (JBPDA) problem as a mixed-integer nonlinear program (MINLP). The formulated MINLP problem is challenging to solve directly; therefore, we tackle it via a decomposition approach. The zero-forcing (ZF) technique is used to optimize the beamforming
matrix, a closed-form expression for power allocation is derived, and a stable matching-based
algorithm is proposed for device-RIS association based on achievable data rates. Comprehensive simulations demonstrate that the proposed scheme approaches the performance of exhaustive search (ES) while exhibiting substantially lower complexity, and it consistently outperforms greedy search (GS) and random search (RS) baselines. Moreover, the proposed scheme converges much faster than the ES scheme.
Read the full abstract ▾
Signal Processing
Dual-Tier IRS-Assisted Mid-Band 6G Mobile Networks: Robust Beamforming and User Association
Muddasir Rahim and Soumaya Cherkaoui
The rapid growth of Internet of Things (IoT) applications necessitates robust resource allocation in future sixth-generation (6G) networks, particularly at the upper mid-band (7-15 GHz, FR3). This paper presents a novel intelligent reconfigurable surface (IRS)-assisted framework combining terrestrial IRS (TIRS) and aerial IRS (AIRS) mounted on low-altitude platform stations, to ensure reliable connectivity under severe line-of-sight (LoS) blockages. Distinguishing itself from prior work restricted to terrestrial IRS and mmWave and THz bands, this work targets the FR3 spectrum, the so-called Golden Band for 6G. The joint beamforming and user association (JBUA) problem is formulated as a mixed-integer nonlinear program (MINLP), solved through problem decomposition, zero-forcing beamforming, and a stable matching
algorithm. Comprehensive simulations show our method approaches exhaustive search performance with significantly lower complexity, outperforming existing greedy and random baselines. These results provide a scalable blueprint for real-world 6G deployments, supporting massive IoT connectivity in challenging environments.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.LG
LLMs as High-Dimensional Nonlinear Autoregressive Models with Attention: Training, Alignment and Inference
Vikram Krishnamurthy
Large
language models (LLMs) based on
transformer architectures are typically described through collections of architectural components and training procedures, obscuring their underlying computational structure. This review article provides a concise mathematical reference for researchers seeking an explicit, equation-level description of LLM training,
alignment, and generation. We formulate LLMs as high-dimensional nonlinear autoregressive models with
attention-based dependencies. The framework encompasses pretraining via next-
token prediction,
alignment methods such as reinforcement learning from human feedback (RLHF), direct preference optimization (DPO), rejection sampling fine-tuning (RSFT), and reinforcement learning from verifiable rewards (RLVR), as well as autoregressive generation during inference. Self-
attention emerges naturally as a repeated bilinear–softmax–linear composition, yielding highly expressive sequence models. This formulation enables principled analysis of
alignment-induced behaviors (including sycophancy), inference-time phenomena (such as
hallucination, in-context learning, chain-of-thought prompting, and
retrieval-augmented generation), and extensions like continual learning, while serving as a concise reference for interpretation and further theoretical development.
Read the full abstract ▾