Search

3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While the vanilla Gaussian Splatting representation is mainly designed for view synthesis, more recent works investigated how to extend it with scene understanding and language features. However, existing methods lack a detailed comprehension of scenes, limiting their ability to segment and interpret complex structures. To this end, We introduce SuperGSeg, a novel approach that fosters cohesive, context-aware scene representation by disentangling segmentation and language field distillation. SuperGSeg first employs neural Gaussians to learn instance and hierarchical segmentation features from multi-view images with the aid of off-the-shelf 2D masks. These features are then leveraged to create a sparse set of what we call Super-Gaussians. Super-Gaussians facilitate the distillation of 2D language features into 3D space. Through Super-Gaussians, our method enables high-dimensional language feature rendering without extreme increases in GPU memory. Extensive experiments demonstrate that SuperGSeg outperforms prior works on both open-vocabulary object localization and semantic segmentation tasks., Comment: 13 pages, 8 figures

Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ separate heads for classification and localization tasks but share the same input feature, leading to suboptimal performance. To address this issue, we propose a novel TAL method with Cross Layer Task Decoupling and Refinement (CLTDR). Based on the feature pyramid of video, CLTDR strategy integrates semantically strong features from higher pyramid layers and detailed boundary-aware boundary features from lower pyramid layers to effectively disentangle the action classification and localization tasks. Moreover, the multiple features from cross layers are also employed to refine and align the disentangled classification and regression results. At last, a lightweight Gated Multi-Granularity (GMG) module is proposed to comprehensively extract and aggregate video features at instant, local, and global temporal granularities. Benefiting from the CLTDR and GMG modules, our method achieves state-of-the-art performance on five challenging benchmarks: THUMOS14, MultiTHUMOS, EPIC-KITCHENS-100, ActivityNet-1.3, and HACS. Our code and pre-trained models are publicly available at: https://github.com/LiQiang0307/CLTDR-GMG., Comment: Accepted in AAAI 2025

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations. Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems.

Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person's appearance or pose. However, prior methods often distort fine-grained textural details from the reference image, despite achieving high overall image quality. We attribute these distortions to inadequate attention to corresponding regions in the reference image. To address this, we thereby propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key in the attention layer during training. Specifically, it is realized via a regularization loss on top of the attention map within a diffusion-based baseline. Our extensive experiments show that Leffa achieves state-of-the-art performance in controlling appearance (virtual try-on) and pose (pose transfer), significantly reducing fine-grained detail distortion while maintaining high image quality. Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models., Comment: github: https://github.com/franciszzj/Leffa, demo: https://huggingface.co/spaces/franciszzj/Leffa, model: https://huggingface.co/franciszzj/Leffa

We establish a high-precision composite model for a piezoelectric fast steering mirror (PFSM) using a Hammerstein structure. A novel asymmetric Bouc-Wen model is proposed to describe the nonlinear rate-independent hysteresis, while a dynamic model is derived to represent the linear rate-dependent component. By analyzing the physical process from the displacement of the piezoelectric actuator to the angle of the PFSM, cross-axis coupling is modeled based on first principles. Given the dynamic isolation of each module on different frequency scales, a step-by-step method for model parameter identification is carried out. Finally, experimental results demonstrate that the identified parameters can accurately represent the hysteresis, creep, and mechanical dynamic characteristics of the PFSM. Furthermore, by comparing the outputs of the identified model with the real PFSM under different excitation signals, the effectiveness of the proposed dual-input dual-output composite model is validated.

This study explores the design of a memory-based dynamic event-triggered mechanisms (DETM) scheme for heterogeneous multi-agent systems (MASs) characterized by interval type-2 Takagi-Sugeno (IT2 T-S) fuzzy models. To address the complex nonlinear uncertainties inherent in such systems, discrete IT2 T-S fuzzy models are employed to accurately capture system dynamics. In response to the limitations on communication resources and computational capabilities within MASs, this research introduces a distributed DETM approach based on a dynamic threshold method. This mechanism effectively minimizes unnecessary communication while maintaining robust performance. The proposed memory-based control strategy not only reduces the conservatism associated with controller design conditions but also enhances overall controller performance. Furthermore, leveraging a non-parallel distributed compensation (non-PDC) strategy, a novel derivation method is developed for controller design conditions that significantly decreases conservatism. This leads to sufficient conditions for the asymptotic stability of the closed-loop system. The designed distributed event-triggered controllers improve the overall performance of MASs, as evidenced by numerical simulations that validate the effectiveness of the proposed approach. Overall, these findings advance the state-of-the-art in control strategies for heterogeneous MASs, offering practical solutions for real-world applications where resource constraints are critical.

In the solar corona, magnetically sheared structures are unstable to both tearing and thermal instabilities in a coupled fashion. However, how the choice of linear perturbation modes influences the time-scale to achieve the thermal runaway in a coupled tearing-thermal coronal current sheet is not well understood to date. Here, we model a force-free Harris current sheet under solar coronal conditions to investigate this coupling in the linear and non-linear regimes. In the linear regime, we adopt the magnetohydrodynamic spectroscopy code Legolas to compare the current sheet under thermal and thermoresistive conditions, after which we initialise non-linear simulations (with MPI-AMRVAC) with the unstable, linear tearing and thermal perturbations obtained with Legolas. It is shown that part of the unstable thermal quasi-continuum adopts tearing properties in the linear stage, but that it is not until the non-linear stage is reached that a true thermal 'runaway' effect leads to condensations inside tearing-induced flux ropes. Hence, the linear stage is governed by the dominant tearing instability whilst condensations form due to tearing-thermal coupling in the non-linear stage. Our results imply that perturbing an equilibrium current sheet with the fastest growing linear mode skips the mode mixing phase in which the dominant instability traditionally emerges, and significantly reduces the time-scale to enter into the non-linear stage and thermal runaway process from its equilibrium configuration., Comment: 14 pages, 19 figures. Accepted for publication in MNRAS

