Fusion

arXiv:2602.02056v1 Announce Type: cross Abstract: Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales. Meeting these requirements demands low-latency, fixed-precision computation under strict memory constraints, a regime in which conventional Multi-Layer Perceptrons (MLPs) are both inefficient and numerically unstable. We identify key properties of Kolmogorov-Arnold Networks (KANs) that align with these constraints. Specifically, we show that: (i) KAN updates exploiting B-spline locality are sparse, enabling superior on-chip resource scaling, and (ii) KANs are inherently robust to fixed-point quantization. By implementing fixed-point online training on Field-Programmable Gate Arrays (FPGAs), a representative platform for on-chip computation, we demonstrate that KAN-based online learners are significantly more efficient and expressive than MLPs across a

arXiv:2602.00037v1 Announce Type: new Abstract: In this work, we propose to apply a new model fusion and learning paradigm, known as Combinatorial Fusion Analysis (CFA), to the field of Bitcoin price prediction. Price prediction of financial product has always been a big topic in finance, as the successful prediction of the price can yield significant profit. Every machine learning model has its own strength and weakness, which hinders progress toward robustness. CFA has been used to enhance models by leveraging rank-score characteristic (RSC) function and cognitive diversity in the combination of a moderate set of diverse and relatively well-performed models. Our method utilizes both score and rank combinations as well as other weighted combination techniques. Key metrics such as RMSE and MAPE are used to evaluate our methodology performance. Our proposal presents a notable MAPE performance of 0.19\%. The proposed method greatly improves upon individual model performance, as well as

arXiv:2601.11665v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) are transforming infrastructure inspections in the Architecture, Engineering, Construction, and Facility Management (AEC+FM) domain. By synthesizing insights from over 150 studies, this review paper highlights UAV-based methodologies for data acquisition, photogrammetric modeling, defect detection, and decision-making support. Key innovations include path optimization, thermal integration, and advanced machine learning (ML) models such as YOLO and Faster R-CNN for anomaly detection. UAVs have demonstrated value in structural health monitoring (SHM), disaster response, urban infrastructure management, energy efficiency evaluations, and cultural heritage preservation. Despite these advancements, challenges in real-time processing, multimodal data fusion, and generalizability remain. A proposed workflow framework, informed by literature and a case study, integrates RGB imagery, LiDAR, and thermal sensing

arXiv:2602.00102v1 Announce Type: cross Abstract: Radiomics enables quantitative medical image analysis by converting imaging data into structured, high-dimensional feature representations for predictive modeling. Despite methodological developments and encouraging retrospective results, radiomics continue to face persistent challenges related to feature instability, limited reproducibility, validation bias, and restricted clinical translation. Existing reviews largely focus on application-specific outcomes or isolated pipeline components, with limited analysis of how interdependent design choices across acquisition, preprocessing, feature engineering, modeling, and evaluation collectively affect robustness and generalizability. This survey provides an end-to-end analysis of radiomics pipelines, examining how methodological decisions at each stage influence feature stability, model reliability, and translational validity. This paper reviews radiomic feature extraction, selection, and

arXiv:2602.00042v1 Announce Type: cross Abstract: The transition toward cognitive global navigation satellite system (GNSS) receivers requires accurate interference classification to trigger adaptive mitigation strategies. However, conventional methods relying on Time-Frequency Analysis (TFA) and Convolutional Neural Networks (CNNs) face two fundamental limitations: severe performance degradation in low Jamming-to-Signal Ratio (JSR) regimes due to noise obscuration, and ``feature degeneracy'' caused by the loss of phase information in magnitude-only spectrograms. Consequently, spectrally similar signals -- such as high-order Quadrature Amplitude Modulation versus Band-Limited Gaussian Noise -- become indistinguishable. To overcome these challenges, this paper proposes the \textbf{JSR-Guided Fusion Network (JSR-GFNet)}. This multi-modal architecture combines phase-sensitive complex In-Phase/Quadrature (IQ) samples with Short-Time Fourier Transform (STFT) spectrograms. Central to this

arXiv:2602.00037v1 Announce Type: cross Abstract: In this work, we propose to apply a new model fusion and learning paradigm, known as Combinatorial Fusion Analysis (CFA), to the field of Bitcoin price prediction. Price prediction of financial product has always been a big topic in finance, as the successful prediction of the price can yield significant profit. Every machine learning model has its own strength and weakness, which hinders progress toward robustness. CFA has been used to enhance models by leveraging rank-score characteristic (RSC) function and cognitive diversity in the combination of a moderate set of diverse and relatively well-performed models. Our method utilizes both score and rank combinations as well as other weighted combination techniques. Key metrics such as RMSE and MAPE are used to evaluate our methodology performance. Our proposal presents a notable MAPE performance of 0.19\%. The proposed method greatly improves upon individual model performance, as well

arXiv:2602.02056v1 Announce Type: new Abstract: Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales. Meeting these requirements demands low-latency, fixed-precision computation under strict memory constraints, a regime in which conventional Multi-Layer Perceptrons (MLPs) are both inefficient and numerically unstable. We identify key properties of Kolmogorov-Arnold Networks (KANs) that align with these constraints. Specifically, we show that: (i) KAN updates exploiting B-spline locality are sparse, enabling superior on-chip resource scaling, and (ii) KANs are inherently robust to fixed-point quantization. By implementing fixed-point online training on Field-Programmable Gate Arrays (FPGAs), a representative platform for on-chip computation, we demonstrate that KAN-based online learners are significantly more efficient and expressive than MLPs across a

arXiv:2601.23140v1 Announce Type: new Abstract: The electron density at the separatrix ($n_{e,\mathrm{sep}}$) plays a central role in balancing energy confinement, detachment achievement, and ELM suppression in tokamaks, thereby influencing core-edge integration. To study what determines this key parameter, a database of H-mode separatrix density measurements from Alcator C-Mod, ASDEX Upgrade, and JET tokamaks has been assembled using a consistent analysis method across all devices. This dataset is used to derive a regression scaling expression based solely on engineering parameters, and the results are compared to predictions from the two-point model. The agreement found is remarkable: both the regression and model provide similar parameter dependencies and tokamak-specific multiplicative constants. Building on this agreement, a fully predictive formula that combines the regression dependencies and the two-point model multiplicative constant is proposed. This formula is able to

arXiv:2601.23167v1 Announce Type: new Abstract: Video relighting offers immense creative potential and commercial value but is hindered by challenges, including the absence of an adequate evaluation metric, severe light flickering, and the degradation of fine-grained details during editing. To overcome these challenges, we introduce Hi-Light, a novel, training-free framework for high-fidelity, high-resolution, robust video relighting. Our approach introduces three technical innovations: lightness prior anchored guided relighting diffusion that stabilises intermediate relit video, a Hybrid Motion-Adaptive Lighting Smoothing Filter that leverages optical flow to ensure temporal stability without introducing motion blur, and a LAB-based Detail Fusion module that preserves high-frequency detail information from the original video. Furthermore, to address the critical gap in evaluation, we propose the Light Stability Score, the first quantitative metric designed to specifically measure

arXiv:2601.22406v1 Announce Type: new Abstract: The contribution describes a pedestrian navigation approach designed to improve localization accuracy in urban environments where GNSS performance is degraded, a problem that is especially critical for blind or low-vision users who depend on precise guidance such as identifying the correct side of a street. To address GNSS limitations and the impracticality of camera-based visual positioning, the work proposes a particle filter based fusion of GNSS and inertial data that incorporates spatial priors from maps, such as impassable buildings and unlikely walking areas, functioning as a probabilistic form of map matching. Inertial localization is provided by the RoNIN machine learning method, and fusion with GNSS is achieved by weighting particles based on their consistency with GNSS estimates and uncertainty. The system was evaluated on six challenging walking routes in downtown San Francisco using three metrics related to sidewalk

arXiv:2601.21482v1 Announce Type: new Abstract: Unpredictable sensor-to-estimator delays fundamentally distort what matters for wireless remote state estimation: not just freshness, but how delay interacts with sensor informativeness and energy efficiency. In this paper, we present a unified, delay-aware framework that models this coupling explicitly and quantifies a delay-dependent information gain, motivating an information-per-joule scheduling objective beyond age of information proxies (AoI). To this end, we first introduce an efficient posterior-fusion update that incorporates delayed measurements without state augmentation, providing a consistent approximation to optimal delayed Kalman updates, and then derive tractable stability conditions ensuring that bounded estimation error is achievable under stochastic, delayed scheduling. This conditions highlight the need for unstable modes to be observable across sensors. Building on this foundation, we cast scheduling as a Markov

arXiv:2601.21724v1 Announce Type: new Abstract: This paper summarizes and consolidates fusion power-plant costing work performed in support of ARPA-E from 2017 through 2024, and documents the evolution of the associated analysis framework from early capital-cost-focused studies to a standards-aligned, auditable costing capability. Early efforts applied ARIES-style cost-scaling relations to generate Nth-of-a-kind (NOAK) estimates and were calibrated through a pilot study with Bechtel and Decysive Systems to benchmark balance-of-plant (BOP) costs and validate plant-level reasonableness from an engineering, procurement, and construction (EPC) perspective. Subsequent work, informed by Lucid Catalyst studies of nuclear cost drivers, expanded the methodology to treat indirect costs explicitly and to evaluate cost-reduction pathways for non-fusion-island systems through design-for-cost practices, modularization, centralized manufacturing, and learning. As ARPA-E's fusion portfolio expanded,

