Papers

Combinatorial Optimization (CO) problems exhibit exponential complexity, making their resolution challenging. Simulated Adiabatic Bifurcation (aSB) is a quantum-inspired algorithm to obtain approximate solutions to largescale CO problems written in the Ising form. It explores the solution space by emulating the adiabatic evolution of a network of Kerr-nonlinear parametric oscillators (KPOs), where each oscillator represents a variable in the problem. The optimal solution corresponds to the ground state of this system. A key advantage of this approach is the possibility of updating multiple variables simultaneously, making it particularly suited for hardware implementation. To enhance solution quality and convergence speed, variations of the algorithm have been proposed in the literature, including ballistic (bSB), discrete (dSB), and thermal (HbSB) versions. In this work, we have comprehensively analyzed dSB, bSB, and HbSB using dedicated software models, evaluating the feasibility of using a fixed-point representation for hardware implementation. We then present an opensource hardware architecture implementing the dSB algorithm for Field-Programmable Gate Arrays (FPGAs). The design allows users to adjust the degree of algorithmic parallelization based on their specific requirements. A proof-of-concept implementation that solves 256-variable problems was achieved on an AMD Kria KV260 SoM, a low-tier FPGA, validated using well-known max-cut and knapsack problems.

Wind power producers can benefit from forming coalitions to participate cooperatively in electricity markets. To support such collaboration, various profit allocation rules rooted in cooperative game theory have been proposed. However, existing approaches overlook the lack of coherence among producers regarding forecast information, which may lead to ambiguity in offering and allocations. In this paper, we introduce a “reconcile-then-optimize” framework for cooperative market offerings. This framework first aligns the individual forecasts into a coherent joint forecast before determining market offers. With such forecasts, we formulate and solve a two-stage stochastic programming problem to derive both the aggregate offer and the corresponding scenario-based dual values for each trading hour. Based on these dual values, we construct a profit allocation rule that is budget-balanced and stable. Finally, we validate the proposed method through empirical case studies, demonstrating its practical effectiveness and theoretical soundness.

The widespread adoption of advanced video codecs such as AV1 is often hindered by their high decoding complexity, posing a challenge for battery-constrained devices. While encoders can be configured to produce bitstreams that are decoder-friendly, estimating the decoding complexity and energy overhead for a given video is non-trivial. In this study, we systematically analyse the impact of disabling various coding tools and adjusting coding parameters in two AV1 encoders, libaom-av1 and SVT-AV1. Using system-level energy measurement tools like RAPL (Running Average Power Limit), Intel SoC Watch (integrated with VTune profiler), we quantify the resulting trade-offs between decoding complexity, energy consumption, and compression efficiency for decoding a bitstream. Our results demonstrate that specific encoder configurations can substantially reduce decoding complexity with minimal perceptual quality degradation. For libaom-av1, disabling CDEF, an in-loop filter gives us a mean reduction in decoding cycles by 10%. For SVT-AV1, using the in-built, fast-decode=2 preset achieves a more substantial 24% reduction in decoding cycles. These findings provide strategies for content providers to lower the energy footprint of AV1 video streaming.

In the last decade, video workflows in the cinema production ecosystem have presented new use cases for video streaming technology. These new workflows, e.g. in On-set Virtual Production, present the challenge of requiring precise quality control and energy efficiency. Existing approaches to transcoding often fall short of these requirements, either due to a lack of quality control or computational overhead. To fill this gap, we present a lightweight neural network (LiteVPNet) for accurately predicting Quantisation Parameters for NVENC AV1 encoders that achieve a specified VMAF score. We use low-complexity features, including bitstream characteristics, video complexity measures, and CLIP-based semantic embeddings. Our results demonstrate that LiteVPNet achieves mean VMAF errors below 1.2 points across a wide range of quality targets. Notably, LiteVPNet achieves VMAF errors within 2 points for over 87% of our test corpus, c.f. approx 61% with state-of-the-art methods. LiteVPNet's performance across various quality regions highlights its applicability for enhancing high-value content transport and streaming for more energy-efficient, high-quality media experiences.