We investigate the inseparability of states generated by superposition of a multipartite pure entangled state with a product state. In particular, we identify specific multipartite entangled states that will always produce inseparability after superposition with an arbitrary completely product state. Thus, these entangled states are unconditionally superposition-robust, and we refer to this phenomenon as ``unconditional inseparability of superposition" in multipartite quantum systems. In this way, we complete the picture of unconditional inseparability of superposition which was introduced earlier for bipartite systems. We also characterize the superposition of a multipartite pure entangled state with a pure bi-separable state. However, the present analysis allows us to obtain a more general result, viz. there exists at least one pure entangled state in any multipartite Hilbert space such that its superposition with an arbitrary completely product state always yields an entangled state. On the other hand, for any bipartite pure entangled state, if at least one of the subsystems is a qubit, then it is always possible to find a suitable product state such that the superposition of the entangled state and the product state produces a product state. In this way, we find a feature of multipartite quantum systems which is in sharp contrast with that of bipartite ones. We then show how unconditional inseparability of superposition can be useful in exhibiting an indistinguishability property within the local unambiguous state discrimination problem., Comment: 9 + epsilon pages, 1 Figure

Diffusion magnetic resonance imaging (dMRI) provides critical insights into the microstructural and connectional organization of the human brain. However, the availability of high-field, open-access datasets that include raw k-space data for advanced research remains limited. To address this gap, we introduce Diff5T, a first comprehensive 5.0 Tesla diffusion MRI dataset focusing on the human brain. This dataset includes raw k-space data and reconstructed diffusion images, acquired using a variety of imaging protocols. Diff5T is designed to support the development and benchmarking of innovative methods in artifact correction, image reconstruction, image preprocessing, diffusion modelling and tractography. The dataset features a wide range of diffusion parameters, including multiple b-values and gradient directions, allowing extensive research applications in studying human brain microstructure and connectivity. With its emphasis on open accessibility and detailed benchmarks, Diff5T serves as a valuable resource for advancing human brain mapping research using diffusion MRI, fostering reproducibility, and enabling collaboration across the neuroscience and medical imaging communities., Comment: 19 pages, 4 figures, 1 table

To address the challenges in networked environments and control problems associated with complex nonlinear uncertain systems, this paper investigates the design of a membership-function-dependent (MFD) memory output-feedback (MOF) controller for interval type-2 (IT2) fuzzy systems under fading channels, leveraging a memory dynamic event-triggering mechanism (MDETM). To conserve communication resources, MDETM reduces the frequency of data transmission. For mitigating design conservatism, a MOF controller is employed. A stochastic process models the fading channel, accounting for phenomena such as reflection, refraction, and diffraction that occur during data packet transmission through networks. An actuator failure model addresses potential faults and inaccuracies in practical applications. Considering the impacts of channel fading and actuator failures, the non-parallel distributed compensation (non-PDC) strategy enhances the robustness and anti-interference capability of the MDETM MOF controller. By fully exploiting membership function information, novel MFD control design results ensure mean-square exponential stability and $\mathscr H_{\infty}$ performance $\gamma$ for the closed-loop system. Simulation studies validate the effectiveness of the proposed approach.

The power grid is a critical infrastructure essential for public safety and welfare. As its reliance on digital technologies grows, so do its vulnerabilities to sophisticated cyber threats, which could severely disrupt operations. Effective protective measures, such as intrusion detection and decision support systems, are essential to mitigate these risks. Machine learning offers significant potential in this field, yet its effectiveness is constrained by the limited availability of high-quality data due to confidentiality and access restrictions. To address this, we introduce a simulation environment that replicates the power grid's infrastructure and communication dynamics. This environment enables the modeling of complex, multi-stage cyber attacks and defensive responses, using attack trees to outline attacker strategies and game-theoretic approaches to model defender actions. The framework generates diverse, realistic attack data to train machine learning algorithms for detecting and mitigating cyber threats. It also provides a controlled, flexible platform to evaluate emerging security technologies, including advanced decision support systems. The environment is modular and scalable, facilitating the integration of new scenarios without dependence on external components. It supports scenario generation, data modeling, mapping, power flow simulation, and communication traffic analysis in a cohesive chain, capturing all relevant data for cyber security investigations under consistent conditions. Detailed modeling of communication protocols and grid operations offers insights into attack propagation, while datasets undergo validation in laboratory settings to ensure real-world applicability. These datasets are leveraged to train machine learning models for intrusion detection, focusing on their ability to identify complex attack patterns within power grid operations.

The modernization of power grid infrastructures necessitates the incorporation of decision support systems to effectively mitigate cybersecurity threats. This paper presents a comprehensive framework based on integrating Attack-Defense Trees and the Multi-Criteria Decision Making method to enhance smart grid cybersecurity. By analyzing risk attributes and optimizing defense strategies, this framework enables grid operators to prioritize critical security measures. Additionally, this paper incorporates findings on decision-making processes in intelligent power systems to present a comprehensive approach to grid cybersecurity. The proposed model aims to optimize the effectiveness and efficiency of grid cybersecurity efforts while offering insights into future grid management challenges.

The Generalized Extreme Value (GEV) distribution plays a critical role in risk assessment across various domains, such as hydrology, climate science, and finance. In this study, we investigate its application in analyzing intraday trading risks within the Chinese stock market, focusing on abrupt price movements influenced by unique trading regulations. To address limitations of traditional GEV parameter estimators, we leverage recently developed robust and asymptotically normal estimators, enabling accurate modeling of extreme intraday price fluctuations. We introduce two risk indicators: the mean risk level (mEVI) and a Stability Indicator (STI) to evaluate the stability of the shape parameter over time. Using data from 261 Chinese and 32 U.S. stocks (2015-2017), we find that Chinese stocks exhibit higher mEVI, corresponding to greater tail risk, while maintaining high model stability. Additionally, we show that Value at Risk (VaR) estimates derived from our GEV models outperform traditional GP and normal-based VaR methods in terms of variance and portfolio optimization. These findings underscore the versatility and efficiency of GEV modeling for intraday risk management and portfolio strategies.

