Search

Anomaly detection (AD) plays a pivotal role in AI applications, e.g., in classification, and intrusion/threat detection in cybersecurity. However, most existing methods face challenges of heterogeneity amongst feature subsets posed by non-independent and identically distributed (non-IID) data. We propose a novel neural network model called Multiple-Input Auto-Encoder for AD (MIAEAD) to address this. MIAEAD assigns an anomaly score to each feature subset of a data sample to indicate its likelihood of being an anomaly. This is done by using the reconstruction error of its sub-encoder as the anomaly score. All sub-encoders are then simultaneously trained using unsupervised learning to determine the anomaly scores of feature subsets. The final AUC of MIAEAD is calculated for each sub-dataset, and the maximum AUC obtained among the sub-datasets is selected. To leverage the modelling of the distribution of normal data to identify anomalies of the generative models, we develop a novel neural network architecture/model called Multiple-Input Variational Auto-Encoder (MIVAE). MIVAE can process feature subsets through its sub-encoders before learning distribution of normal data in the latent space. This allows MIVAE to identify anomalies that deviate from the learned distribution. We theoretically prove that the difference in the average anomaly score between normal samples and anomalies obtained by the proposed MIVAE is greater than that of the Variational Auto-Encoder (VAEAD), resulting in a higher AUC for MIVAE. Extensive experiments on eight real-world anomaly datasets demonstrate the superior performance of MIAEAD and MIVAE over conventional methods and the state-of-the-art unsupervised models, by up to 6% in terms of AUC score. Alternatively, MIAEAD and MIVAE have a high AUC when applied to feature subsets with low heterogeneity based on the coefficient of variation (CV) score., Comment: 16 pages

Applying Large language models (LLMs) within specific domains requires substantial adaptation to account for the unique terminologies, nuances, and context-specific challenges inherent to those areas. Here, we introduce DropMicroFluidAgents (DMFAs), an advanced language-driven framework leveraging state-of-the-art pre-trained LLMs. DMFAs employs LLM agents to perform two key functions: (1) delivering focused guidance, answers, and suggestions specific to droplet microfluidics and (2) generating machine learning models to optimise and automate the design of droplet microfluidic devices, including the creation of code-based computer-aided design (CAD) scripts to enable rapid and precise design execution. Experimental evaluations demonstrated that the integration of DMFAs with the LLAMA3.1 model yielded the highest accuracy of 76.15%, underscoring the significant performance enhancement provided by agent integration. This effect was particularly pronounced when DMFAs were paired with the GEMMA2 model, resulting in a 34.47% improvement in accuracy compared to the standalone GEMMA2 configuration. This study demonstrates the effective use of LLM agents in droplet microfluidics research as powerful tools for automating workflows, synthesising knowledge, optimising designs, and interacting with external systems. These capabilities enable their application across education and industrial support, driving greater efficiency in scientific discovery and innovation.

In this paper, we would like to study the critical exponent for semi-linear $\sigma$-evolution equations with different damping types under the influence of additional regularity for the initial data. On the one hand, we establish the existence of global (in time) solutions for small initial data and the blow-up in finite time solutions in the supercritical case and the subcritical case, respectively. The very interesting phenomenon is that the critical case belonging to the global solution range or the blow-up solution range depends heavily on the assumption of additional regularity for the initial data. Furthermore, we are going to provide lifespan estimates for solutions when the blow-up phenomenon occurs., Comment: 19 pages

Traditional methods for visualizing dynamic human expressions, particularly in medical training, often rely on flat-screen displays or static mannequins, which have proven inefficient for realistic simulation. In response, we propose a platform that leverages a 3D interactive facial avatar capable of displaying non-verbal feedback, including pain signals. This avatar is projected onto a stereoscopic, view-dependent 3D display, offering a more immersive and realistic simulated patient experience for pain assessment practice. However, there is no existing solution that dynamically predicts and projects interactive 3D facial avatars in real-time. To overcome this, we emphasize the need for a 3D display projection system that can project the facial avatar holographically, allowing users to interact with the avatar from any viewpoint. By incorporating 3D Gaussian Splatting (3DGS) and real-time view-dependent calibration, we significantly improve the training environment for accurate pain recognition and assessment.