arXiv:2601.21724v1 Announce Type: cross Abstract: This paper summarizes and consolidates fusion power-plant costing work performed in support of ARPA-E from 2017 through 2024, and documents the evolution of the associated analysis framework from early capital-cost-focused studies to a standards-aligned, auditable costing capability. Early efforts applied ARIES-style cost-scaling relations to generate Nth-of-a-kind (NOAK) estimates and were calibrated through a pilot study with Bechtel and Decysive Systems to benchmark balance-of-plant (BOP) costs and validate plant-level reasonableness from an engineering, procurement, and construction (EPC) perspective. Subsequent work, informed by Lucid Catalyst studies of nuclear cost drivers, expanded the methodology to treat indirect costs explicitly and to evaluate cost-reduction pathways for non-fusion-island systems through design-for-cost practices, modularization, centralized manufacturing, and learning. As ARPA-E's fusion portfolio

arXiv:2601.21482v1 Announce Type: new Abstract: Unpredictable sensor-to-estimator delays fundamentally distort what matters for wireless remote state estimation: not just freshness, but how delay interacts with sensor informativeness and energy efficiency. In this paper, we present a unified, delay-aware framework that models this coupling explicitly and quantifies a delay-dependent information gain, motivating an information-per-joule scheduling objective beyond age of information proxies (AoI). To this end, we first introduce an efficient posterior-fusion update that incorporates delayed measurements without state augmentation, providing a consistent approximation to optimal delayed Kalman updates, and then derive tractable stability conditions ensuring that bounded estimation error is achievable under stochastic, delayed scheduling. This conditions highlight the need for unstable modes to be observable across sensors. Building on this foundation, we cast scheduling as a Markov

arXiv:2601.21453v1 Announce Type: new Abstract: Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multimodal-attributed graphs. This advancement significantly enhances data representation and expands the scope of graph downstream tasks, such as modality-oriented tasks, thereby improving the practical utility of graph ML. Despite its promise, limitations exist in the current neural paradigms: (1) Neglect Context in Modality Alignment: Most existing methods adopt topology-constrained or modality-specific operators as tokenizers. These aligners inevitably neglect graph context and inhibit modality interaction, resulting in suboptimal alignment. (2) Lack of Adaptation in Modality Fusion: Most existing methods are simple adaptations for 2-modality graphs and fail to adequately exploit aligned tokens equipped with topology priors during fusion, leading to poor generalizability and performance

arXiv:2601.20043v1 Announce Type: cross Abstract: Standard Bayesian Optimization (BO) assumes uniform smoothness across the search space an assumption violated in multi-regime problems such as molecular conformation search through distinct energy basins or drug discovery across heterogeneous molecular scaffolds. A single GP either oversmooths sharp transitions or hallucinates noise in smooth regions, yielding miscalibrated uncertainty. We propose RAMBO, a Dirichlet Process Mixture of Gaussian Processes that automatically discovers latent regimes during optimization, each modeled by an independent GP with locally-optimized hyperparameters. We derive collapsed Gibbs sampling that analytically marginalizes latent functions for efficient inference, and introduce adaptive concentration parameter scheduling for coarse-to-fine regime discovery. Our acquisition functions decompose uncertainty into intra-regime and inter-regime components. Experiments on synthetic benchmarks and real-world

arXiv:2601.20104v1 Announce Type: new Abstract: Nuclei instance segmentation in hematoxylin and eosin (H&E)-stained images plays an important role in automated histological image analysis, with various applications in downstream tasks. While several machine learning and deep learning approaches have been proposed for nuclei instance segmentation, most research in this field focuses on developing new segmentation algorithms and benchmarking them on a limited number of arbitrarily selected public datasets. In this work, rather than focusing on model development, we focused on the datasets used for this task. Based on an extensive literature review, we identified manually annotated, publicly available datasets of H&E-stained images for nuclei instance segmentation and standardized them into a unified input and annotation format. Using two state-of-the-art segmentation models, one based on convolutional neural networks (CNNs) and one based on a hybrid CNN and vision transformer

arXiv:2601.20043v1 Announce Type: new Abstract: Standard Bayesian Optimization (BO) assumes uniform smoothness across the search space an assumption violated in multi-regime problems such as molecular conformation search through distinct energy basins or drug discovery across heterogeneous molecular scaffolds. A single GP either oversmooths sharp transitions or hallucinates noise in smooth regions, yielding miscalibrated uncertainty. We propose RAMBO, a Dirichlet Process Mixture of Gaussian Processes that automatically discovers latent regimes during optimization, each modeled by an independent GP with locally-optimized hyperparameters. We derive collapsed Gibbs sampling that analytically marginalizes latent functions for efficient inference, and introduce adaptive concentration parameter scheduling for coarse-to-fine regime discovery. Our acquisition functions decompose uncertainty into intra-regime and inter-regime components. Experiments on synthetic benchmarks and real-world

arXiv:2601.19205v1 Announce Type: new Abstract: Designing enzymes with substrate-binding pockets is a critical challenge in protein engineering, as catalytic activity depends on the precise interaction between pockets and substrates. Currently, generative models dominate functional protein design but cannot model pocket-substrate interactions, which limits the generation of enzymes with precise catalytic environments. To address this issue, we propose EnzyPGM, a unified framework that jointly generates enzymes and substrate-binding pockets conditioned on functional priors and substrates, with a particular focus on learning accurate pocket-substrate interactions. At its core, EnzyPGM includes two main modules: a Residue-atom Bi-scale Attention (RBA) that jointly models intra-residue dependencies and fine-grained interactions between pocket residues and substrate atoms, and a Residue Function Fusion (RFF) that incorporates enzyme function priors into residue representations. Also, we

arXiv:2601.19890v1 Announce Type: new Abstract: Recent theoretical studies suggest that solenoidal turbulence can significantly enhance fusion reactivity, yet no standard diagnostic exists to directly measure these solenoidal flows in high-energy-density plasmas, nor to distinguish between solenoidal and compressional turbulence. We propose a method that directly diagnoses the energy and spatial structure of this rotational turbulence using the cross-polarization scattering of a probe laser. By coupling to the plasma vorticity, the scattering generates a cross-polarized signal proportional to the turbulent vorticity, effectively acting as a calorimeter for shear flows. We identify a diffractive scattering signature analogous to ``Debye-Scherrer ring'' that reveals the eddy size distribution. We show that this technique is applicable to National Ignition Facility (NIF) implosion conditions and other high-energy-density scenarios.

arXiv:2601.19401v1 Announce Type: new Abstract: Due to any toroidal current column, the magnetic field is found to be sensitive as well as insensitive to its cross-sectional area depending on location of subject point, as predicted by numerical approaches [S. Aich, J. Thakkar, and J. Ghosh, Plasma Fusion Res. 17, 2403055 (2022)], and hence the presence of an angle of invariance is found to be present for any toroidal geometry. Present study aims to validate those numerical observations using the measured magnetic field due to Aditya Upgrade tokamak plasma.

arXiv:2110.10647v2 Announce Type: replace Abstract: The study of magnetohydrodynamics (MHD) significantly boosts the understanding and development of solar physics, planetary dynamics and controlled nuclear fusion. Dynamical properties of the MHD system involve nonlinear interactions of waves with multiple travelling speeds (the fast and slow magnetosonic waves, the Alfv\'{e}n wave and the entropy wave). One intriguing topic is the shock phenomena accompanied by the magnetic field, which have been affirmed by astronomical observations. However, permitting the residence of all above multi-speed waves, mathematically, whether one can prove shock formation for three dimensional (3D) MHD is still open. The multiple-speed nature of the MHD system makes it fascinating and challenging. In this paper, we report our recent progress in answering the above question. For 3D ideal compressible MHD, we construct planar symmetric examples of shock formation allowing the presence of all

arXiv:2110.10647v2 Announce Type: replace-cross Abstract: The study of magnetohydrodynamics (MHD) significantly boosts the understanding and development of solar physics, planetary dynamics and controlled nuclear fusion. Dynamical properties of the MHD system involve nonlinear interactions of waves with multiple travelling speeds (the fast and slow magnetosonic waves, the Alfv\'{e}n wave and the entropy wave). One intriguing topic is the shock phenomena accompanied by the magnetic field, which have been affirmed by astronomical observations. However, permitting the residence of all above multi-speed waves, mathematically, whether one can prove shock formation for three dimensional (3D) MHD is still open. The multiple-speed nature of the MHD system makes it fascinating and challenging. In this paper, we report our recent progress in answering the above question. For 3D ideal compressible MHD, we construct planar symmetric examples of shock formation allowing the presence of all