A persistent challenge in astronomical machine learning is a systematic bias where predictions compress the dynamic range of true values -- high values are consistently predicted too low while low values are predicted too high. Understanding this bias has important consequences for astronomical measurements and our understanding of physical processes in astronomical inference. Through analytical examination of linear regression, we show that this bias arises naturally from measurement uncertainties in input features and persists regardless of training sample size, label accuracy, or parameter distribution. In the univariate case, we demonstrate that attenuation becomes important when the ratio of intrinsic signal range to measurement uncertainty ($\sigma_{\text{range}}/\sigma_x$) is below O(10) -- a regime common in astronomy. We further extend the theoretical framework to multivariate linear regression and demonstrate its implications using stellar spectroscopy as a case study. Even under optimal conditions -- high-resolution APOGEE-like spectra (R=24,000) with high signal-to-noise ratios (SNR=100) and multiple correlated features -- we find percent-level bias. The effect becomes even more severe for modern-day low-resolution surveys like LAMOST and DESI due to the lower SNR and resolution. These findings have broad implications, providing a theoretical framework for understanding and addressing this limitation in astronomical data analysis with machine learning., Comment: 36 pages, 13 figures, submitted to OJA. Comments are welcome

The promise of unsupervised multi-view-stereo (MVS) is to leverage large unlabeled datasets, yet current methods underperform when training on difficult data, such as handheld smartphone videos of indoor scenes. Meanwhile, high-quality synthetic datasets are available but MVS networks trained on these datasets fail to generalize to real-world examples. To bridge this gap, we propose a semi-supervised learning framework that allows us to train on real and rendered images jointly, capturing structural priors from synthetic data while ensuring parity with the real-world domain. Central to our framework is a novel set of losses that leverages powerful existing monocular relative-depth estimators trained on the synthetic dataset, transferring the rich structure of this relative depth to the MVS predictions on unlabeled data. Inspired by perceptual image metrics, we compare the MVS and monocular predictions via a deep feature loss and a multi-scale statistical loss. Our full framework, which we call Prism, achieves large quantitative and qualitative improvements over current unsupervised and synthetic-supervised MVS networks. This is a best-case-scenario result, opening the door to using both unlabeled smartphone videos and photorealistic synthetic datasets for training MVS networks., Comment: 11 pages, 6 figures, 3 tables

Sulfide-based photocatalysts (PC) are promising materials for efficiently producing hydrogen (H2). This chapter aims to provide a detailed survey of the recent advancements in sulfide-based photocatalysts and emphasize their enhanced performance and pathways to efficient H2 production. A detailed summary has been given, including several metal sulfides, such as cadmium sulfide (CdS), zinc sulfide (ZnS), molybdenum disulfide (MoS2), tungsten disulfide (WS2), lead sulfide (PbS), nickel sulfides (NiS/NiS2), iron disulfide (FeS2), copper sulfides (CuS/Cu2S), cobalt sulfides (CoS/CoS2), tin disulfide (SnS2), indium sulfide (In2S3), bismuth sulfide (Bi2S3), zinc cadmium sulfide (ZnxCd1-xS), manganese cadmium sulfide (MnxCd1-xS), zinc indium sulfide (ZnIn2S4), and cadmium indium sulfide (CdIn2S4). This chapter will focus on the latest advancements in metal-sulfide-based materials for photocatalytic hydrogen evolution reactions (HER), taking its accelerated growth and excellent research into account. After briefly outlining the basic properties, the chapter will showcase the cutting-edge strategies and recent research progress, including the construction of heterojunctions, defect engineering, co-catalyst loading, elemental doping, and single-atom engineering, which improve the electronic structure and charge separation capabilities of metal sulfides for photocatalytic hydrogen production. A future perspective and outlook have been proposed, focusing on some key points and a standard protocol. With this knowledge, we hope sulfide-based photocatalysts can be modified and engineered to improve their efficiency and stability in future research.

Although hydrogen generation by water electrolysis is the cheapest of all other available sources, water splitting still occurs with sluggish kinetics. It is a challenging barrier for H2 production on a large scale. Moreover, research is still underway to understand the oxygen evolution reaction (OER) and design the catalysts with improved OER performance. Herein, we report the synthesis, characterization, and OER performance of iron-doped copper oxide (CuO) as low-cost catalysts for water oxidation. The OER occurs at about 1.49 V versus the RHE with a Tafel slope of 69 mV/dec in a 1 M KOH solution. The overpotential of 338 mV at 10 mA/cm2 is among the lowest compared with other copper-based materials. The catalyst can deliver a stable current density of >10 mA/cm2 for more than 10 hours. Additionally, wastewater treatment, particularly synthetic dye wastewater, is vital for preventing water scarcity and adverse effects on human health and ecotoxicology. The as-synthesized catalysts are also utilized for Fenton-like photo-degradation under low-power visible household LED lights toward the most commonly industrially used simulated Methylene blue dye wastewater. Almost complete degradation of the MB dye has been achieved within 50 minutes of visible light irradiation with a first-order rate constant of 0.0973/min. This dual functionality feature can open new pathways as a non-noble, highly efficient, and robust catalyst for OER and wastewater treatments.

We explore the charging advantages of a many-body quantum battery driven by a Landau-Zener field. Such a system may be modeled as a Heisenberg XY spin chain with $\textit{N}$ interacting spin-$\frac{1}{2}$ particles under an external magnetic field. Here we consider both nearest-neighbor and long-range spin interactions. The charging performance of this many-body quantum battery is evaluated by comparing Landau-Zener and periodic driving protocols within these interaction regimes. Our findings show that the Landau-Zener driving can offer superior energy deposition and storage efficiency compared to periodic driving. Notably, the Landau-Zener protocol may deliver optimal performance when combined with long-range interactions. The efficiency of a Landau-Zener quantum battery can be significantly enhanced by optimizing key parameters, such as XY anisotropy, the magnitude of the driving field, and interaction strength., Comment: 14 pages, 9 figures

The shift to smart grids has made electrical power systems more vulnerable to sophisticated cyber threats. To protect these systems, holistic security measures that encompass preventive, detective, and reactive components are required, even with encrypted data. However, traditional intrusion detection methods struggle with encrypted traffic, our research focuses on the low-level communication layers of encrypted power grid systems to identify irregular patterns using statistics and machine learning. Our results indicate that a harmonic security concept based on encrypted traffic and anomaly detection is promising for smart grid security; however, further research is necessary to improve detection accuracy.