Undesired acoustic feedback is a known issue in communication systems, such as speech in-car communication, public address systems, or hearing aids. Without additional precautions, there is a high risk that the adaptive filter - intended to cancel the feedback path - also suppresses parts of the desired signal. One solution is to decorrelate the loudspeaker and microphone signals. In this work, we combine the two decorrelation approaches frequency shifting and phase modulation in a unified framework: a so-called phase synthesizer, implemented in a discrete Fourier transform (DFT) filter bank. Furthermore, we extend the phase modulation technique using variable delay lines, as known from vibrato and chorus effects. We demonstrate the benefits of the proposed phase synthesizer using an example from speech in-car communication, employing an adaptive frequency-domain Kalman filter. Improvements in system stability, speech quality measured by perceptual evaluation of speech quality (PESQ) are presented.

Reconfigurable intelligent surface (RIS) is a promising technology for future wireless communication systems. Conventional RIS is constrained to a diagonal scattering matrix, which limits its flexibility. Recently, beyond-diagonal RIS (BD-RIS) has been proposed as a more general RIS architecture class that allows inter-element connections and shows great potential for performance improvement. Despite extensive progress on BD-RIS, most existing studies rely on simplified channel models that ignore practical electromagnetic (EM) effects such as mutual coupling and impedance mismatching. To address this gap, this paper investigates the architecture design and optimization of BD-RIS under the general physics-consistent model derived with multiport network theory in recent literature. Building on a compact reformulation of this model, we show that band-connected RIS achieves the same channel-shaping capability as fully-connected RIS, which extends existing results obtained for conventional channel models. We then develop optimization methods under the general physics-consistent model; specifically, we derive closed-form solutions for single-input single-output (SISO) systems, propose a globally optimal semidefinite relaxation (SDR)-based algorithm for single-stream multi-input multi-output (MIMO) systems, and design an efficient alternating direction method of multipliers (ADMM)-based algorithm for multiuser MIMO systems. Using the proposed algorithms, we conduct comprehensive simulations to evaluate the impact of various EM effects and approximations. The results indicate that the commonly adopted unilateral approximation provides sufficient accuracy in RIS-aided systems and can therefore be readily adopted to simplify the channel model, whereas mutual coupling among RIS elements should be properly taken into account in channel modeling.

This paper proposes a unidirectionally connected fully actuated system (UC-FAS) approach for the sub-stabilization and tracking control of 6-DOF quadrotors, tackling limitations both in state-space and FAS framework to some extent. The framework systematically converts underactuated quadrotor dynamics into a UC-FAS model, unifying the existing different FAS transformation ways. By eliminating estimation of the high-order derivatives of control inputs, a drawback of current methods, the UC-FAS model simplifies controller design and enables direct eigenstructure assignment for closed-loop dynamics. Simulations demonstrate precise 6-DOF tracking performance. This work bridges theoretical FAS approach advancements with practical implementation needs, offering a standardized paradigm for nonlinear quadrotor control.

We propose a non-parametric frequency-domain method to identify small-signal $dq$-asymmetric grid impedances, over a wide frequency band, using grid-connected converters. Existing identification methods are faced with significant trade-offs: e.g., passive approaches rely on ambient harmonics and rare grid events and thus can only provide estimates at a few frequencies, while many active approaches that intentionally perturb grid operation require long time series measurement and specialized equipment. Although active time-domain methods reduce the measurement time, they either make crude simplifying assumptions or require laborious model order tuning. Our approach effectively addresses these challenges: it does not require specialized excitation signals or hardware and achieves ultrafast ($<1$ s) identification, drastically reducing measurement time. Being non-parametric, our approach also makes no assumptions on the grid structure. A detailed electromagnetic transient simulation is used to validate the method and demonstrate its clear superiority over existing alternatives.

Electric Vehicles (EVs) offer substantial flexibility for grid services, yet large-scale, uncoordinated charging can threaten voltage stability in distribution networks. Existing Reinforcement Learning (RL) approaches for smart charging often disregard physical grid constraints or have limited performance for complex large-scale tasks, limiting their scalability and real-world applicability. This paper introduces a physics-informed (PI) RL algorithm that integrates a differentiable power flow model and voltage-based reward design into the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, enabling EVs to deliver real-time voltage support while meeting user demands. The resulting PI-TD3 algorithm achieves faster convergence, improved sample efficiency, and reliable voltage magnitude regulation under uncertain and overloaded conditions. Benchmarks on the IEEE 34-bus and 123-bus networks show that the proposed PI-TD3 outperforms both model-free RL and optimization-based baselines in grid constraint management, user satisfaction, and economic metrics, even as the system scales to hundreds of EVs. These advances enable robust, scalable, and practical EV charging strategies that enhance grid resilience and support distribution networks operation.