A space-time interface-fitted approximation of an inverse source problem for the advection-diffusion equation with moving subdomains is investigated. The problem is reformulated as an optimization problem using Tikhonov regularization. A space-time interface-fitted method is employed to discretize the advection-diffusion equation, where two second-order a priori error estimates are established with respect to the $L^2$-norms. Additionally, the regularized source is discretized sequentially using the variational approach, the element-wise constant discretization, and finally, the post-processing strategy. Optimal error estimates are achieved for the first two methods, while superlinear convergence is obtained for the third. Furthermore, a priori choices for the regularization parameter are proposed, depending on the mesh size and noise level. These choices ensure that the discrete and post-processing solutions strongly converge to the exact source as the mesh size and noise level tend to zero.

Teacher-forcing training for audio captioning usually leads to exposure bias due to training and inference mismatch. Prior works propose the contrastive method to deal with caption degeneration. However, the contrastive method ignores the temporal information when measuring similarity across acoustic and linguistic modalities, leading to inferior performance. In this work, we develop the temporal-similarity score by introducing the unbiased sliced Wasserstein RBF (USW-RBF) kernel equipped with rotary positional embedding to account for temporal information across modalities. In contrast to the conventional sliced Wasserstein RBF kernel, we can form an unbiased estimation of USW-RBF kernel via Monte Carlo estimation. Therefore, it is well-suited to stochastic gradient optimization algorithms, and its approximation error decreases at a parametric rate of $\mathcal{O}(L^{-1/2})$ with $L$ Monte Carlo samples. Additionally, we introduce an audio captioning framework based on the unbiased sliced Wasserstein kernel, incorporating stochastic decoding methods to mitigate caption degeneration during the generation process. We conduct extensive quantitative and qualitative experiments on two datasets, AudioCaps and Clotho, to illustrate the capability of generating high-quality audio captions. Experimental results show that our framework is able to increase caption length, lexical diversity, and text-to-audio self-retrieval accuracy., Comment: 17 pages, 9 tables, 2 figures

Retrieval-augmented generation (RAG) has proven effective in integrating knowledge into large language models (LLMs). However, conventional RAGs struggle to capture complex relationships between pieces of knowledge, limiting their performance in intricate reasoning that requires integrating knowledge from multiple sources. Recently, graph-enhanced retrieval augmented generation (GraphRAG) builds graph structure to explicitly model these relationships, enabling more effective and efficient retrievers. Nevertheless, its performance is still hindered by the noise and incompleteness within the graph structure. To address this, we introduce GFM-RAG, a novel graph foundation model (GFM) for retrieval augmented generation. GFM-RAG is powered by an innovative graph neural network that reasons over graph structure to capture complex query-knowledge relationships. The GFM with 8M parameters undergoes a two-stage training process on large-scale datasets, comprising 60 knowledge graphs with over 14M triples and 700k documents. This results in impressive performance and generalizability for GFM-RAG, making it the first graph foundation model applicable to unseen datasets for retrieval without any fine-tuning required. Extensive experiments on three multi-hop QA datasets and seven domain-specific RAG datasets demonstrate that GFM-RAG achieves state-of-the-art performance while maintaining efficiency and alignment with neural scaling laws, highlighting its potential for further improvement., Comment: 19 pages, 6 figures

We proved convergence rates of fully discrete multi-level simultaneous linear collocation approximation of solutions to parametric elliptic PDEs on bounded polygonal domain with log-normal random inputs based on a finite number of their values at points in the spatial-parametric domain. These convergence rates significantly improve the best-known convergence rates of fully discrete collocation approximation and with some logarithm factors coincide with the convergence rates of best $n$-term approximation. These results are obtained as consequences of general results on multi-level linear sampling recovery in abstract Bochner spaces.

Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models by selectively unlearning undesirable concepts. The common principle of previous works to remove a specific concept is to map it to a fixed generic concept, such as a neutral concept or just an empty text prompt. In this paper, we demonstrate that this fixed-target strategy is suboptimal, as it fails to account for the impact of erasing one concept on the others. To address this limitation, we model the concept space as a graph and empirically analyze the effects of erasing one concept on the remaining concepts. Our analysis uncovers intriguing geometric properties of the concept space, where the influence of erasing a concept is confined to a local region. Building on this insight, we propose the Adaptive Guided Erasure (AGE) method, which \emph{dynamically} selects optimal target concepts tailored to each undesirable concept, minimizing unintended side effects. Experimental results show that AGE significantly outperforms state-of-the-art erasure methods on preserving unrelated concepts while maintaining effective erasure performance. Our code is published at {https://github.com/tuananhbui89/Adaptive-Guided-Erasure}.

We present a theory that studies the state composition of a bound exciton in magnetic field. Using a basis set made of products of free electron and hole wavefunctions in Landau gauge, we derive a secular equation which shows the relation between Landau levels (LLs) of the electron and hole when a bound exciton is formed. Focusing on excitons in the light cone, we establish a scattering selection rule for the interaction of an electron in LL $n_\text{e}$ with a hole in LL $n_\text{h}$. We solve the resulting secular equation and identify a simple pairing law, $n_\text{e} = n_\text{h} + l$, which informs us on the construction of a bound exciton state with magnetic quantum number $l$, and on the interaction of the exciton magnetic moment with magnetic field. We obtain good agreement between theory results and recent measurements of the diamagnetic shifts of exciton states in WSe$_2$ monolayers., Comment: 19 pages, 6 figures. We welcome your feedback

Recently, cellular Ambient Backscattering has been proposed for 4G/5G/6G networks. An Ambient backscatter tag broadcasts its message by backscattering ambient downlink waves from the closest base station according to a predefined pattern. A tag is detected by smartphones nearby. This paper presents, for the first time, a novel ambient backscatter communication system exploiting uplink ambient waves from smartphones instead of downlink waves. In this novel system, the base station connected to a smartphone monitors the uplink pilot signals and detects tags in proximity. The proposed system is implemented and tested with prototypes of tags, a commercial 4G smartphone and a 4G Software Defined Radio base station. At the base station side, a non-coherent correlator receiver is implemented, and a novel technique based on pre-correlation data processing is proposed to separate useful variations on pilot signals due to tags from variations due to time varying channel effects. To deal with collision between multiple tags, distinct Gold pseudo noise codes with minimum cross correlation are used. Tests are run in different indoor and outdoor environments. A receiver detection probability of 95% has been achieved at 0.5% False-alarm probability when the tag is at 5 meters from the UE. At the refresh rate of 2 seconds, the proposed scheme is suitable for tracking objects at moderate speeds and can therefore be used for many passive IoT-based applications., Comment: 9 pages, 16 figures, submitted to JRFID (under review)

The problem of estimating the number of clusters (say k) is one of the major challenges for the partitional clustering. This paper proposes an algorithm named k-SCC to estimate the optimal k in categorical data clustering. For the clustering step, the algorithm uses the kernel density estimation approach to define cluster centers. In addition, it uses an information-theoretic based dissimilarity to measure the distance between centers and objects in each cluster. The silhouette analysis based approach is then used to evaluate the quality of different clustering obtained in the former step to choose the best k. Comparative experiments were conducted on both synthetic and real datasets to compare the performance of k-SCC with three other algorithms. Experimental results show that k-SCC outperforms the compared algorithms in determining the number of clusters for each dataset.

Ensuring the correctness of code generated by Large Language Models (LLMs) presents a significant challenge in AI-driven software development. Existing approaches predominantly rely on black-box (closed-box) approaches that evaluate correctness post-generation, failing to utilize the rich insights embedded in the LLMs' internal states during code generation. In this paper, we introduce OPENIA, a novel white-box (open-box) framework that leverages these internal representations to assess the correctness of LLM-generated code. OPENIA systematically analyzes the intermediate states of representative open-source LLMs specialized for code, including DeepSeek-Coder, CodeLlama, and MagicCoder, across diverse code generation benchmarks. Our empirical analysis reveals that these internal representations encode latent information, which strongly correlates with the correctness of the generated code. Building on these insights, OPENIA uses a white-box/open-box approach to make informed predictions about code correctness, offering significant advantages in adaptability and robustness over traditional classification-based methods and zero-shot approaches. Experimental results demonstrate that OPENIA consistently outperforms baseline models, achieving higher accuracy, precision, recall, and F1-Scores with up to a 2X improvement in standalone code generation and a 46% enhancement in repository-specific scenarios. By unlocking the potential of in-process signals, OPENIA paves the way for more proactive and efficient quality assurance mechanisms in LLM-assisted code generation.