This study delves into the role of process awareness in enhancing intrusion detection within Smart Grids, considering the increasing fusion of ICT in power systems and the associated emerging threats. The research harnesses a co-simulation environment, encapsulating IT, OT, and ET layers, to model multi-stage cyberattacks and evaluate machine learning-based IDS strategies. The key observation is that process-aware IDS demonstrate superior detection capabilities, especially in scenarios closely tied to operational processes, as opposed to IT-only IDS. This improvement is notable in distinguishing complex cyber threats from regular IT activities. The findings underscore the significance of further developing sophisticated IDS benchmarks and digital twin datasets in Smart Grid environments, paving the way for more resilient cybersecurity infrastructures.

The integration of information and communication technology in distribution grids presents opportunities for active grid operation management, but also increases the need for security against power outages and cyberattacks. This paper examines the impact of cyberattacks on smart grids by replicating the power grid in a secure laboratory environment as a cyber-physical digital twin. A simulation is used to study communication infrastructures for secure operation of smart grids. The cyber-physical digital twin approach combines communication network emulation and power grid simulation in a common modular environment, and is demonstrated through laboratory tests and attack replications.

The zero-error capacity of a noisy classical channel quantifies its ability to transmit information with absolute certainty, i.e., without any error. Unlike Shannon's standard channel capacity, which remains unaffected by pre-shared correlations, zero-error capacity can be enhanced through nonlocal correlations. In this work, we investigate zero-error communication utility of such correlations arising in the 2-2-m Bell scenario, where two parties have two inputs and m possible outcomes per input. For all m\geq2, we construct examples of noisy classical channels with zero zero-error capacity that, when assisted by extremal 2-2-m nonlocal correlations, can transmit one bit of information. While nonlocal correlations arising from quantum entangled states cannot achieve a positive zero-error capacity for these channels, they significantly enhance the probability of successfully transmitting a classical bit in a single use. Extending this analysis to the 2-m-2 Bell scenario, we identify channels with zero zero-error capacity that can nonetheless perfectly transmit log m bits of information when assisted by corresponding extremal nonlocal correlations. Our findings underscore the versatile utility of Bell nonlocal correlations in achieving zero-error communication., Comment: 4.5 + 11 pages; Comments are welcome

Existing self-supervised monocular depth estimation (MDE) models attempt to improve nighttime performance by using GANs to transfer nighttime images into their daytime versions. However, this can introduce inconsistencies due to the complexities of real-world daytime lighting variations, which may finally lead to inaccurate estimation results. To address this issue, we leverage physical-prior-knowledge about light wavelength and light attenuation during nighttime. Specifically, our model, Light-Attenuation-Aware Network (LAA-Net), incorporates physical insights from Rayleigh scattering theory for robust nighttime depth estimation: LAA-Net is trained based on red channel values because red light preserves more information under nighttime scenarios due to its longer wavelength. Additionally, based on Beer-Lambert law, we introduce Red Channel Attenuation (RCA) loss to guide LAA-Net's training. Experiments on the RobotCar-Night, nuScenes-Night, RobotCar-Day, and KITTI datasets demonstrate that our model outperforms SOTA models.

We introduce and study Multi-Quantile estimators for the parameters $( \xi, \sigma, \mu)$ of Generalized Extreme Value (GEV) distributions to provide a robust approach to extreme value modeling. Unlike classical estimators, such as the Maximum Likelihood Estimation (MLE) estimator and the Probability Weighted Moments (PWM) estimator, which impose strict constraints on the shape parameter $\xi$, our estimators are always asymptotically normal and consistent across all values of the GEV parameters. The asymptotic variances of our estimators decrease with the number of quantiles increasing and can approach the Cram\'er-Rao lower bound very closely whenever it exists. Our Multi-Quantile Estimators thus offer a more flexible and efficient alternative for practical applications. We also discuss how they can be implemented in the context of Block Maxima method.

Patterned nanomagnet arrays (PNAs) have been shown to exhibit a strong geometrically frustrated dipole interaction. Some PNAs have also shown emergent domain wall dynamics. Previous works have demonstrated methods to physically probe these magnetization dynamics of PNAs to realize neuromorphic reservoir systems that exhibit chaotic dynamical behavior and high-dimensional nonlinearity. These PNA reservoir systems from prior works leverage echo state properties and linear/nonlinear short-term memory of component reservoir nodes to map and preserve the dynamical information of the input time-series data into nondelay spatial embeddings. Such mappings enable these PNA reservoir systems to imitate and predict/forecast the input time series data. However, these prior PNA reservoir systems are based solely on the nondelay spatial embeddings obtained at component reservoir nodes. As a result, they require a massive number of component reservoir nodes, or a very large spatial embedding (i.e., high-dimensional spatial embedding) per reservoir node, or both, to achieve acceptable imitation and prediction accuracy. These requirements reduce the practical feasibility of such PNA reservoir systems. To address this shortcoming, we present a mixed delay/nondelay embeddings-based PNA reservoir system. Our system uses a single PNA reservoir node with the ability to obtain a mixture of delay/nondelay embeddings of the dynamical information of the time-series data applied at the input of a single PNA reservoir node. Our analysis shows that when these mixed delay/nondelay embeddings are used to train a perceptron at the output layer, our reservoir system outperforms existing PNA-based reservoir systems for the imitation of NARMA 2, NARMA 5, NARMA 7, and NARMA 10 time series data, and for the short-term and long-term prediction of the Mackey Glass time series data.