arXiv:2601.18274v1 Announce Type: new Abstract: In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence modeling. However, existing Spiking Transformers still lack a principled mechanism for effective temporal fusion, limiting their ability to fully exploit spatiotemporal dependencies. Inspired by feedforward-feedback modulation in the human visual pathway, we propose TEFormer, the first Spiking Transformer framework that achieves bidirectional temporal fusion by decoupling temporal modeling across its core components. Specifically, TEFormer employs a lightweight and hyperparameter-free forward temporal fusion mechanism in the attention module, enabling fully parallel computation, while incorporating a backward gated recurrent structure in the MLP to aggregate temporal information in reverse order and reinforce temporal consistency. Extensive experiments across a

arXiv:2601.18263v1 Announce Type: new Abstract: Aerial images play a vital role in urban planning and environmental preservation, as they consist of various structures, representing different types of buildings, forests, mountains, and unoccupied lands. Due to its heterogeneous nature, developing robust models for scene classification remains a challenge. In this study, we conduct a literature review of various machine learning methods for aerial image classification. Our survey covers a range of approaches from handcrafted features (e.g., SIFT, LBP) to traditional CNNs (e.g., VGG, GoogLeNet), and advanced deep hybrid networks. In this connection, we have also designed Aerial-Y-Net, a spatial attention-enhanced CNN with multi-scale feature fusion mechanism, which acts as an attention-based model and helps us to better understand the complexities of aerial images. Evaluated on the AID dataset, our model achieves 91.72% accuracy, outperforming several baseline architectures.

arXiv:2601.17711v1 Announce Type: new Abstract: Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw waveforms at a fusion center (FC) from all devices and then design a multi-microphone model, causing high bandwidth and energy costs. In this work, we propose a \emph{Compress-and-Send Network (CaSNet)} for resource-constrained DMAs, where one microphone serves as the FC and reference. Each of other devices encodes the measured raw data into a feature matrix, which is then compressed by singular value decomposition (SVD) to produce a more compact representation. The received features at the FC are aligned via cross window query with respect to the reference, followed by neural decoding to yield spatially coherent enhanced speech. Experiments on multiple datasets show that the proposed CaSNet can save the

arXiv:2601.17468v1 Announce Type: new Abstract: Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to implicit fusion mechanisms and inadequate multi-scale coordination. We propose ReflexSplit, a dual-stream framework with three key innovations. (1) Cross-scale Gated Fusion (CrGF) adaptively aggregates semantic priors, texture details, and decoder context across hierarchical depths, stabilizing gradient flow and maintaining feature consistency. (2) Layer Fusion-Separation Blocks (LFSB) alternate between fusion for shared structure extraction and differential separation for layer-specific disentanglement. Inspired by Differential Transformer, we extend attention cancellation to dual-stream separation via cross-stream subtraction. (3) Curriculum training progressively strengthens differential separation

arXiv:2601.16225v1 Announce Type: cross Abstract: Empathetic speech dialogue requires not only understanding linguistic content but also perceiving rich paralinguistic information such as prosody, tone, and emotional intensity for affective understandings. Existing speech-to-speech large language models either rely on ASR transcription or use encoders to extract latent representations, often weakening affective information and contextual coherence in multi-turn dialogues. To address this, we propose \textbf{ES4R}, a framework for speech-based empathetic response generation. Our core innovation lies in explicitly modeling structured affective context before speech encoding, rather than relying on implicit learning by the encoder or explicit emotion supervision. Specifically, we introduce a dual-level attention mechanism to capture turn-level affective states and dialogue-level affective dynamics. The resulting affective representations are then integrated with textual semantics through

We live near a fusion reactor in space that provides all our heat and light. That reactor is also responsible for the creation of various elements heavier than hydrogen, and that's true of all stars. So, how do we know that stars are element generators?

arXiv:2601.15629v1 Announce Type: new Abstract: Ultrafast laser welding provides a promising approach for high precision integration of transparent and metallic materials. However, its practical application remains constrained by the precise regulation of the interfacial gap. This study investigates the interfacial response and bonding mechanism of sapphire and Fe-36Ni alloy joints under controlled non-optical contact conditions using burst mode ultrafast laser irradiation. A polymer interlayer was introduced between naturally stacked samples to establish a variable interfacial gap, allowing systematic evaluation of gap-dependent morphology, melting behavior, and elemental transport. By redistributing the pulse energy into sequential sub-pulses, the burst mode reconstructs the temporal energy-deposition process, yielding enhanced plasma-material coupling and stable thermal accumulation. Compared with single pulse irradiation, burst mode sustains continuous bonding across gaps

arXiv:2601.15590v1 Announce Type: new Abstract: The density limit is a mysterious barrier to magnetic confinement nuclear fusion, and is still an unresolved issue. In this paper, we will present the experimental results of the density limit and core-localized kinetic MHD instabilities on HL-2A. Firstly, the high density shots with $ne/ne_G>1$ have been achieved by the conventional gas-puff fuelling method in Ohmic heating plasmas, and the corresponding duration time is close to $t\sim500$ ms ($\sim$ $30\tau_E$), where $\tau_E$ is the global energy confinement time. Secondly, it is found for the first time that there are kinetic MHD instabilities in the core plasmas while $ne/ne_G\sim1$. The analysis suggests that the core-localized MHD activities belong to Alfv{\'e}nic ion temperature gradient (AITG) modes or kinetic ballooning modes (KBM), and firstly it is found on experiment that they trigger the minor or major disruption of bulk plasmas while the density profile is peaked. These

arXiv:2601.15567v1 Announce Type: new Abstract: To achieve a high energy gain, the fusion reactor plasma must reach a very high density. However, the tokamak plasmas ofen undergo disruption when the density exceeds the Greenwald density. The density limit disruption in tokamak plasmas is a mysterious barrier to magnetic confinement nuclear fusion, and hitherto, is still an unresolved issue. Over the past several years, the high density experiments with Greenwald density ratio $n_e/n_{eG}\sim1$ has been carried out using the conventional gas-puff fuelling method in HL-2A NBI and Ohmically heated plasmas. It is found for the first time that there are multiple-branch MHD instabilities in the core plasmas while $n_e/n_{eG}>0.85$. The simulation analysis suggests that the core-localized magnetohydrodynamics (MHD) activities belong to Alfv${\'e}$nic ion temperature gradient (AITG) modes, and on experiment firstly, it is discovered that they trigger the minor or major disruption of bulk

arXiv:2601.15391v1 Announce Type: new Abstract: Turbulent transport remains one of the principal obstacles to achieving efficient magnetic confinement in fusion devices. Two of the dominant drivers of the turbulence are microscale instabilities fuelled by electron- and ion-temperature gradients (ETG and ITG), whose nonlinear saturation determines the cross-field transport of particles and energy. Despite decades of study, predictive modelling of this turbulence has been limited either to expensive gyrokinetic simulations or to reduced models calibrated by fitting to numerical or experimental data, restricting their utility for reactor design. Here we present a simple asymptotic scaling theory that unifies ETG- and ITG-driven turbulence within a common framework. By balancing the fundamental time scales of linear growth, nonlinear decorrelation, and parallel propagation, the theory isolates the dependence of the heat flux on equilibrium parameters to two key quantities: the parallel

arXiv:2509.16994v2 Announce Type: replace-cross Abstract: We introduce a novel deep learning-based audio-visual quality (AVQ) prediction model that leverages internal features from state-of-the-art unimodal predictors. Unlike prior approaches that rely on simple fusion strategies, our model employs a hybrid representation that combines learned Generative Machine Listener (GML) audio features with hand-crafted Video Multimethod Assessment Fusion (VMAF) video features. Attention mechanisms capture cross-modal interactions and intra-modal relationships, yielding context-aware quality representations. A modality relevance estimator quantifies each modality's contribution per content, potentially enabling adaptive bitrate allocation. Experiments demonstrate improved AVQ prediction accuracy and robustness across diverse content types.