Solid-state quantum emitters, molecular-sized complexes releasing a single photon at a time, have garnered much attention owing to their use as a key building block in various quantum technologies. Among these, quantum emitters in hexagonal boron nitride (hBN) have emerged as front runners with superior attributes compared to other competing platforms. These attributes are attainable thanks to the robust, two-dimensional lattice of the material formed by the extremely strong B-N bonds. This review discusses the fundamental properties of quantum emitters in hBN and highlights recent progress in the field. The focus is on the fabrication and engineering of these quantum emitters facilitated by state-of-the-art equipment. Strategies to integrate the quantum emitters with dielectric and plasmonic cavities to enhance their optical properties are summarized. The latest developments in new classes of spin-active defects, their predicted structural configurations, and the proposed suitable quantum applications are examined. Despite the current challenges, quantum emitters in hBN have steadily become a promising platform for applications in quantum information science.

Sharpness-Aware Minimization (SAM) has attracted significant attention for its effectiveness in improving generalization across various tasks. However, its underlying principles remain poorly understood. In this work, we analyze SAM's training dynamics using the maximum eigenvalue of the Hessian as a measure of sharpness, and propose a third-order stochastic differential equation (SDE), which reveals that the dynamics are driven by a complex mixture of second- and third-order terms. We show that alignment between the perturbation vector and the top eigenvector is crucial for SAM's effectiveness in regularizing sharpness, but find that this alignment is often inadequate in practice, limiting SAM's efficiency. Building on these insights, we introduce Eigen-SAM, an algorithm that explicitly aims to regularize the top Hessian eigenvalue by aligning the perturbation vector with the leading eigenvector. We validate the effectiveness of our theory and the practical advantages of our proposed approach through comprehensive experiments. Code is available at https://github.com/RitianLuo/EigenSAM.

This paper investigates predicting market strength solely from candlestick chart images to assist investment decisions. The core research problem is developing an effective computer vision-based model using raw candlestick visuals without time-series data. We specifically analyze the impact of incorporating candlestick patterns that were detected by YOLOv8. The study implements two approaches: pure CNN on chart images and a Decomposer architecture detecting patterns. Experiments utilize diverse financial datasets spanning stocks, cryptocurrencies, and forex assets. Key findings demonstrate candlestick patterns do not improve model performance over only image data in our research. The significance is illuminating limitations in candlestick image signals. Performance peaked at approximately 0.7 accuracy, below more complex time-series models. Outcomes reveal challenges in distilling sufficient predictive power from visual shapes alone, motivating the incorporation of other data modalities. This research clarifies how purely image-based models can inform trading while confirming patterns add little value over raw charts. Our content is endeavored to be delineated into distinct sections, each autonomously furnishing a unique contribution while maintaining cohesive linkage. Note that, the examples discussed herein are not limited to the scope, applicability, or knowledge outlined in the paper., Comment: ACMLC 2025; 8 pages

The presence of impurities in the neutron star crust is known to affect in an important way the thermal and electrical conductivity of the star. In this work, we explore the possibility that such impurities might arise from the simultaneous presence of heavy ions together with Hydrogen and Helium isotopes formed during the cooling process of the star. We consider an equilibrium population of such light particles at temperatures close to the crystallization of the crust within an effective quasi-particle approach including in-medium binding energy shifts, and using different versions of the relativistic mean field approach for the crustal modeling. Thermal effects are consistently included also in the dominant ion species present in each crustal layer described in the compressible liquid drop approximation. We find that the impurity factor associated to light clusters is comparatively very small and can be neglected in transport calculations, even if a strong model dependence is observed., Comment: 12 pages, 8 figures, 2 tables