The high costs and risks involved in extensive environment interactions hinder the practical application of current online safe reinforcement learning (RL) methods. While offline safe RL addresses this by learning policies from static datasets, the performance therein is usually limited due to reliance on data quality and challenges with out-of-distribution (OOD) actions. Inspired by recent successes in offline-to-online (O2O) RL, it is crucial to explore whether offline safe RL can be leveraged to facilitate faster and safer online policy learning, a direction that has yet to be fully investigated. To fill this gap, we first demonstrate that naively applying existing O2O algorithms from standard RL would not work well in the safe RL setting due to two unique challenges: \emph{erroneous Q-estimations}, resulted from offline-online objective mismatch and offline cost sparsity, and \emph{Lagrangian mismatch}, resulted from difficulties in aligning Lagrange multipliers between offline and online policies. To address these challenges, we introduce \textbf{Marvel}, a novel framework for O2O safe RL, comprising two key components that work in concert: \emph{Value Pre-Alignment} to align the Q-functions with the underlying truth before online learning, and \emph{Adaptive PID Control} to effectively adjust the Lagrange multipliers during online finetuning. Extensive experiments demonstrate that Marvel significantly outperforms existing baselines in both reward maximization and safety constraint satisfaction. By introducing the first policy-finetuning based framework for O2O safe RL, which is compatible with many offline and online safe RL methods, our work has the great potential to advance the field towards more efficient and practical safe RL solutions.

In this paper, we focus on the gravitational waves emitted by a stellar-mass object in a quasi-circular inspiral orbit around a central supermassive polymerized black hole in loop quantum gravity. Treating the stellar-mass object as a massive test particle, we derive its equations of motion and the corresponding radial effective potential. We find that the peak of the radial effective potential decreases with the quantum parameter $\hat{k}$. We also examine the impact of quantum corrections on the properties of stable circular orbits around the polymerized black hole. Given that gravitational radiation induces changes in the energy and orbital angular momentum of the smaller object, we model its trajectory as an adiabatic evolution along stable circular orbits. The corresponding gravitational waveforms are generated using the numerical kludge method, revealing that quantum corrections cause phase advances in the gravitational waveforms. We further analyze the potential constraints on the quantum parameter $\hat{k}$ from future space-based gravitational wave observations, concluding that these observations will likely impose stronger constraints on $\hat{k}$ than those obtained from black hole shadow measurements., Comment: 13 pages, 9 figures. arXiv admin note: text overlap with arXiv:2407.00283

As the integration of digital technologies and communication systems continues within distribution grids, new avenues emerge to tackle energy transition challenges. Nevertheless, this deeper technological immersion amplifies the necessity for resilience against threats, encompassing both systemic outages and targeted cyberattacks. To ensure the robustness and safeguarding of vital infrastructure, a thorough examination of potential smart grid vulnerabilities and subsequent countermeasure development is essential. This study delves into the potential of digital twins, replicating a smart grid's cyber-physical laboratory environment, thereby enabling focused cybersecurity assessments. Merging the nuances of communication network emulation and power network simulation, we introduce a flexible, comprehensive digital twin model equipped for hardware-in-the-loop evaluations. Through this innovative framework, we not only verify and refine security countermeasures but also underscore their role in maintaining grid stability and trustworthiness.

The transition to smart grids has increased the vulnerability of electrical power systems to advanced cyber threats. To safeguard these systems, comprehensive security measures-including preventive, detective, and reactive strategies-are necessary. As part of the critical infrastructure, securing these systems is a major research focus, particularly against cyberattacks. Many methods are developed to detect anomalies and intrusions and assess the damage potential of attacks. However, these methods require large amounts of data, which are often limited or private due to security concerns. We propose a co-simulation framework that employs an autonomous agent to execute modular cyberattacks within a configurable environment, enabling reproducible and adaptable data generation. The impact of virtual attacks is compared to those in a physical lab targeting real smart grids. We also investigate the use of large language models for automating attack generation, though current models on consumer hardware are unreliable. Our approach offers a flexible, versatile source for data generation, aiding in faster prototyping and reducing development resources and time.

On-chip quantum photon sources are pivotal components in integrated photonics, driving significant advancements in quantum information technologies over recent decades. Traditionally, the coherence of the pump beam has been considered a critical property in ensuring the quality of the source. In this work, we produce a photon-pair source via spontaneous four-wave mixing pumped by temporally incoherent light in a standard silicon nanowire. Compared to a coherent laser, the incoherence improves pump utilization efficiency, which results in higher source brightness. Additionally, its spectrally uncorrelated nature of incoherent light is transferred to the generated photon source, allowing high-purity state preparation without the need for narrow filtering. Experimentally, we demonstrate the advantages using an amplified spontaneous emission source over a continuous-wave laser. With temporally incoherent pumping, the photon pair generation rate increases by 40%. The coincidence-to-accidental ratio and heralded second-order autocorrelation exhibit improved performance at low power. Our work expands the scope of incoherently pumped quantum states and provides a method for generating photon sources using a more readily accessible light.

We present here a brief discussion, in Bangla (Bengali), on what is entanglement and why it is interesting., Comment: 22 pages, 1 figure; in Bangla (Bengali) language; title, author name, affiliation, abstract are also in English

We have grown (111)- and (001)-oriented NiO thin films on (0001)-Sapphire and (001)-MgO substrates using pulsed laser deposition (PLD), respectively. DC magnetic susceptibility measurements underline that the N\'eel temperatures of the samples are beyond room-temperature. This is further confirmed by the presence of two-magnon Raman scattering modes in these films in ambient conditions. Moreover, relative intensity of the two magnon-mode with respect to a neighboring phonon mode in the films, at least down to 30 nm thickness, is comparable to the same for bulk NiO. UV-vis spectroscopy and spectroscopic ellipsometry determined that the bandgap of the films is 3.6 eV which is well within the range for bulk NiO. Thus, these indicate that the thin films are bulk-like. Further, photoluminescence measurements on (111)-NiO films obtained two-radiative transitions at 385 and 405 nm. The linewidth of the latter broadens towards low temperatures, indicating a plausible exciton-magnon coupling. Overall, these PLD-grown oxide films hold significant technological importance due to their optical transparency and their capacity to host robust magnons at room temperature.