This paper presents the Deep learning-based Perceptual Audio Quality metric (DeePAQ) for evaluating general audio quality. Our approach leverages metric learning together with the music foundation model MERT, guided by surrogate labels, to construct an embedding space that captures distortion intensity in general audio. To the best of our knowledge, DeePAQ is the first in the general audio quality domain to leverage weakly supervised labels and metric learning for fine-tuning a music foundation model with Low-Rank Adaptation (LoRA), a direction not yet explored by other state-of-the-art methods. We benchmark the proposed model against state-of-the-art objective audio quality metrics across listening tests spanning audio coding and source separation. Results show that our method surpasses existing metrics in detecting coding artifacts and generalizes well to unseen distortions such as source separation, highlighting its robustness and versatility.

Since the 1990s, widespread introduction of central (wholesale) electricity markets has been seen across multiple continents, driven by the search for efficient operation of the power grid through competition. The increase of renewables has made significant impacts both on central electricity markets and distribution-level grids as renewable power generation is often connected to the latter. These stochastic renewable technologies have both advantages and disadvantages. On one hand they offer very low marginal cost and carbon emissions, while on the other hand, their output is uncertain, requiring flexible backup power with high marginal cost. Flexibility from end-prosumers or smaller market participants is therefore seen as a key enabler of large-scale integration of renewables. However, current central electricity markets do not directly include uncertainty into the market clearing and do not account for physical constraints of distribution grids. In this paper we propose a local electricity market framework based on probabilistic locational marginal pricing, effectively accounting for uncertainties in production, consumption and grid variables. The model includes a representation of the grid using the lindistflow equations and accounts for the propagation of uncertainty using general Polynomial Chaos (gPC). A two-stage convex model is proposed; in the day-ahead stage, probability distributions of prices are calculated for every timestep, where the expected values represent the day-ahead (spot) prices. In the real-time stage, uncertainties are realized (measured) and a trivial calculation reveals the real-time price. Through four instructive case-studies we highlight the effectiveness of the method to incentivize end-prosumers' participation in the market, while ensuring that their behavior does not have an adverse impact on the operation of the grid.

A Hadamard matrix $H$ of order $n$ is a square matrix with entries $\pm 1$ satisfying $HH^T = nI_n$, where $I_n$ is the identity matrix of order $n$. A circulant Hadamard matrix is a Hadamard matrix whose rows are cyclic shifts of one another. This work establishes a unified algebraic framework that treats arbitrary Hadamard matrices as flexible seeds to systematically generate Golay complementary sets (GCS), cross Z-complementary sets (CZCS), complete complementary codes (CCC), and optimal cross-Z complementary sequence sets (CZCSS) through algebraic transformations. In this paper, a systematic framework using cyclic operators is presented. First, circulant Hadamard matrices of order 4 are utilized recursively to propose binary CZCS of arbitrary lengths, achieving a maximum ZCZ ratio of 2/3, and binary GCS. Significantly, this framework is generalized to establish that by employing binary or complex Hadamard matrices of any order, binary or non-binary CZCSs of arbitrary lengths can be constructed with a ZCZ ratio of 1/2. Furthermore, to provide flexible user capacity, an alternative construction of binary GCS of all lengths and Hadamard matrices of order $2^{a+1} 10^b 26^c$ ($a, b, c \geq 0$) is proposed using circulant matrices and Golay complementary pairs (GCP). These constructions are further extended to form binary CCC with parameters $(2N, 2N, 2N)$, where $N=2^a 10^b 26^c$, and $(4n, 4n, 4n)$ for $n \geq 1$. Additionally, optimal binary $(8n, 8n, 8n, 4n)$-CZCSS and their complex versions with parameters $(2m, 2m, 2m, m)$ are proposed for $n, m \geq 1$. These results provide the first generalized framework for constructing optimal CZCSS from arbitrary Hadamard seeds. Finally, a theoretical relation between Hadamard matrices and GCSs is established, and fundamental properties of circulant matrices over aperiodic correlation functions are presented.