Ambient Internet of Things (AIoT), recently standardized by the 3rd Generation Partnership Project (3GPP), demands a low-power wide-area communication solution that operates several orders of magnitude below the power requirements of existing 3GPP specifications. Ambient backscatter communication (AmBC) is considered as a competitive potential technique by harvesting energy from the ambient RF signal. This paper considers a symbiotic AmBC into Long Term Evolution (LTE) cellular system uplink. Leveraging by LTE uplink channel estimation ability, AIoT conveys its own message to Base Station (BS) by modulating backscatter path. We explore the detector design, analyze the error performance of the proposed scheme, provide exact expression and its Guassian approximation for the error probability. We corroborate the receiver error performance by Monte Carlo simulation. Analysis of communication range reveals AmBC achieves a reasonable BER of order of magnitude $10^{-2}$ within four times wavelength reading distance. In addition, a AmBC prototype in LTE uplink confirms the its feasibility. The over-the-air experiment results validate theoretical analysis. Hence, the proposed AmBC approach enables AIoT deployment with minimal changes to the LTE system., Comment: Draft V0.3

Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication. This transformation builds upon a foundation of generative models to produce realistic images, videos, and 3D or 4D content. Traditionally, generative models primarily focus on visual fidelity while often neglecting the physical plausibility of generated content. This gap limits their effectiveness in applications requiring adherence to real-world physical laws, such as robotics, autonomous systems, and scientific simulations. As generative AI evolves to increasingly integrate physical realism and dynamic simulation, its potential to function as a "world simulator" expands-enabling the modeling of interactions governed by physics and bridging the divide between virtual and physical realities. This survey systematically reviews this emerging field of physics-aware generative AI in computer vision, categorizing methods based on how they incorporate physical knowledge-either through explicit simulation or implicit learning. We analyze key paradigms, discuss evaluation protocols, and identify future research directions. By offering a comprehensive overview, this survey aims to help future developments in physically grounded generation for vision. The reviewed papers are summarized at https://github.com/BestJunYu/Awesome-Physics-aware-Generation.

Low harvested energy poses a significant challenge to sustaining continuous communication in energy harvesting (EH)-powered wireless sensor networks. This is mainly due to intermittent and limited power availability from radio frequency signals. In this paper, we introduce a novel energy-aware resource allocation problem aimed at enabling the asynchronous accumulate-then-transmit protocol, offering an alternative to the extensively studied harvest-then-transmit approach. Specifically, we jointly optimize power allocation and time fraction dedicated to EH to maximize the average long-term system throughput, accounting for both data and energy queue lengths. By leveraging inner approximation and network utility maximization techniques, we develop a simple yet efficient iterative algorithm that guarantees at least a local optimum and achieves long-term utility improvement. Numerical results highlight the proposed approach's effectiveness in terms of both queue length and sustained system throughput., Comment: To be appeared in IEEE COMMUNICATIONS LETTERS

Symbolic music analysis tasks are often performed by models originally developed for Natural Language Processing, such as Transformers. Such models require the input data to be represented as sequences, which is achieved through a process of tokenization. Tokenization strategies for symbolic music often rely on absolute MIDI values to represent pitch information. However, music research largely promotes the benefit of higher-level representations such as melodic contour and harmonic relations for which pitch intervals turn out to be more expressive than absolute pitches. In this work, we introduce a general framework for building interval-based tokenizations. By evaluating these tokenizations on three music analysis tasks, we show that such interval-based tokenizations improve model performances and facilitate their explainability., Comment: Accepted at Artificial Intelligence for Music Workshop at AAAI 2025 (https://ai4musicians.org/2025aaai.html)