arXiv:2601.15734v1 Announce Type: new Abstract: The successful adaptation of foundation models to multi-modal medical imaging is a critical yet unresolved challenge. Existing models often struggle to effectively fuse information from multiple sources and adapt to the heterogeneous nature of pathological tissues. To address this, we introduce a novel framework for adapting foundation models to multi-modal medical imaging, featuring two key technical innovations: sub-region-aware modality attention and adaptive prompt engineering. The attention mechanism enables the model to learn the optimal combination of modalities for each tumor sub-region, while the adaptive prompting strategy leverages the inherent capabilities of foundation models to refine segmentation accuracy. We validate our framework on the BraTS 2020 brain tumor segmentation dataset, demonstrating that our approach significantly outperforms baseline methods, particularly in the challenging necrotic core sub-region. Our work

arXiv:2601.15416v1 Announce Type: new Abstract: Sparse-view Cone-Beam Computed Tomography reconstruction from limited X-ray projections remains a challenging problem in medical imaging due to the inherent undersampling of fine-grained anatomical details, which correspond to high-frequency components. Conventional CNN-based methods often struggle to recover these fine structures, as they are typically biased toward learning low-frequency information. To address this challenge, this paper presents DuFal (Dual-Frequency-Aware Learning), a novel framework that integrates frequency-domain and spatial-domain processing via a dual-path architecture. The core innovation lies in our High-Local Factorized Fourier Neural Operator, which comprises two complementary branches: a Global High-Frequency Enhanced Fourier Neural Operator that captures global frequency patterns and a Local High-Frequency Enhanced Fourier Neural Operator that processes spatially partitioned patches to preserve spatial

arXiv:2601.14886v1 Announce Type: new Abstract: In piecewise omnigenous magnetic fields, charged particles remain perfectly confined in the abscence of collisions and turbulence. This concept extends the traditional notion of omnigenity, the theoretical principle upon which most of existing magnetic fusion reactor designs, including tokamaks, are based. While piecewise omnigenity broadens the range of potentially viable stellarator reactor candidates, it is achieved by relaxing the requirement of continuity in the magnetic field strength, which could appear to pose significant challenges for the design of magnetohydrodynamic equilibria. In this work, a stellarator magnetic configuration is presented that satisfies the ideal magnetohydrodynamic equilibrium equation and that achieves unprecedented levels of piecewise omnigenity. As a result, it exhibits favorable transport characteristics, including reduced bulk radial (neoclassical and turbulent transport), bootstrap current and fast

arXiv:2601.14834v1 Announce Type: new Abstract: It is found by using the gyrokinetic theory that significant radial electric fields, or zonal flows, can be generated by the radial redistribution of energetic ion pressure in a tokamak fusion device. Trapped energetic ions are more effective to generate the radial electric field than the isotropic energetic ions. This suggests that the energetic $\alpha$ particles produced by DT fusion may induce significant radial electric field and thus help to improve the core plasma confinement in a fusion reactor.

arXiv:2601.14749v1 Announce Type: new Abstract: We report the discovery of the trigger for detachment bifurcation phenomenon in tokamak divertors, revealed through steady-state and time-dependent UEDGE simulations: The observed electron temperature cliff at the outer target in DIII-D H-mode plasmas with ion $B\times \nabla B$ drift driven into the active divertor results from a bifurcation-induced $T_e$ drop above the X-point accompanied by reversal of the $E\times B$ flow pattern in the private flux region. Time-dependent simulations reveal a two-phase transition mechanism: the high-field-side radiation front first extends across the last closed flux surface and stabilizes above the X-point, causing local $T_e$ to drop from $\sim 70\,\mathrm{eV}$ to $\sim 10\,\mathrm{eV}$ and inducing $E\times B$ flow reversal in a thin layer below the X-point, which lasts $

arXiv:2601.14471v1 Announce Type: new Abstract: The high-power helicon wave system in the DIII-D tokamak introduces new plasma--material interaction (PMI) challenges due to rectified RF sheath potentials forming near antenna structures and surrounding tiles. Using the STRIPE modeling framework-which integrates SOLPS-ITER, COMSOL, RustBCA, and GITR/GITRm-we simulate carbon erosion, re-deposition, and global impurity transport in two H-mode discharges with varying antenna--plasma gaps and RF powers. COMSOL predicts rectified sheath potentials of 1-5 kV, localized near the bottom of the antenna where magnetic field lines intersect at grazing angles. Erosion is dominated by carbon self-sputtering, with RF-accelerated D+ ions contributing up to 1 % of the total erosion flux. GITRm simulations show that in the small-gap case, only ~ 13 % of eroded carbon is re-deposited locally, with 58 % transported into the core. In contrast, the large-gap case exhibits lower total erosion, along with

arXiv:2601.14301v1 Announce Type: new Abstract: The field of plasma physics heavily relies on simulations to model various phenomena, such as instabilities, turbulence, and nonlinear behaviors that would otherwise be difficult to study from a purely theoretical approach. Simulations are fundamental in accurately setting up experiments, which can be extremely costly and complex. As high-fidelity tools, gyrokinetic simulations play a crucial role in discovering new physics, interpreting experimental results, and improving the design of next-generation devices. However, their high computational costs necessitate the use of acceleration platforms to reduce execution time. This work revolves around the TRIangular MEsh based Gyrokinetic (TRIMEG) code, which performs high-accuracy particle-in-cell plasma simulations in tokamak geometries, leveraging a novel finite element approach. The rise of graphical processing units (GPUs) constitutes an occasion to satisfy such computational needs, by

arXiv:2601.14677v1 Announce Type: new Abstract: Object detection in video and image surveillance is a well-established yet rapidly evolving task, strongly influenced by recent deep learning advancements. This review summarises modern techniques by examining architectural innovations, generative model integration, and the use of temporal information to enhance robustness and accuracy. Unlike earlier surveys, it classifies methods based on core architectures, data processing strategies, and surveillance specific challenges such as dynamic environments, occlusions, lighting variations, and real-time requirements. The primary goal is to evaluate the current effectiveness of semantic object detection, while secondary aims include analysing deep learning models and their practical applications. The review covers CNN-based detectors, GAN-assisted approaches, and temporal fusion methods, highlighting how generative models support tasks such as reconstructing missing frames, reducing

A research group has achieved a new plasma confinement regime using small 3D magnetic perturbations that simultaneously suppress edge instabilities and enhance core plasma confinement in the Experimental Advanced Superconducting Tokamak (EAST). The research results are published in PRX Energy.

arXiv:2601.13573v1 Announce Type: cross Abstract: Accurate and efficient rumor detection is critical for information governance, particularly in the context of the rapid spread of misinformation on social networks. Traditional rumor detection relied primarily on manual analysis. With the continuous advancement of technology, machine learning and deep learning approaches for rumor identification have gradually emerged and gained prominence. However, previous approaches often struggle to simultaneously capture both the sequential and the global structural relationships among topological nodes within a social network. To tackle this issue, we introduce a hybrid model for detecting rumors that integrates a Graph Convolutional Network (GCN) with a Transformer architecture, aiming to leverage the complementary strengths of structural and semantic feature extraction. Positional encoding helps preserve the sequential order of these nodes within the propagation structure. The use of Multi-head

arXiv:2601.14028v1 Announce Type: new Abstract: The imaging platform developed at the High Energy Density - Helmholtz International Beamline for Extreme Fields (HED-HiBEF) instrument at the European XFEL and its applications to high energy density and fusion related research are presented. The platform combines the XFEL beam with the high-intensity short-pulse laser ReLaX and the high-energy nanosecond-pulse laser DiPOLE-100X. The spatial resolution is better than 500 nm and the temporal resolution of the order of 50 fs. We show examples of blast waves and converging cylindrical shocks in aluminium, resonant absorption measurements of specific charged states in copper with ReLaX and planar shocks in polystyrene material generated by DiPOLE-100X. We also discuss the possibilities introduced by combining this imaging platform with a kJ-class laser.

arXiv:2601.13413v1 Announce Type: new Abstract: Nitrogen vacancy centres (NVC) in diamond have been widely used for near-dc magnetometry. The intrinsic properties of diamonds make them potential candidates for tokamak fusion power diagnostics, where radiation-hard magnetometers will be essential for efficient control. An NVC magnetometer placed in a tokamak will need to operate within a $\geq$ 1 T magnetic field. In this work, we demonstrate fibre-coupled ensemble NVC optically detected magnetic resonance (ODMR) and magnetometry measurements at magnetic fields up to 1.2 T. Sensitivities of approximately 240 to 600 nT/$\sqrt{\textrm{Hz}}$ and 110 nT/$\sqrt{\textrm{Hz}}$ are achieved in a (10-150) Hz frequency range, for non-degenerate and near-$\langle$111$\rangle$ field alignments respectively.

arXiv:2601.12469v1 Announce Type: new Abstract: Non-axisymmetric magnetic field coils have been designed to provide efficient error field correction and suppress edge localized modes in SPARC - a compact high-field tokamak that is presently under construction at Commonwealth Fusion Systems. These designs utilize the Generalized Perturbed Equilibrium Code's (GPEC's) representation of the multi-modal, non-axisymmetric plasma response to optimize the geometric coupling between 3D coil arrays and the desired core or edge plasma response. Error field correction coils are designed to couple to the plasma-amplified kink that dominates the drive of core resonances. The maximum allowable error field is projected to SPARC using an empirical scaling that is consistent with linear and nonlinear MHD modeling expectations. Asymmetric construction and assembly tolerances are then balanced against the corresponding kA-turns needed for correction to levels below the allowable limit. These

arXiv:2601.12378v1 Announce Type: new Abstract: This work proposes for the first time a novel optimization method for numerical algorithms, which takes advantages of machine learning frameworks PyTorch and TensorRT, leveraging their modularity, low development threshold, and automatic tuning characteristics to achieve a real-time plasmas reconstruction algorithm called PTEFIT as an application in tokamak-based controlled fusion that combines performance, flexibility, and usability. The algorithm has been deployed and routinely operated on the EXL-50U spherical tokamak, with an average inference time of only 0.268ms per time slice at $129\times 129$ resolution, and has successfully driven feedback control of the maximum radial position of plasmas and isoflux control. We believe that its design philosophy has sufficient potential to accelerate development and optimization in GPU parallel computing, and is expected to be extended to other numerical algorithms.