Standardized (link-level) channel models such as the 3GPP TDL and CDL models are frequently used to evaluate machine learning (ML)-based physical-layer methods. However, in this work, we argue that a link-level perspective incorporates limiting assumptions, causing unwanted distributional shifts or necessitating impractical online training. An additional drawback is that this perspective leads to (near-)Gaussian channel characteristics. Thus, ML-based models, trained on link-level channel data, do not outperform classical approaches for a variety of physical-layer applications. Particularly, we demonstrate the optimality of simple linear methods for channel compression, estimation, and modeling, revealing the unsuitability of link-level channel models for evaluating ML models. On the upside, adopting a scenario-level perspective offers a solution to this problem and unlocks the relative gains enabled by ML.

The quality of experience (QoE) delivered by video conferencing systems is significantly influenced by accurately estimating the time-varying available bandwidth between the sender and receiver. Bandwidth estimation for real-time communications remains an open challenge due to rapidly evolving network architectures, increasingly complex protocol stacks, and the difficulty of defining QoE metrics that reliably improve user experience. In this work, we propose a deployed, human-in-the-loop, data-driven framework for bandwidth estimation to address these challenges. Our approach begins with training objective QoE reward models derived from subjective user evaluations to measure audio and video quality in real-time video conferencing systems. Subsequently, we collect roughly $1$M network traces with objective QoE rewards from real-world Microsoft Teams calls to curate a bandwidth estimation training dataset. We then introduce a novel distributional offline reinforcement learning (RL) algorithm to train a neural-network-based bandwidth estimator aimed at improving QoE for users. Our real-world A/B test demonstrates that the proposed approach reduces the subjective poor call ratio by $11.41\%$ compared to the baseline bandwidth estimator. Furthermore, the proposed offline RL algorithm is benchmarked on D4RL tasks to demonstrate its generalization beyond bandwidth estimation.

Visible-infrared image fusion is crucial in key applications such as autonomous driving and nighttime surveillance. Its main goal is to integrate multimodal information to produce enhanced images that are better suited for downstream tasks. Although deep learning based fusion methods have made significant progress, mainstream unsupervised approaches still face serious challenges in practical applications. Existing methods mostly rely on manually designed loss functions to guide the fusion process. However, these loss functions have obvious limitations. On one hand, the reference images constructed by existing methods often lack details and have uneven brightness. On the other hand, the widely used gradient losses focus only on gradient magnitude. To address these challenges, this paper proposes an angle-based perception framework for spatial-sensitive image fusion (AngularFuse). At first, we design a cross-modal complementary mask module to force the network to learn complementary information between modalities. Then, a fine-grained reference image synthesis strategy is introduced. By combining Laplacian edge enhancement with adaptive histogram equalization, reference images with richer details and more balanced brightness are generated. Last but not least, we introduce an angle-aware loss, which for the first time constrains both gradient magnitude and direction simultaneously in the gradient domain. AngularFuse ensures that the fused images preserve both texture intensity and correct edge orientation. Comprehensive experiments on the MSRS, RoadScene, and M3FD public datasets show that AngularFuse outperforms existing mainstream methods with clear margin. Visual comparisons further confirm that our method produces sharper and more detailed results in challenging scenes, demonstrating superior fusion capability.

In the multimedia domain, Infrared Small Target Detection (ISTD) plays a important role in drone-based multi-modality sensing. To address the dual challenges of cross-domain shift and heteroscedastic noise perturbations in ISTD, we propose a doubly wavelet-guided Invariance learning framework(Ivan-ISTD). In the first stage, we generate training samples aligned with the target domain using Wavelet-guided Cross-domain Synthesis. This wavelet-guided alignment machine accurately separates the target background through multi-frequency wavelet filtering. In the second stage, we introduce Real-domain Noise Invariance Learning, which extracts real noise characteristics from the target domain to build a dynamic noise library. The model learns noise invariance through self-supervised loss, thereby overcoming the limitations of distribution bias in traditional artificial noise modeling. Finally, we create the Dynamic-ISTD Benchmark, a cross-domain dynamic degradation dataset that simulates the distribution shifts encountered in real-world applications. Additionally, we validate the versatility of our method using other real-world datasets. Experimental results demonstrate that our approach outperforms existing state-of-the-art methods in terms of many quantitative metrics. In particular, Ivan-ISTD demonstrates excellent robustness in cross-domain scenarios. The code for this work can be found at: https://github.com/nanjin1/Ivan-ISTD.

Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under distribution shift and offer limited levers for controllability. We introduce DISTAR, a zero-shot text-to-speech framework that operates entirely in a discrete residual vector quantization (RVQ) code space and tightly couples an AR language model with a masked diffusion model, without forced alignment or a duration predictor. Concretely, DISTAR drafts block-level RVQ tokens with an AR language model and then performs parallel masked-diffusion infilling conditioned on the draft to complete the next block, yielding long-form synthesis with blockwise parallelism while mitigating classic AR exposure bias. The discrete code space affords explicit control at inference: DISTAR produces high-quality audio under both greedy and sample-based decoding using classifier-free guidance, supports trade-offs between robustness and diversity, and enables variable bit-rate and controllable computation via RVQ layer pruning at test time. Extensive experiments and ablations demonstrate that DISTAR surpasses state-of-the-art zero-shot TTS systems in robustness, naturalness, and speaker/style consistency, while maintaining rich output diversity. Audio samples are provided on https://anonymous.4open.science/w/DiSTAR_demo.

The most startling of the contemporary problems is the sleepiness of chauffeur which causes lots of car accidents. Prevention of those impending accidents by detecting and alerting the sleepy chauffeur is vital, otherwise that would lead to loss of lives and various traumas along with severe injuries. The slumber or sleep may be caused by huge stress, pressure, relentless work load or alcoholism, for which sleep deprivation occurs and the chauffeur while driving gets drowsy. So far, considerable amount of systems has been developed to detect drowsiness of drivers, most of which mainly depend on image processing algorithms using cameras. Some of them also incorporate artificial intelligence and machine learning based algorithms. This paper presents a review of the existing systems and also proposes an easy and cheap system using sensors and Arduino, capable of detecting sleepiness and generates siren alarm and send alert message to take precautionary measures.

Integrated sensing and communications (ISAC) is considered an innovative technology in sixth-generation (6G) wireless networks, where utilizing orthogonal frequency division multiplexing (OFDM) communication signals for sensing provides a cost-effective solution for implementing ISAC. However, the sensing performance of matched and mismatched filtering schemes can be significantly deteriorated due to the signaling randomness induced by finite-alphabet modulations with nonconstant modulus, such as quadrature amplitude modulation (QAM) constellations. Therefore, improving sensing performance without significantly compromising communication capability (i.e., maintaining randomness), remains a challenging task. To that end, we propose a unified probabilistic constellation shaping (PCS) framework that is compatible with both matched and mismatched filtering schemes, by maximizing the communication rate while imposing constraints on mean square error (MSE) of sensing channel state information (CSI), power, and probability distribution. Specifically, the MSE of sensing CSI is leveraged to optimize sensing capability, which is illustrated to be a more comprehensive metric compared to the output SNR after filtering (SNRout) and integrated sidelobes ratio (ISLR). Additionally, the internal relationships among these three sensing metrics are explicitly analyzed. Finally, both simulations and field measurements validate the efficiency of proposed PCS approach in achieving a flexible S&C trade-off, as well as its credibility in enhancing 6G wireless transmission in real-world scenarios.

Impulsive noise poses a significant challenge to the reliability of wireless communication systems, necessitating accurate estimation of its statistical parameters for effective mitigation. This paper introduces a multitask learning (MTL) framework based on a CNN-LSTM architecture enhanced with an attention mechanism for the joint estimation of impulsive noise parameters. The proposed model leverages a unified weighted-loss function to enable simultaneous learning of multiple parameters within a shared representation space, improving learning efficiency and generalization across related tasks. Experimental results show that the proposed MTL framework achieves stable convergence, faster training, and enhanced scalability with modest computational overhead. Benchmarking against conventional single-task learning (STL) models confirms its favorable complexity-performance trade-off and significant memory savings, indicating the effectiveness of the MTL approach for real-time impulsive noise parameter estimation in wireless systems.

Recent advances in diffusion-based generative models have enabled high-quality text-to-audio synthesis, but fine-grained acoustic control remains a significant challenge in open-source research. We present Audio Palette, a diffusion transformer (DiT) based model that extends the Stable Audio Open architecture to address this "control gap" in controllable audio generation. Unlike prior approaches that rely solely on semantic conditioning, Audio Palette introduces four time-varying control signals, loudness, pitch, spectral centroid, and timbre, for precise and interpretable manipulation of acoustic features. The model is efficiently adapted for the nuanced domain of Foley synthesis using Low-Rank Adaptation (LoRA) on a curated subset of AudioSet, requiring only 0.85% of the original parameters to be trained. Experiments demonstrate that Audio Palette achieves fine-grained, interpretable control of sound attributes. Crucially, it accomplishes this novel controllability while maintaining high audio quality and strong semantic alignment to text prompts, with performance on standard metrics such as Frechet Audio Distance (FAD) and LAION-CLAP scores remaining comparable to the original baseline model. We provide a scalable, modular pipeline for audio research, emphasizing sequence-based conditioning, memory efficiency, and a three-scale classifier-free guidance mechanism for nuanced inference-time control. This work establishes a robust foundation for controllable sound design and performative audio synthesis in open-source settings, enabling a more artist-centric workflow in the broader context of music and sound information retrieval.