Following the first part of our project, this paper comprehensively studies two types of extragradient-based methods: anchored extragradient and Nesterov's accelerated extragradient for solving [non]linear inclusions (and, in particular, equations), primarily under the Lipschitz continuity and the co-hypomonotonicity assumptions. We unify and generalize a class of anchored extragradient methods for monotone inclusions to a wider range of schemes encompassing existing algorithms as special cases. We establish $\mathcal{O}(1/k)$ last-iterate convergence rates on the residual norm of the underlying mapping for this general framework and then specialize it to obtain convergence guarantees for specific instances, where $k$ denotes the iteration counter. We extend our approach to a class of anchored Tseng's forward-backward-forward splitting methods to obtain a broader class of algorithms for solving co-hypomonotone inclusions. Again, we analyze $\mathcal{O}(1/k)$ last-iterate convergence rates for this general scheme and specialize it to obtain convergence results for existing and new variants. We generalize and unify Nesterov's accelerated extra-gradient method to a new class of algorithms that covers existing schemes as special instances while generating new variants. For these schemes, we can prove $\mathcal{O}(1/k)$ last-iterate convergence rates for the residual norm under co-hypomonotonicity, covering a class of nonmonotone problems. We propose another novel class of Nesterov's accelerated extragradient methods to solve inclusions. Interestingly, these algorithms achieve both $\mathcal{O}(1/k)$ and $o(1/k)$ last-iterate convergence rates, and also the convergence of iterate sequences under co-hypomonotonicity and Lipschitz continuity. Finally, we provide a set of numerical experiments encompassing different scenarios to validate our algorithms and theoretical guarantees., Comment: 75 pages, 7 figures, and 1 table

Gait and movement analysis have become a well-established clinical tool for diagnosing health conditions, monitoring disease progression for a wide spectrum of diseases, and to implement and assess treatment, surgery and or rehabilitation interventions. However, quantitative motion assessment remains limited to costly motion capture systems and specialized personnel, restricting its accessibility and broader application. Recent advancements in deep neural networks have enabled quantitative movement analysis using single-camera videos, offering an accessible alternative to conventional motion capture systems. In this paper, we present an efficient approach for clinical gait analysis through a dual-pattern input convolutional Transformer network. The proposed system leverages a dual-input Transformer model to estimate essential gait parameters from single RGB videos captured by a single-view camera. The system demonstrates high accuracy in estimating critical metrics such as the gait deviation index (GDI), knee flexion angle, step length, and walking cadence, validated on a dataset of individuals with movement disorders. Notably, our approach surpasses state-of-the-art methods in various scenarios, using fewer resources and proving highly suitable for clinical application, particularly in resource-constrained environments., Comment: Accepted for presentation at The IEEE International Symposium on Biomedical Imaging (ISBI 2025)

Continuous gravitational waves (CWs) emission from neutron stars carries information about their internal structure and equation of state, and it can provide tests of General Relativity. We present a search for CWs from a set of 45 known pulsars in the first part of the fourth LIGO--Virgo--KAGRA observing run, known as O4a. We conducted a targeted search for each pulsar using three independent analysis methods considering the single-harmonic and the dual-harmonic emission models. We find no evidence of a CW signal in O4a data for both models and set upper limits on the signal amplitude and on the ellipticity, which quantifies the asymmetry in the neutron star mass distribution. For the single-harmonic emission model, 29 targets have the upper limit on the amplitude below the theoretical spin-down limit. The lowest upper limit on the amplitude is $6.4\!\times\!10^{-27}$ for the young energetic pulsar J0537-6910, while the lowest constraint on the ellipticity is $8.8\!\times\!10^{-9}$ for the bright nearby millisecond pulsar J0437-4715. Additionally, for a subset of 16 targets we performed a narrowband search that is more robust regarding the emission model, with no evidence of a signal. We also found no evidence of non-standard polarizations as predicted by the Brans-Dicke theory., Comment: main paper: 12 pages, 6 figures, 4 tables

We propose novel methods for approximate sampling recovery and integration of functions in the Freud-weighted Sobolev space $W^r_{p,w}(\mathbb{R})$ with the approximation error measured in the norm of the Freud-weighted Lebesgue space $L_{q,w}(\mathbb{R})$. Namely, we construct equidistant compact-supported B-spline quasi-interpolation and interpolation sampling algorithms $Q_{\rho,m}$ and $P_{\rho,m}$ which are asymptotically optimal in terms of the sampling $n$-widths $\varrho_n(\boldsymbol{W}^r_{p,w}(\mathbb{R}), L_{q,w}(\mathbb{R}))$ for every pair $p,q \in [1,\infty]$, and prove the right convergence rate of these sampling $n$-widths, where $\boldsymbol{W}^r_{p,w}(\mathbb{R})$ denotes the unit ball in $W^r_{p,w}(\mathbb{R})$. The algorithms $Q_{\rho,m}$ and $P_{\rho,m}$ are based on truncated scaled B-spline quasi-interpolation and interpolation, respectively. We also prove the asymptotical optimality and right convergence rate of the equidistant quadratures generated from $Q_{\rho,m}$ and $P_{\rho,m}$, for Freud-weighted numerical integration of functions in $W^r_{p,w}(\mathbb{R})$.