arXiv:2601.14154v1 Announce Type: new Abstract: Postoperative complications remain a critical concern in clinical practice, adversely affecting patient outcomes and contributing to rising healthcare costs. We present MIRACLE, a deep learning architecture for prediction of risk of postoperative complications in lung cancer surgery by integrating preoperative clinical and radiological data. MIRACLE employs a hyperspherical embedding space fusion of heterogeneous inputs, enabling the extraction of robust, discriminative features from both structured clinical records and high-dimensional radiological images. To enhance transparency of prediction and clinical utility, we incorporate an interventional deep learning module in MIRACLE, that not only refines predictions but also provides interpretable and actionable insights, allowing domain experts to interactively adjust recommendations based on clinical expertise. We validate our approach on POC-L, a real-world dataset comprising 3,094 lung

arXiv:2601.13732v1 Announce Type: new Abstract: The fact that robots are getting deployed more often in dynamic environments, together with the increasing complexity of their software systems, raises the need for self-adaptive approaches. In these environments robotic software systems increasingly operate amid (1) uncertainties, where symptoms are easy to observe but root causes are ambiguous, or (2) multiple uncertainties appear concurrently. We present SUNSET, a ROS2-based exemplar that enables rigorous, repeatable evaluation of architecture-based self-adaptation in such conditions. It implements a sensor fusion semantic-segmentation pipeline driven by a trained Machine Learning (ML) model whose input preprocessing can be perturbed to induce realistic performance degradations. The exemplar exposes five observable symptoms, where each can be caused by different root causes and supports concurrent uncertainties spanning self-healing and self-optimisation. SUNSET includes the

arXiv:2601.13573v1 Announce Type: new Abstract: Accurate and efficient rumor detection is critical for information governance, particularly in the context of the rapid spread of misinformation on social networks. Traditional rumor detection relied primarily on manual analysis. With the continuous advancement of technology, machine learning and deep learning approaches for rumor identification have gradually emerged and gained prominence. However, previous approaches often struggle to simultaneously capture both the sequential and the global structural relationships among topological nodes within a social network. To tackle this issue, we introduce a hybrid model for detecting rumors that integrates a Graph Convolutional Network (GCN) with a Transformer architecture, aiming to leverage the complementary strengths of structural and semantic feature extraction. Positional encoding helps preserve the sequential order of these nodes within the propagation structure. The use of Multi-head

arXiv:2601.13423v1 Announce Type: new Abstract: Post-quantum cryptography (PQC) introduces significant computational and communication overhead, which poses challenges for resource-constrained computer systems, Internet of Things (IoT), and Industrial IoT (IIoT) devices. This paper presents an experimental evaluation of the Quantum Encryption Resilience Score (QERS) applied to MQTT, HTTP, and HTTPS communication protocols operating under PQC. Using an ESP32-C6 client and an ARM-based Raspberry Pi CM4 server, latency, CPU utilization, RSSI, energy consumption, key size, and TLS handshake overhead are measured under realistic operating conditions. QERS integrates these heterogeneous metrics into normalized Basic, Tuned, and Fusion scores, enabling systematic comparison of protocol efficiency and security resilience. Experimental results show that MQTT provides the highest efficiency under PQC constraints, while HTTPS achieves the highest security-weighted resilience at the cost of

arXiv:2601.13096v1 Announce Type: new Abstract: Maritime port inspection plays a critical role in ensuring safety, regulatory compliance, and operational efficiency in complex maritime environments. However, existing inspection methods often rely on manual operations and conventional computer vision techniques that lack scalability and contextual understanding. This study introduces a novel integrated engineering framework that utilizes the synergy between Large Language Models (LLMs) and Vision Language Models (VLMs) to enable autonomous maritime port inspection using cooperative aerial and surface robotic platforms. The proposed framework replaces traditional state-machine mission planners with LLM-driven symbolic planning and improved perception pipelines through VLM-based semantic inspection, enabling context-aware and adaptive monitoring. The LLM module translates natural language mission instructions into executable symbolic plans with dependency graphs that encode operational

arXiv:2601.12684v1 Announce Type: new Abstract: Credit default poses significant challenges to financial institutions and consumers, resulting in substantial financial losses and diminished trust. As such, credit default risk management has been a critical topic in the financial industry. In this paper, we present Combinatorial Fusion Analysis (CFA), a model fusion framework, that combines multiple machine learning algorithms to detect and predict credit card approval with high accuracy. We present the design methodology and implementation using five pre-trained models. The CFA results show an accuracy of 89.13% which is better than conventional machine learning and ensemble methods.

arXiv:2601.12249v1 Announce Type: new Abstract: Breast cancer is one of the most common cancers among women worldwide, and its accurate and timely diagnosis plays a critical role in improving treatment outcomes. This thesis presents an innovative framework for detecting malignant masses in mammographic images by integrating the Pyramid Adaptive Atrous Convolution (PAAC) and Transformer architectures. The proposed approach utilizes Multi-Scale Feature Fusion to enhance the extraction of features from benign and malignant tissues and combines Dice Loss and Focal Loss functions to improve the model's learning process, effectively reducing errors in binary breast cancer classification and achieving high accuracy and efficiency. In this study, a comprehensive dataset of breast cancer images from INbreast, MIAS, and DDSM was preprocessed through data augmentation and contrast enhancement and resized to 227x227 pixels for model training. Leveraging the Transformer's ability to manage

Young stars need time to grow into their final masses before they begin fusing lighter elements into heavier elements as main-sequence stars. They can spend hundreds of thousands of years as protostars, when they're still accreting mass from the molecular clouds they form in. But even though they haven't begun fusion, they still inject energy into their surroundings.

arXiv:2401.04600v3 Announce Type: replace Abstract: We developed kinetic models based on general fishbone-like dispersion relations. Firstly, a general model for arbitrary magnetic configuration and ion orbit width is presented. Then, by disregarding ion orbit width and approximating the magnetic geometry as circular, we introduce a simplified model that fully incorporates circulating/trapped ion effects. Finally, by considering the limit of ions being well-circulating or deeply trapped, the results directly revert to those observed in earlier theoretical studies.

arXiv:2601.11014v1 Announce Type: new Abstract: Circular cross-section plasma is the most basic form of tokamak plasma and the fundamental configuration for magnetic confinement fusion experiments. Based on the HL-2A limiter discharge experiments, the magnetohydrodynamic (MHD) equilibrium and MHD instability of circular cross-section tokamak plasmas are investigated in this work. The results show that when q_0=0.95, the internal kink mode of m/n=1/1 is always unstable. The increase in plasma \b{eta} (the ratio of thermal pressure to magnetic pressure) can lead to the appearance of external kink modes. The combination of axial safety factor q_0 and edge safety factor q_a determines the equilibrium configuration of the plasma and also affects the MHD stability of the equilibrium, but its growth rate is also related to the size of \b{eta}. Under the condition of q_a>2 and q_0 slightly greater than 1, the internal kink mode and surface kink mode can be easily stabilized. However the

arXiv:2601.10509v1 Announce Type: new Abstract: This report is a follow up to my paper "A simple model of current ramp-up and ramp-down in tokamaks" [Nucl. Fusion 66, 016012 (2026)] in the light of comments on the paper recently made by Dr. A.H. Boozer (arXiv:2601.05977).

arXiv:2601.10295v1 Announce Type: new Abstract: High-temperature technical superconductors are potential candidates for compact and high-field tokamak magnets. The demand for higher fusion power can be met with an on-axis high magnetic field due to toroidal magnets. An R&D activity has been initiated at the Institute for Plasma Research, India, to develop a compact D-shaped superconducting magnet utilizing REBCO high-temperature superconducting tapes. Under this initiative, a toroidal configuration with a major radius of 0.42 m, consisting of eight D-shaped, four poloidal field, and a central solenoid high-temperature superconducting magnets producing an on-axis toroidal magnetic field of 0.23 T has been conceptualized. The fabrication feasibility of a D-shaped coil for this toroidal configuration also envisaged using stacked high-temperature superconducting cable. In this paper, we report the design of a compact D-shaped coil, the fabrication of a long length HTS cable, a winding

arXiv:2601.09996v1 Announce Type: new Abstract: One of the most public episodes of gatekeeping in modern science was the case of so-called 'cold fusion'. At a news conference in 1989 the electrochemists Martin Fleischmann and Stanley Pons announced that they had found evidence of nuclear fusion in palladium electrodes loaded with deuterium. There was worldwide interest. Many groups sought to reproduce the results, most unsuccessfully. Within months, the prevailing view became strongly negative. The claims of Fleischmann and Pons came to be regarded as disreputable, as well as false. As the Caltech physicist David Goldstein put it, cold fusion became 'a pariah field, cast out by the scientific establishment' (Goldstein 1994). The case would already be interesting for students of gatekeeping if the story had ended at that point. Even more interestingly, however, the field survived and persisted. It has been enjoying a modest renaissance, with recent government funding both in the US and