We employ molecular dynamics simulation to study the phase separation and rheological properties of a three-dimensional binary liquid mixture with hydrodynamics undergoing simple shear deformation. The impact of shear intensity on domain growth is investigated, with a focus on how shear primarily distorts the domains, leading to the formation of anisotropic structures. The structural anisotropy is quantified by evaluating domain sizes along the flow and shear direction. The rheological properties of the system is studied in terms of shear stress and excess viscosity. At low shear rates, the system behaves like a Newtonian fluid. However, the strong-shear case is marked by a transition characterized by non-Newtonian behavior.

Emerging superionic conductors Li3InCl6 (LIC) and Li6PS5Cl (LPSC) are very promising for solid-state electrolytes (SSEs) in all-solid-state lithium batteries (ASSLBs). However, unstable lithium-anode interfaces in LIC and LPSC have been observed through experiments and ab initio calculations, while the interphases formed in determining interfacial stability remain unclear. In this study, we investigate the ab initio stability of LIC-Li and LPSC-Li interfaces and interphases. Our ab initio calculations revealed that both interfaces are not chemically or electrochemically thermodynamically stable. Interestingly, the LPSC-Li has a stable interphase, but the LIC-Li doesn't. Moreover, the interlayers were systematically evaluated for the LIC-Li and LPSC-Li interfaces, and the desired interlayer materials are clarified for the two interfaces. This ab initio understanding of the interfaces, interphases and interlayers would help the development of a variety of stable interfaces in ASSLBs.

The Huge Object model of property testing [Goldreich and Ron, TheoretiCS 23] concerns properties of distributions supported on $\{0,1\}^n$, where $n$ is so large that even reading a single sampled string is unrealistic. Instead, query access is provided to the samples, and the efficiency of the algorithm is measured by the total number of queries that were made to them. Index-invariant properties under this model were defined in [Chakraborty et al., COLT 23], as a compromise between enduring the full intricacies of string testing when considering unconstrained properties, and giving up completely on the string structure when considering label-invariant properties. Index-invariant properties are those that are invariant through a consistent reordering of the bits of the involved strings. Here we provide an adaptation of Szemer\'edi's regularity method for this setting, and in particular show that if an index-invariant property admits an $\epsilon$-test with a number of queries depending only on the proximity parameter $\epsilon$, then it also admits a distance estimation algorithm whose number of queries depends only on the approximation parameter., Comment: 57 Pages

Advancements in artificial intelligence, machine learning, and deep learning have catalyzed the transformation of big data analytics and management into pivotal domains for research and application. This work explores the theoretical foundations, methodological advancements, and practical implementations of these technologies, emphasizing their role in uncovering actionable insights from massive, high-dimensional datasets. The study presents a systematic overview of data preprocessing techniques, including data cleaning, normalization, integration, and dimensionality reduction, to prepare raw data for analysis. Core analytics methodologies such as classification, clustering, regression, and anomaly detection are examined, with a focus on algorithmic innovation and scalability. Furthermore, the text delves into state-of-the-art frameworks for data mining and predictive modeling, highlighting the role of neural networks, support vector machines, and ensemble methods in tackling complex analytical challenges. Special emphasis is placed on the convergence of big data with distributed computing paradigms, including cloud and edge computing, to address challenges in storage, computation, and real-time analytics. The integration of ethical considerations, including data privacy and compliance with global standards, ensures a holistic perspective on data management. Practical applications across healthcare, finance, marketing, and policy-making illustrate the real-world impact of these technologies. Through comprehensive case studies and Python-based implementations, this work equips researchers, practitioners, and data enthusiasts with the tools to navigate the complexities of modern data analytics. It bridges the gap between theory and practice, fostering the development of innovative solutions for managing and leveraging data in the era of artificial intelligence., Comment: 174 pages

Recent advancements in computational pathology have produced patch-level Multi-modal Large Language Models (MLLMs), but these models are limited by their inability to analyze whole slide images (WSIs) comprehensively and their tendency to bypass crucial morphological features that pathologists rely on for diagnosis. To address these challenges, we first introduce WSI-Bench, a large-scale morphology-aware benchmark containing 180k VQA pairs from 9,850 WSIs across 30 cancer types, designed to evaluate MLLMs' understanding of morphological characteristics crucial for accurate diagnosis. Building upon this benchmark, we present WSI-LLaVA, a novel framework for gigapixel WSI understanding that employs a three-stage training approach: WSI-text alignment, feature space alignment, and task-specific instruction tuning. To better assess model performance in pathological contexts, we develop two specialized WSI metrics: WSI-Precision and WSI-Relevance. Experimental results demonstrate that WSI-LLaVA outperforms existing models across all capability dimensions, with a significant improvement in morphological analysis, establishing a clear correlation between morphological understanding and diagnostic accuracy., Comment: 38 pages, 22 figures, 35 tables

Experimental realizations of Abelian fractional Chern insulators (FCIs) have demonstrated the potentials of moir\'e systems in synthesizing exotic quantum phases. Remarkably, twisted multilayer graphene system may also host non-Abelian states competing with charge density wave under Coulomb interaction. Here, through larger scale exact diagonalization simulations, we map out the quantum phase diagram for $\nu=1/2$ system with electrons occupying the lowest moir\`e band of the double twisted bilayer graphene. By increasing the system size, we find the ground state has six-fold near degeneracy and with a finite spectral gap separating the ground states from excited states across a broad range of parameters. Further computation of many-body Chern number establish the topological order of the state, and we rule out possibility of charge density wave orders based on featureless density structure factor. Furthermore, we inspect the particle-cut entanglement spectrum to identify the topological state as a non-Abelian Moore-Read state. Combining all the above evidences we conclude that Moore-Read ground state dominates the quantum phase diagram for the double twisted bilayer graphene system for a broad range of coupling strength with realistic Coulomb interaction.