Autonomous ground vehicles operating off-road must plan curvature-feasible paths while accounting for spatially varying soil strength and slope hazards in real time. We present a continuous state–cost metric that combines a Bekker pressure–sinkage model with elevation-derived slope and attitude penalties. The resulting terrain cost field is analytic, bounded, and monotonic in soil modulus and slope, ensuring well-posed discretization and stable updates under sensor noise. This metric is evaluated on a lattice with exact steering primitives: Dubins and Reeds–Shepp motions for differential drive and time-parameterized bicycle arcs for Ackermann steering. Global exploration is performed using Vehicle-Dynamics RRT\(^{*}\), while local repair is managed by Vehicle-Dynamics D\(^{*}\) Lite, enabling millisecond-scale replanning without heuristic smoothing. By separating the terrain–vehicle model from the planner, the framework provides a reusable basis for deterministic, sampling-based, or learning-driven planning in deformable terrain. Hardware trials on an off-road platform demonstrate real-time navigation across soft soil and slope transitions, supporting reliable autonomy in unstructured environments.

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec compression or malicious removal attacks. To address these issues, we propose FakeMark, a novel watermarking framework that injects artifact-correlated watermarks associated with deepfake systems rather than pre-assigned bitstring messages. This design allows a detector to attribute the source system by leveraging both injected watermark and intrinsic deepfake artifacts, remaining effective even if one of these cues is elusive or removed. Experimental results show that FakeMark improves generalization to cross-dataset samples where classifier-based solutions struggle and maintains high accuracy under various distortions where conventional watermarking-based solutions fail.

In audio signal processing, the interpretation of complex information using visual representation enhances pattern recognition through its alignment with human perceptual systems. Software tools that carry hidden assumptions inherited from their historical contexts risk misalignment with modern workflows as design origins become obscured. We argue that creating tools that align with emergent needs improves analytical and creative outputs due to an increased affinity for using them. This paper explores the potentials associated with adding dimensionality and interactivity into visualization tools to facilitate complex workflows in audio information research using the Jellyfish Dynamite software.

This thesis delves into the world of non-invasive electrophysiological brain signals like electroencephalography (EEG) and magnetoencephalography (MEG), focusing on modelling and decoding such data. The research aims to investigate what happens in the brain when we perceive visual stimuli or engage in covert speech (inner speech) and enhance the decoding performance of such stimuli. The thesis is divided into two main sections, methodological and experimental work. A central concern in both sections is the large variability present in electrophysiological recordings, whether it be within-subject or between-subject variability, and to a certain extent between-dataset variability. In the methodological sections, we explore the potential of deep learning for brain decoding. We present advancements in decoding visual stimuli using linear models at the individual subject level. We then explore how deep learning techniques can be employed for group decoding, introducing new methods to deal with between-subject variability. Finally, we also explores novel forecasting models of MEG data based on convolutional and Transformer-based architectures. In particular, Transformer-based models demonstrate superior capabilities in generating signals that closely match real brain data, thereby enhancing the accuracy and reliability of modelling the brain's electrophysiology. In the experimental section, we present a unique dataset containing high-trial inner speech EEG, MEG, and preliminary optically pumped magnetometer (OPM) data. Our aim is to investigate different types of inner speech and push decoding performance by collecting a high number of trials and sessions from a few participants. However, the decoding results are found to be mostly negative, underscoring the difficulty of decoding inner speech.

JPEG AI is an emerging learning-based image coding standard developed by Joint Photographic Experts Group (JPEG). The scope of the JPEG AI is the creation of a practical learning-based image coding standard offering a single-stream, compact compressed domain representation, targeting both human visualization and machine consumption. Scheduled for completion in early 2025, the first version of JPEG AI focuses on human vision tasks, demonstrating significant BD-rate reductions compared to existing standards, in terms of MS-SSIM, FSIM, VIF, VMAF, PSNR-HVS, IW-SSIM and NLPD quality metrics. Designed to ensure broad interoperability, JPEG AI incorporates various design features to support deployment across diverse devices and applications. This paper provides an overview of the technical features and characteristics of the JPEG AI standard.