arXiv:2601.09906v1 Announce Type: new Abstract: In this work we present a study on the viability and practicality of installing a Doppler reflectometer (DR) system in the JT-60SA advanced tokamak. First, we discuss its scientific scope in the context of the JT-60SA research plan. We identify a number of fields in which a DR would be very relevant for the accomplishment of said plan and outline a scientific program for the diagnostic. Then, starting from a number of design hypothesis, we use a ray tracing code to carry out a feasibility study for a number of relevant scenarios and identify a geometric solution for the installation of a DR such that both core and edge can be probed in the prescribed wave number range, thus achieving the proposed scientific objectives. Finally, we perform a preliminary discussion on the different possibilities for a conceptual design (including a minimum viable system and a baseline system) and their requirements in terms of components and space. We

arXiv:2601.09952v1 Announce Type: new Abstract: Reliable traversable area segmentation in unstructured environments is critical for planning and decision-making in autonomous driving. However, existing data-driven approaches often suffer from degraded segmentation performance in out-of-distribution (OOD) scenarios, consequently impairing downstream driving tasks. To address this issue, we propose OT-Drive, an Optimal Transport--driven multi-modal fusion framework. The proposed method formulates RGB and surface normal fusion as a distribution transport problem. Specifically, we design a novel Scene Anchor Generator (SAG) to decompose scene information into the joint distribution of weather, time-of-day, and road type, thereby constructing semantic anchors that can generalize to unseen scenarios. Subsequently, we design an innovative Optimal Transport-based multi-modal fusion module (OT Fusion) to transport RGB and surface normal features onto the manifold defined by the semantic

arXiv:2601.09458v1 Announce Type: cross Abstract: Nuclear fusion promises a nearly limitless energy source, but achieving breakeven-where fusion output exceeds input-requires extreme plasma conditions and complex confinement systems. Here we propose an alternative approach based on beam-target interactions, introducing a simple energy-based criterion that compares fusion energy generation with energy loss. By creating electron-free targets, stopping power is drastically reduced, enabling conditions where fusion energy surpasses beam energy deposition under practical scenarios. This approach offers a viable alternative pathway to fusion energy without high-temperature plasma confinement and warrants further experimental investigation.

arXiv:2601.09115v1 Announce Type: cross Abstract: We present SASHMAG (Saturated Absorption Spectroscopy High-field MAGnetometer), an atomic sensor designed for precision magnetic-field measurements in the intermediate-to-high field regime ($>0.2\,\text{T}$) using Rubidium-87 ($^{87}Rb$). The sensor operates in the hyperfine Paschen-Back regime, where the hyperfine and Zeeman interactions decouple, and utilizes counter-propagating pump-probe configuration in Faraday geometry to resolve isolated, Doppler-free Zeeman transitions. To interpret the resulting spectra in this strongly field-dependent regime, we developed a comprehensive multilevel optical Bloch-equation model solved explicitly in the uncoupled $\ket{m_I, m_J}$ basis, capturing state mixing and nonlinear saturation dynamics. This model reproduces measured spectra at sub-Doppler resolution and is consistent with analytical expectations for power broadening and thermal Doppler scaling. Magnetic field estimation is performed

arXiv:2601.09246v1 Announce Type: new Abstract: Standardized Student Evaluation of Teaching often suffer from low reliability, restricted response options, and response distortion. Existing machine learning methods that mine open-ended comments usually reduce feedback to binary sentiment, which overlooks concrete concerns such as content clarity, feedback timeliness, and instructor demeanor, and provides limited guidance for instructional improvement.We propose TeachPro, a multi-label learning framework that systematically assesses five key teaching dimensions: professional expertise, instructional behavior, pedagogical efficacy, classroom experience, and other performance metrics. We first propose a Dimension-Anchored Evidence Encoder, which integrates three core components: (i) a pre-trained text encoder that transforms qualitative feedback annotations into contextualized embeddings; (ii) a prompt module that represents five teaching dimensions as learnable semantic anchors; and

arXiv:2601.08400v1 Announce Type: new Abstract: In this work, we investigate the landscape of quasi-isodynamic stellarators using the near-axis expansion of the magnetic field. Building on recent theoretical developments, we construct a database of more than 800,000 stable, approximately quasi-isodynamic vacuum magnetic configurations. These configurations span a range of field period numbers and other geometric control parameters, including the magnetic axis shape and plasma elongation. To evaluate each configuration, we use a broad set of measures, including effective ripple, sensitivity of the Shafranov shift to changes in plasma beta, the prevalence of maximum-J trapped particles, and the Rosenbluth-Hinton residual, among others. This enables an exhaustive, thorough and quantitative characterization of the database. Statistical analysis and modern machine learning techniques are then employed to find correlations, and identify key descriptors and heuristics to help understand

arXiv:2601.07969v1 Announce Type: cross Abstract: In this paper, we propose a standardized framework for automatic tuberculosis (TB) detection from cough audio and routinely collected clinical data using machine learning. While TB screening from audio has attracted growing interest, progress is difficult to measure because existing studies vary substantially in datasets, cohort definitions, feature representations, model families, validation protocols, and reported metrics. Consequently, reported gains are often not directly comparable, and it remains unclear whether improvements stem from modeling advances or from differences in data and evaluation. We address this gap by establishing a strong, well-documented baseline for TB prediction using cough recordings and accompanying clinical metadata from a recently compiled dataset from several countries. Our pipeline is reproducible end-to-end, covering feature extraction, multimodal fusion, cougher-independent evaluation, and uncertainty

arXiv:2601.07966v1 Announce Type: new Abstract: The acceleration of materials discovery requires digital platforms that go beyond data repositories to embed learning, optimization, and decision-making directly into research workflows. We introduce DataScribe, an AI-native, cloud-based materials discovery platform that unifies heterogeneous experimental and computational data through ontology-backed ingestion and machine-actionable knowledge graphs. The platform integrates FAIR-compliant metadata capture, schema and unit harmonization, uncertainty-aware surrogate modeling, and native multi-objective multi-fidelity Bayesian optimization, enabling closed-loop propose-measure-learn workflows across experimental and computational pipelines. DataScribe functions as an application-layer intelligence stack, coupling data governance, optimization, and explainability rather than treating them as downstream add-ons. We validate the platform through case studies in electrochemical materials and

arXiv:2601.07652v1 Announce Type: new Abstract: In future nuclear fusion reactors, even a small fraction of fusion-born energetic particles (EP) about 100 times hotter than the thermal bulk species, contributes substantially to the kinetic pressure and therefore affect the MHD equilibrium, mainly via the Shafranov shift. In this work, we perform first-principles numerical simulations using the gyrokinetic, electromagnetic, global code ORB5 to study the effect of a self-consistent finite $\beta$ equilibrium on the arising Alfv\'en Eigenmodes (destabilized by EPs), Ion Temperature Gradient (ITG), and Kinetic Ballooning Modes (KBM) microturbulence (destabilized by thermal species). Linearly, we explore the complex interplay between EP fraction, bulk gradients and a self-consistent Shafranov shift on the plasma stability. We choose single toroidal mode numbers to represent the system's instabilities and study the characteristic nonlinear evolutions of TAEs, KBMs and ITGs separately and

arXiv:2601.07205v1 Announce Type: new Abstract: The plasma discharges in ADITYA Upgrade Tokamak are produced by means of transformer action, in which Ohmically created plasma is driven by means of a secondary loop voltage. Due to reduction of plasma resistivity after a certain level of plasma temperature, Ohmic heating becomes poor and further achievement of temperature needs other heating techniques. ADITYA-U tokamak is facilitated with a 42 GHz-500 kW Electron Cyclotron Resonant Heating (ECRH) system. Also, there is a Lower Hybrid Current Drive (LHCD) system installed and operated at 3.7 GHz for driving non-inductive plasma current followed by the Ohmic current drive. Though an eventual impact in the rise of plasma temperature and plasma current due to the application of ECRH and LHCD respectively are very obvious, their energy coupling with the plasma results in several interesting outcomes in a number of experimentally measured plasma parameters. The present work addresses such

arXiv:2601.07250v1 Announce Type: new Abstract: Accurate energy time-series forecasting is crucial for ensuring grid stability and promoting the integration of renewable energy, yet it faces significant challenges from complex temporal dependencies and the heterogeneity of multi-source data. To address these issues, we propose DDT, a novel and robust deep learning framework for high-precision time-series forecasting. At its core, DDT introduces two key innovations. First, we design a dual-masking mechanism that synergistically combines a strict causal mask with a data-driven dynamic mask. This novel design ensures theoretical causal consistency while adaptively focusing on the most salient historical information, overcoming the rigidity of traditional masking techniques. Second, our architecture features a dual-expert system that decouples the modeling of temporal dynamics and cross-variable correlations into parallel, specialized pathways, which are then intelligently integrated

arXiv:2601.05923v1 Announce Type: cross Abstract: Functional near-infrared spectroscopy (fNIRS) and diffuse optical tomography (DOT) are rapidly evolving toward wearable, multimodal, and data-driven, AI-supported neuroimaging in the everyday world. However, current analytical tools are fragmented across platforms, limiting reproducibility, interoperability, and integration with modern machine learning (ML) workflows. Cedalion is a Python-based open-source framework designed to unify advanced model-based and data-driven analysis of multimodal fNIRS and DOT data within a reproducible, extensible, and community-driven environment. Cedalion integrates forward modelling, photogrammetric optode co-registration, signal processing, GLM Analysis, DOT image reconstruction, and ML-based data-driven methods within a single standardized architecture based on the Python ecosystem. It adheres to SNIRF and BIDS standards, supports cloud-executable Jupyter notebooks, and provides containerized