In this work, we explore a cost-effective framework for multilingual image generation. We find that, unlike models tuned on high-quality images with multilingual annotations, leveraging text encoders pre-trained on widely available, noisy Internet image-text pairs significantly enhances data efficiency in text-to-image (T2I) generation across multiple languages. Based on this insight, we introduce MuLan, Multi-Language adapter, a lightweight language adapter with fewer than 20M parameters, trained alongside a frozen text encoder and image diffusion model. Compared to previous multilingual T2I models, this framework offers: (1) Cost efficiency. Using readily accessible English data and off-the-shelf multilingual text encoders minimizes the training cost; (2) High performance. Achieving comparable generation capabilities in over 110 languages with CLIP similarity scores nearly matching those in English (38.61 for English vs. 37.61 for other languages); and (3) Broad applicability. Seamlessly integrating with compatible community tools like LoRA, LCM, ControlNet, and IP-Adapter, expanding its potential use cases.

It has recently been argued that a proposal to nonperturbatively regulate chiral gauge theories on the boundary of a five-dimensional lattice will fail due to the existence of exact $U(1)$ symmetries not present in the target theories. A related observation is that in the presence of gauge fields with nontrivial topology, fermion zeromodes will appear embedded in the extra dimension which do not decouple from the four-dimensional world. Here we show that these problems can be evaded by simulating the theory in the trivial topological sector of the boundary gauge fields. A regulated version of the Standard Model using this approach in the continuum and large volume limits is expected to appear as if it possessed a Peccei-Quinn mechanism for relaxing $\theta_\text{QCD}$ to zero, without there being an axion in the spectrum., Comment: Corrections to references

Explainable Artificial Intelligence (XAI) addresses the growing need for transparency and interpretability in AI systems, enabling trust and accountability in decision-making processes. This book offers a comprehensive guide to XAI, bridging foundational concepts with advanced methodologies. It explores interpretability in traditional models such as Decision Trees, Linear Regression, and Support Vector Machines, alongside the challenges of explaining deep learning architectures like CNNs, RNNs, and Large Language Models (LLMs), including BERT, GPT, and T5. The book presents practical techniques such as SHAP, LIME, Grad-CAM, counterfactual explanations, and causal inference, supported by Python code examples for real-world applications. Case studies illustrate XAI's role in healthcare, finance, and policymaking, demonstrating its impact on fairness and decision support. The book also covers evaluation metrics for explanation quality, an overview of cutting-edge XAI tools and frameworks, and emerging research directions, such as interpretability in federated learning and ethical AI considerations. Designed for a broad audience, this resource equips readers with the theoretical insights and practical skills needed to master XAI. Hands-on examples and additional resources are available at the companion GitHub repository: https://github.com/Echoslayer/XAI_From_Classical_Models_to_LLMs.

We present an analysis of the structure, kinematics, and chemo-dynamical properties of the Milky Way bulge using data from OGLE, APOGEE, and Gaia. Firstly, we identified 2,156 ab-type RR Lyrae stars (RRabs) from OGLE-IV, then through their apocenters derived from orbital integration, we distinguished three populations: the central bulge RRabs, the inner bulge RRabs and halo interlopers. Inner bulge RRabs kinematically align with the Galactic bar, while central bulge RRabs show slower rotation with lower velocity dispersion, which do not trace the bar. Higher velocity dispersion stars were identified as halo interlopers. Then, orbital analysis of 28,188 APOGEE Red Clump and Red Giant Branch stars revealed kinematic properties consistent with RRabs, and chemical abundance distribution displayed a bimodal stellar density pattern, suggesting complex star evolution histories and also slightly different star formation histories for the inner bulge and central bulge. The differences in the density distribution on the $|\mathrm{Z}|_{\text{max}}$-eccentricity plane for the central bulge, inner bulge, and halo regions are clearly detected. Finally, the chemodynamical analysis of 301,485 Gaia DR3 red giants without orbital integration indicated that metal-rich bulge stars form a bar-like structure, while metal-poor bulge stars are dominated by velocity dispersion. It is found that the classification of bulge stars based on orbital parameters, rather than solely on metallicity, provides a more accurate population separation. Our results also support that secular evolution of the Galactic disk is the primary origin of the bulge, and boxy/peanut (B-P) bulge population might be more dominant than X-shape bulge population., Comment: 24 pages, 20 figures

We construct infinitely many examples of four manifolds with macroscopic dimension 4 equipped with circle bundles whose total spaces admit metrics of positive scalar curvature. Further, we verify that these bundles have macroscopic dimension at most 3. Our constructions are based on techniques from symplectic geometry., Comment: 11 pages, comments welcome

Despite the success of the O-RAN Alliance in developing a set of interoperable interfaces, development of unique Radio Access Network (RAN) deployments remains challenging. This is especially true for military communications, where deployments are highly specialized with limited volume. The construction and maintenance of the RAN, which is a real time embedded system, is an ill-defined NP problem requiring teams of specialized system engineers, with specialized knowledge of the hardware platform. In this paper, we introduce a RAN Domain Specific Language (RDSL(TM)) to formally describe use cases, constraints, and multi-vendor hardware/software abstraction to allow automation of RAN construction. In this DSL, system requirements are declarative, and performance constraints are guaranteed by construction using an automated system solver. Using our RAN system solver platform, Gabriel(TM) we show how a system engineer can confidently modify RAN functionality without knowledge of the underlying hardware. We show benefits for specific system requirements when compared to the manually optimized, default configuration of the Intel FlexRAN(TM), and conclude that DSL/automation driven construction of the RAN can lead to significant power and latency benefits when the deployment constraints are tuned for a specific case. We give examples of how constraints and requirements can be formatted in a "Kubernetes style" YAML format which allows the use of other tools, such as Ansible, to integrate the generation of these requirements into higher level automation flows such as Service Management and Orchestration (SMO)., Comment: 6 pages, 11 figures, 19 references. Presented at the IEEE Military Communications Conference, 28 Oct - 1 Nov 2024, Washington DC