Human communication is multimodal, with speech and gestures tightly coupled, yet most computational methods for generating speech and gestures synthesize them sequentially, weakening synchrony and prosody alignment. We introduce Gelina, a unified framework that jointly synthesizes speech and co-speech gestures from text using interleaved token sequences in a discrete autoregressive backbone, with modality-specific decoders. Gelina supports multi-speaker and multi-style cloning and enables gesture-only synthesis from speech inputs. Subjective and objective evaluations demonstrate competitive speech quality and improved gesture generation over unimodal baselines.

Limited visibility of distribution network power flows at the low voltage level presents challenges to both distribution network operators from a planning perspective and distribution system operators from a congestion management perspective. More representative loads are required to support meaningful analysis of LV substations; otherwise, such analysis risks misinforming future decisions. Traditional load profiling relies on typical profiles, oversimplifying substation-level complexity. Generative models have attempted to address this through synthesising representative loads from historical exemplars; however, while these approaches can approximate load shapes to a convincing degree of fidelity, analysis of the co-behaviour between substations is limited, which ultimately impacts higher voltage level network operation. This limitation will become even more pronounced with the increasing integration of low-carbon technologies, as estimates of base loads fail to capture load diversity. To address this gap, Conditional Diffusion models for synthesising daily active and reactive power profiles at the low voltage distribution substation level are proposed. The evaluation of fidelity is demonstrated through conventional metrics capturing temporal and statistical realism, as well as power flow modelling. Multiple models are proposed to handle varying levels of data availability, ranging from unconditional synthesis to an informed generation driven by metadata and daily statistics. The results show synthesised load profiles are plausible both independently and as a cohort in a wider power systems context. The Conditional Diffusion model is benchmarked against both naive and state-of-the-art models to demonstrate its effectiveness in producing realistic scenarios on which to base sub-regional power distribution network planning and operations.

We demonstrate a record-high 62.6 GHz solidly mounted acoustic resonator (SMR) incorporating a 67.6 nm scandium aluminum nitride (Sc0.3Al0.7N) piezoelectric layer on a 40 nm buried platinum (Pt) bottom electrode, positioned above an acoustic Bragg reflector composed of alternating SiO2 (28.2 nm) and Ta2O5 (24.3 nm) layers in 8.5 pairs. The Bragg reflector and piezoelectric stack above are designed to confine a third-order thickness-extensional (TE) bulk acoustic wave (BAW) mode, while efficiently transducing with thickness-field excitation. The fabricated SMR exhibits an extracted piezoelectric coupling coefficient (k2) of 0.8% and a maximum Bode quality factor (Q) of 51 at 63 GHz, representing the highest operating frequency reported for an SMR to date. These results establish a pathway toward mmWave SMR devices for filters and resonators in next-generation RF front ends.

Diffusion models (DMs) have rapidly emerged as a powerful framework for image generation and restoration. However, existing DMs are primarily trained in a supervised manner by using a large corpus of clean images. This reliance on clean data poses fundamental challenges in many real-world scenarios, where acquiring noise-free data is hard or infeasible, and only noisy and potentially incomplete measurements are available. While some methods can train DMs using noisy data, they are generally effective only when the amount of noise is very mild or when some additional noise-free data is available. In addition, existing methods for training DMs from incomplete measurements require access to multiple complementary acquisition processes, an assumption that poses a significant practical limitation. Here we introduce the first approach for learning DMs for image restoration using only noisy measurement data from a single operator. As a first key contribution, we show that DMs, and more broadly minimum mean squared error denoisers, exhibit a weak form of scale equivariance linking rescaling in signal amplitude to changes in noise intensity. We then leverage this theoretical insight to develop a denoising score-matching strategy that generalizes robustly to noise levels lower than those present in the training data, thereby enabling the learning of DMs from noisy measurements. To further address the challenges of incomplete and noisy data, we integrate our method with equivariant imaging, a complementary self-supervised learning framework that exploits the inherent invariants of imaging problems, to train DMs for image restoration from single-operator measurements that are both incomplete and noisy. We validate the effectiveness of our approach through extensive experiments on image denoising, demosaicing, and inpainting, along with comparisons with the state of the art.