arXiv:2601.05977v1 Announce Type: new Abstract: The article Nuclear Fusion \textbf{66}, 016012 (2026) by Richard Fitzpatrick is based on fundamental errors in the physics of the poloidal magnetic flux in tokamaks. His paper was inspired by an article that I posted on arXiv in various versions [arXiv:2507.05456]. The September 9, 2025 version was submitted to the Physics of Plasmas, which flatly rejected the article. Before I can resubmit, the Physics of Plasmas stated that the issues with the Fitzpatrick article must be explained. Not only did Fitzpatrick make numerous fundamental errors in science, he totally misrepresented my views as clearly stated in my article and even more explicitly in email exchanges, called ``private communication" in his paper. Enquiries were made to the journal Nuclear Fusion staring on November 24, 2025 of the consistency of Fitzpatrick's article with the scientific and ethical standards of the journal. On January 5, 2026, Nuclear Fusion said they had "no

arXiv:2601.05886v1 Announce Type: new Abstract: The interaction between energetic particles (EPs) and ion temperature gradient (ITG) modes is studied using the global particle in cell ORB5 code. In this work, we extend previous studies to a broader range of EP temperatures, including the burning plasma regime and to wider variety of EP distribution functions. Two main stabilization mechanisms are found to be effective in ITG stabilization confirming previous studies: direct dispersion relation modification (DDRM) effective only at intermediate EP temperatures and dilution effect (DE) which is independent of EP temperature and becomes dominant in burning plasma regime ($T_f > 50T_i$). The study is further extended to slowing-down EP distributions which in contrast exhibit no DDRM-related stabilization. The findings are further validated in an ITER pre-fusion operation scenario and additionally compared with electromagnetic effects. In this scenario EP stabilization is found to be

arXiv:2601.05331v1 Announce Type: new Abstract: Why do we use nano-antennas for fusion? In three sentences: The present laser induced fusion plans use extreme mechanical shock compression to get one hotspot and then ignition. Still fusion burning spreads slower than expansion, and mechanical instabilities may also develop. With nano-antennas in radiation dominated systems, simultaneous ignition can be achieved in the whole target volume and there is no time left for mechanical instabilities. Ignition is achieved with protons accelerated in the direction of the nanoantennas that are orthogonal to the direction of laser irradiation. Present laser fusion methods are based on extreme and slow mechanical compression with an ablator surface on the fuel target pellet to increase compression and eliminate penetration of laser electromagnetic energy into the target. This arises from a mistaken assumption, [1] that the detonation normal 4-vector should have vanishing time-like component, and

arXiv:2601.05285v1 Announce Type: new Abstract: The $^{12}$C+$^{12}$C fusion reaction plays a crucial role in stellar evolution, including the occurrence of supernova explosions, and in the synthesis of the chemical elements. However, our understanding of its cross section remains severely deficient, particularly below $E_\textrm{cm}=2.5$\,MeV, the energy range of interest for astrophysics. To address these unresolved issues, the LUNA collaboration will conduct a dedicated study of the $^{12}$C+$^{12}$C reaction at the Bellotti Ion Beam Facility (Bellotti IBF) located deep underground within the Gran Sasso National Laboratory (LNGS) in Italy. Based on the combination of passive and active shields, this campaign aims to achieve unprecedented sensitivity in measuring the cross sections of the two key reaction channels, $^{12}$C($^{12}$C,$\alpha$)$^{20}$Ne and $^{12}$C($^{12}$C,$p$)$^{23}$Na in the low-energy regime via $\gamma$-ray detection. Here, we report on a sensitivity study for

arXiv:2601.05923v1 Announce Type: cross Abstract: Functional near-infrared spectroscopy (fNIRS) and diffuse optical tomography (DOT) are rapidly evolving toward wearable, multimodal, and data-driven, AI-supported neuroimaging in the everyday world. However, current analytical tools are fragmented across platforms, limiting reproducibility, interoperability, and integration with modern machine learning (ML) workflows. Cedalion is a Python-based open-source framework designed to unify advanced model-based and data-driven analysis of multimodal fNIRS and DOT data within a reproducible, extensible, and community-driven environment. Cedalion integrates forward modelling, photogrammetric optode co-registration, signal processing, GLM Analysis, DOT image reconstruction, and ML-based data-driven methods within a single standardized architecture based on the Python ecosystem. It adheres to SNIRF and BIDS standards, supports cloud-executable Jupyter notebooks, and provides containerized

arXiv:2601.06022v1 Announce Type: new Abstract: Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without retraining. However, existing ensemble approaches suffer from fundamental limitations. Most rely on fixed fusion granularity, which lacks the flexibility required for mid-generation adaptation and fails to adapt to different generation characteristics across tasks. To address these challenges, we propose AdaFuse, an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation. Rather than committing to a fixed granularity, AdaFuse adjusts fusion behavior on the fly based on the decoding context, with words serving as basic building blocks for alignment. To be specific, we introduce an uncertainty-based criterion to decide whether to apply

arXiv:2601.05446v1 Announce Type: new Abstract: Infrared small target detection (ISTD) remains a long-standing challenge due to weak signal contrast, limited spatial extent, and cluttered backgrounds. Despite performance improvements from convolutional neural networks (CNNs) and Vision Transformers (ViTs), current models lack a mechanism to trace how small targets trigger directional, layer-wise perturbations in the feature space, which is an essential cue for distinguishing signal from structured noise in infrared scenes. To address this limitation, we propose the Trajectory-Aware Mamba Propagation Network (TAPM-Net), which explicitly models the spatial diffusion behavior of target-induced feature disturbances. TAPM-Net is built upon two novel components: a Perturbation-guided Path Module (PGM) and a Trajectory-Aware State Block (TASB). The PGM constructs perturbation energy fields from multi-level features and extracts gradient-following feature trajectories that reflect the

China's EAST nuclear fusion reactor has successfully kept plasma stable at extreme densities, passing a major fusion milestone and potentially bringing humanity closer to wielding near-limitless clean energy.

At the heart of our sun, fusion is unfolding. As hydrogen atoms merge to form helium, they emit energy, producing the heat and light that reach us here on Earth. Inspired by our nearby star, researchers want to create fusion closer to home. If they can crack the engineering challenges underlying the process, they would create an abundant new source of power to eclipse all others.

arXiv:2601.03569v1 Announce Type: cross Abstract: Local Intrinsic Dimensionality (LID) has shown strong potential for identifying anomalies and outliers in high-dimensional data across a wide range of real-world applications, including landslide failure detection in granular media. Early and accurate identification of failure zones in landslide-prone areas is crucial for effective geohazard mitigation. While existing approaches typically rely on surface displacement data analyzed through statistical or machine learning techniques, they often fall short in capturing both the spatial correlations and temporal dynamics that are inherent in such data. To address this gap, we focus on ground-monitored landslides and introduce a novel approach that jointly incorporates spatial and temporal information, enabling the detection of complex landslides and including multiple successive failures occurring in distinct areas of the same slope. To be specific, our method builds upon an existing

arXiv:2601.03943v1 Announce Type: new Abstract: We introduce a novel fusion scheme enabled by laser-plasma solitons, which promises to overcome several fundamental obstructions to reaching the breakeven condition. For concreteness, we invoke deuterium-tritium (DT) as fuels. The intense electromagnetic field trapped inside the soliton significantly enhances the DT-fusion cross section, its ponderomotive potential evacuates electrons, and it accelerates D/T to kinetic energies suitable for fusion reaction. While electrons are expelled almost instantly, the much heavier D/T moves at picosecond time scale. Such a difference in time scales renders a time window for DT fusion to occur efficiently in an electron-free environment. We inject two consecutive lasers, where the first would excite plasma solitons and the second, much more intense and with a matched lower frequency, would fortify the soliton electromagnetic field resonantly. We impose a plasma density gradient to induce soliton

arXiv:2601.03632v1 Announce Type: cross Abstract: Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model's implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently

arXiv:2601.03660v1 Announce Type: new Abstract: Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and Transformer-based methods, have achieved strong performance on synthetic benchmarks. However, due to the limitations of modality, scalability, and generative capacity, their generalization to novel objects and real-world scenarios remains challenging. In this paper, we propose MGPC, a generalizable multimodal point cloud completion framework that integrates point clouds, RGB images, and text within a unified architecture. MGPC introduces an innovative modality dropout strategy, a Transformer-based fusion module, and a novel progressive generator to improve robustness, scalability, and geometric modeling capability. We further develop an automatic data generation pipeline and construct MGPC-1M, a large-scale