Achieving quantum advantage in energy storage and power extraction is a primary objective in the design of quantum-based batteries. We explore how long-range (LR) interactions in conjunction with Floquet driving can improve the performance of quantum batteries, particularly when the battery is initialized in a fully polarized state. In particular, we exhibit that by optimizing the driving frequency, the maximum average power scales super extensively with system-size which is not achievable through next-nearest neighbor interactions or traditional unitary charging, thereby gaining genuine quantum advantage. We illustrate that the inclusion of either two-body or many-body interaction terms in the LR charging Hamiltonian leads to a scaling benefit. Furthermore, we discover that a super-linear scaling in power results from increasing the strength of interaction compared to the transverse magnetic field and the range of interaction with low fall-off rate, highlighting the advantageous role of long-range interactions in optimizing quantum battery charging., Comment: 10 pages, 8 figures

Software composition analysis (SCA) denotes the process of identifying open-source software components in an input software application. SCA has been extensively developed and adopted by academia and industry. However, we notice that the modern SCA techniques in industry scenarios still need to be improved due to privacy concerns. Overall, SCA requires the users to upload their applications' source code to a remote SCA server, which then inspects the applications and reports the component usage to users. This process is privacy-sensitive since the applications may contain sensitive information, such as proprietary source code, algorithms, trade secrets, and user data. Privacy concerns have prevented the SCA technology from being used in real-world scenarios. Therefore, academia and the industry demand privacy-preserving SCA solutions. For the first time, we analyze the privacy requirements of SCA and provide a landscape depicting possible technical solutions with varying privacy gains and overheads. In particular, given that de facto SCA frameworks are primarily driven by code similarity-based techniques, we explore combining several privacy-preserving protocols to encapsulate the similarity-based SCA framework. Among all viable solutions, we find that multi-party computation (MPC) offers the strongest privacy guarantee and plausible accuracy; it, however, incurs high overhead (184 times). We optimize the MPC-based SCA framework by reducing the amount of crypto protocol transactions using program analysis techniques. The evaluation results show that our proposed optimizations can reduce the MPC-based SCA overhead to only 8.5% without sacrificing SCA's privacy guarantee or accuracy., Comment: 14 pages, 9 figures, 47th International Conference on Software Engineering (ICSE 2025), Research Track

Using $(10087 \pm 44) \times 10^6$ $J/\psi$ events collected with the BESIII detector in 2009, 2012, 2018 and 2019, the tracking efficiency of charged pions is studied using the decay $J/\psi \rightarrow \pi^+ \pi^- \pi^0$. The systematic uncertainty of the tracking efficiency and the corresponding correction factors for charged pions are evaluated, in bins of transverse momentum and polar angle of the charged pions., Comment: 9 pages and 10 figures

The response of many-body quantum systems to an optical pulse can be extremely challenging to model. Here we explore the use of neural networks, both traditional and generative, to learn and thus simulate the response of such a system from data. The quantum system can be viewed as performing a complex mapping from an input time-series (the optical pulse) to an output time-series (the systems response) which is often also an optical pulse. Using both the transverse and non-integrable Ising models as examples, we show that not only can temporal convolutional networks capture the input/output mapping generated by the system but can also be used to characterize the complexity of the mapping. This measure of complexity is provided by the size of the smallest latent space that is able to accurately model the mapping. We further find that a generative model, in particular a variational auto-encoder, significantly outperforms traditional auto-encoders at learning the complex response of many-body quantum systems. For the example that generated the most complex mapping, the variational auto-encoder produces outputs that have less than 10% error for more than 90% of inputs across our test data.

The detection of sensitive content in large datasets is crucial for ensuring that shared and analysed data is free from harmful material. However, current moderation tools, such as external APIs, suffer from limitations in customisation, accuracy across diverse sensitive categories, and privacy concerns. Additionally, existing datasets and open-source models focus predominantly on toxic language, leaving gaps in detecting other sensitive categories such as substance abuse or self-harm. In this paper, we put forward a unified dataset tailored for social media content moderation across six sensitive categories: conflictual language, profanity, sexually explicit material, drug-related content, self-harm, and spam. By collecting and annotating data with consistent retrieval strategies and guidelines, we address the shortcomings of previous focalised research. Our analysis demonstrates that fine-tuning large language models (LLMs) on this novel dataset yields significant improvements in detection performance compared to open off-the-shelf models such as LLaMA, and even proprietary OpenAI models, which underperform by 10-15% overall. This limitation is even more pronounced on popular moderation APIs, which cannot be easily tailored to specific sensitive content categories, among others.

Change detection, which typically relies on the comparison of bi-temporal images, is significantly hindered when only a single image is available. Comparing a single image with an existing map, such as OpenStreetMap, which is continuously updated through crowd-sourcing, offers a viable solution to this challenge. Unlike images that carry low-level visual details of ground objects, maps convey high-level categorical information. This discrepancy in abstraction levels complicates the alignment and comparison of the two data types. In this paper, we propose a \textbf{La}nguage-\textbf{VI}sion \textbf{D}iscriminator for d\textbf{E}tecting changes in satellite image with map references, namely \ours{}, which leverages language to bridge the information gap between maps and images. Specifically, \ours{} formulates change detection as the problem of ``{\textit Does the pixel belong to [class]?}'', aligning maps and images within the feature space of the language-vision model to associate high-level map categories with low-level image details. Moreover, we build a mixture-of-experts discriminative module, which compares linguistic features from maps with visual features from images across various semantic perspectives, achieving comprehensive semantic comparison for change detection. Extensive evaluation on four benchmark datasets demonstrates that \ours{} can effectively detect changes in satellite image with map references, outperforming state-of-the-art change detection algorithms, e.g., with gains of about $13.8$\% on the DynamicEarthNet dataset and $4.3$\% on the SECOND dataset.