arXiv:2601.03569v1 Announce Type: new Abstract: Local Intrinsic Dimensionality (LID) has shown strong potential for identifying anomalies and outliers in high-dimensional data across a wide range of real-world applications, including landslide failure detection in granular media. Early and accurate identification of failure zones in landslide-prone areas is crucial for effective geohazard mitigation. While existing approaches typically rely on surface displacement data analyzed through statistical or machine learning techniques, they often fall short in capturing both the spatial correlations and temporal dynamics that are inherent in such data. To address this gap, we focus on ground-monitored landslides and introduce a novel approach that jointly incorporates spatial and temporal information, enabling the detection of complex landslides and including multiple successive failures occurring in distinct areas of the same slope. To be specific, our method builds upon an existing

arXiv:2601.03303v1 Announce Type: new Abstract: Cloud computing has changed online communities in three dimensions, which are scalability, adaptability and reduced overhead. But there are serious security concerns which are brought about by its distributed and multi-tenant characteristics. The old methods of detecting and reacting to threats which are mostly reliant on fixed signatures, predefined rules and human operators are becoming less and less effective even in the advanced stages of cyberattacks of cloud infrastructures. The recent trend in the field of addressing these limitations is the creation of technologies of artificial intelligence (AI). The strategies allow independent protection, anomaly detection, and real-time analysis with references to using deep learning, machine learning, and reinforcement learning. Through imbuing AI with a constantly-learning feature, it enables the intrusion detection system to be more accurate and generate a lesser number of false positives

arXiv:2601.02946v1 Announce Type: new Abstract: Helium accumulation in structural ceramics used in nuclear, fusion, and aerospace systems causes swelling, cracking, and early failure, yet controlling this damage has remained elusive. Here, we introduce defect landscape engineering, the deliberate creation of vacancy clusters prior to helium exposure, as a general strategy to suppress helium-induced degradation. Using {\alpha}-SiC as a model, we combine advanced microscopy, strain mapping, helium depth profiling, positron annihilation spectroscopy, and atomistic simulations to demonstrate that tailored pre-damage transforms helium defect evolution. Instead of forming extended platelets and nanocracks, helium is trapped in stable, uniformly dispersed nanobubbles. Simulations reveal that small vacancy clusters act as dual-function sinks for irradiation-induced interstitials and preferential helium traps, fundamentally altering cascade recombination dynamics. This mechanism is

arXiv:2601.02942v1 Announce Type: new Abstract: Fast and accurate solutions of the Grad--Shafranov (GS) equation are essential for equilibrium analysis, integrated modeling, and surrogate model construction in magnetic confinement fusion. In this work, we address a fundamental question: what is the minimum number of free parameters required to accurately represent numerical solutions of the GS equation under fixed-boundary conditions? We demonstrate that, for most practical applications, GS equilibria can be represented using only 2--5 free parameters while maintaining relative errors below 5\%. For higher-accuracy requirements, we introduce a unified spectral representation based on the Miller extended harmonic (MXH) expansion in the poloidal direction combined with shifted Chebyshev (Cheb) polynomials in the radial direction. This MXH--Cheb basis exhibits rapid convergence for two-dimensional GS equilibria. For configurations where three geometric moments (shift, elongation, and

arXiv:2601.02588v1 Announce Type: new Abstract: Motivated by breakthroughs in inertial confinement fusion (ICF), first achieving ignition conditions in National Ignition Facility (NIF) shot N210808 and then laser energy breakeven in N221204, modeling efforts here investigate the effect of imposed magnetic fields on integrated hohlraum simulations of igniting systems. Previous NIF experiments have shown yield and hotspot temperature to increase in magnetized, gas-filled capsules in line with scalings. In this work, we use the 2D radiation-magnetohydrodynamics code Lasnex with a Livermore ICF common model. Simulations are tuned to closely approximate data from unmagnetized experiments. Investigated here is the effect of imposed axial fields of up to 100 T on the fusion output of high-performing ICF shots, specifically the record BigFoot shot N180128, and HYBRID-E shots N210808 and N221204. The main observed effect is an increase in the hotspot temperature due to magnetic insulation.

arXiv:2601.03067v1 Announce Type: new Abstract: Modern large language models (LLMs) drive interactive AI systems but are bottlenecked by the memory-heavy growth of key-value (KV) caches, which limits real-time throughput under concurrent loads. Existing KV-cache compression methods rely on rigid heuristics, disrupt tensor layouts, or require specialized compute, hindering scalability and deployment. We propose joint encoding of KV-cache blocks, which fuses similar blocks across requests and input chunks into shared representations while preserving standard cache structure. This alleviates the KV-cache memory bottleneck, supporting high-concurrency serving without specialized hardware. Theoretically, we analyze the rate-distortion tradeoff of fused cache blocks under a Poisson process model. Empirically, our method achieves up to 4.38 $\times$ KV-cache compression with negligible accuracy loss across diverse LLMs and benchmarks, outperforming recent structured and adaptive

Ever since nuclear fusion was discovered in the 1930s, scientists have wondered if we could somehow replicate and harness the phenomenon behind starlight—the smashing together of hydrogen atoms to form helium and a stupendous amount of clean energy. Fusing hydrogen would yield 200 million times more energy than simply burning it. Unlike nuclear fission, which…

arXiv:2601.02262v1 Announce Type: new Abstract: Benign termination, in which magnetohydrodynamic (MHD) instabilities deconfine runaway electrons (REs) following hydrogenic injections, is a promising strategy for mitigating dangerous RE loads after disruptions. Recent experiments on the Joint European Torus (JET) have explored this scenario at higher pre-disruptive plasma currents than are achievable on other devices, revealing challenges in obtaining benign terminations at $I_p \geq 2.5$ MA. This work analyzes the evolution of these high-current RE beams and their terminating MHD events using fast magnetic sensor measurements and EFIT equilibrium reconstructions for approximately $40$ JET and $20$ DIII-D tokamak discharges. On JET, unsuccessful non-benign terminations occur at low edge safety factor ($q_{\text{edge}} \approx 2$), and are preceded by intermittent, non-terminating MHD events at higher rational $q_{\text{edge}}$. Trends in the internal inductance $l_i$ indicate more

arXiv:2601.01566v1 Announce Type: new Abstract: A method is presented for inferring the deuterium fuel ion temperature from neutron counts measured with fast liquid scintillators in conditions where the ion velocity distribution is Maxwellian. Local neutron count rates at each scintillator position are combined to estimate total neutron yield from the plasma, where absolute detection efficiency is determined via MCNP neutron scattering simulation based on a 3D model of the experiment structure. This method is particularly advantageous for Magnetized Target Fusion applications as it yields a time-resolved diagnostic and does not require direct line-of-sight to the plasma or collimation of the neutrons. The instrumentation configuration, pulse-shape discrimination and pile-up correction algorithms, detector calibration, and ion temperature calculation method with uncertainty characterization are discussed. An application of the method to General Fusion's Plasma Injector~3 (PI3)

arXiv:2601.01367v1 Announce Type: new Abstract: Low-energy heavy-ion beams are fundamentally limited by severe space-charge divergence, which constrains the transportable beam current to a few microamperes in conventional electrostatic accelerators. This limitation is particularly critical for high-mass ions, where the generalized perveance increases rapidly because of their low velocity. Here, we demonstrate that this apparent space-charge limit can be overcome by shaping the electrostatic potential configuration of an existing multistage accelerator, thereby transforming the acceleration column itself into a combined acceleration-focusing column. By optimizing the interstage voltage configuration, a strong electrostatic lens effect is superimposed on the accelerating field to counteract space-charge-driven expansion. We formulate a generalized design framework that quantitatively maps the transport 'design window' in terms of beam current, ion mass, and acceleration voltage. For

arXiv:2601.02092v1 Announce Type: new Abstract: SplitFed Learning (SFL) combines federated learning and split learning to enable collaborative training across distributed edge devices; however, it faces significant challenges in heterogeneous environments with diverse computational and communication capabilities. This paper proposes \textit{SuperSFL}, a federated split learning framework that leverages a weight-sharing super-network to dynamically generate resource-aware client-specific subnetworks, effectively mitigating device heterogeneity. SuperSFL introduces Three-Phase Gradient Fusion (TPGF), an optimization mechanism that coordinates local updates, server-side computation, and gradient fusion to accelerate convergence. In addition, a fault-tolerant client-side classifier and collaborative client--server aggregation enable uninterrupted training under intermittent communication failures. Experimental results on CIFAR-10 and CIFAR-100 with up to 100 heterogeneous clients show

arXiv:2601.02008v1 Announce Type: new Abstract: Explainability domain generalization and rare class reliability are critical challenges in medical AI where deep models often fail under real world distribution shifts and exhibit bias against infrequent clinical conditions This paper introduces XAIMeD an explainable medical AI framework that integrates clinically accurate expert knowledge into deep learning through a unified neuro symbolic architecture XAIMeD is designed to improve robustness under distribution shift enhance rare class sensitivity and deliver transparent clinically aligned interpretations The framework encodes clinical expertise as logical connectives over atomic medical propositions transforming them into machine checkable class specific rules Their diagnostic utility is quantified through weighted feature satisfaction scores enabling a symbolic reasoning branch that complements neural predictions A confidence weighted fusion integrates symbolic and deep outputs while