In this paper, we employ the concept of quasi-relative interior to analyze the method of Lagrange multipliers and establish strong Lagrangian duality for nonsmooth convex optimization problems in Hilbert spaces. Then, we generalize the classical support vector machine (SVM) model by incorporating a new geometric constraint or a regularizer on the separating hyperplane, serving as a regularization mechanism for the SVM. This new SVM model is examined using Lagrangian duality and other convex optimization techniques in both theoretical and numerical aspects via a new subgradient algorithm as well as a primal-dual method.

Integrated sensing and communication (ISAC) has emerged as a pivotal technology for enabling vehicle-to-everything (V2X) connectivity, mobility, and security. However, designing efficient beamforming schemes to achieve accurate sensing and enhance communication performance in the dynamic and uncertain environments of V2X networks presents significant challenges. While AI technologies offer promising solutions, the energy-intensive nature of neural networks (NNs) imposes substantial burdens on communication infrastructures. This work proposes an energy-efficient and intelligent ISAC system for V2X networks. Specifically, we first leverage a Markov Decision Process framework to model the dynamic and uncertain nature of V2X networks. This framework allows the roadside unit (RSU) to develop beamforming schemes relying solely on its current sensing state information, eliminating the need for numerous pilot signals and extensive channel state information acquisition. To endow the system with intelligence and enhance its performance, we then introduce an advanced deep reinforcement learning (DRL) algorithm based on the Actor-Critic framework with a policy-clipping technique, enabling the joint optimization of beamforming and power allocation strategies to guarantee both communication rate and sensing accuracy. Furthermore, to alleviate the energy demands of NNs, we integrate Spiking Neural Networks (SNNs) into the DRL algorithm. By leveraging discrete spikes and their temporal characteristics for information transmission, SNNs not only significantly reduce the energy consumption of deploying AI model in ISAC-assisted V2X networks but also further enhance algorithm performance. Extensive simulation results validate the effectiveness of the proposed scheme with lower energy consumption, superior communication performance, and improved sensing accuracy., Comment: 13 pages, 12 figures

In this paper, we consider an aerial reconfigurable intelligent surface (ARIS)-assisted wireless network, where multiple unmanned aerial vehicles (UAVs) collect data from ground users (GUs) by using the non-orthogonal multiple access (NOMA) method. The ARIS provides enhanced channel controllability to improve the NOMA transmissions and reduce the co-channel interference among UAVs. We also propose a novel dual-mode switching scheme, where each UAV equipped with both an ARIS and a radio frequency (RF) transceiver can adaptively perform passive reflection or active transmission. We aim to maximize the overall network throughput by jointly optimizing the UAVs' trajectory planning and operating modes, the ARIS's passive beamforming, and the GUs' transmission control strategies. We propose an optimization-driven hierarchical deep reinforcement learning (O-HDRL) method to decompose it into a series of subproblems. Specifically, the multi-agent deep deterministic policy gradient (MADDPG) adjusts the UAVs' trajectory planning and mode switching strategies, while the passive beamforming and transmission control strategies are tackled by the optimization methods. Numerical results reveal that the O-HDRL efficiently improves the learning stability and reward performance compared to the benchmark methods. Meanwhile, the dual-mode switching scheme is verified to achieve a higher throughput performance compared to the fixed ARIS scheme.

This paper explores the critical role of data clustering in data science, emphasizing its methodologies, tools, and diverse applications. Traditional techniques, such as partitional and hierarchical clustering, are analyzed alongside advanced approaches such as data stream, density-based, graph-based, and model-based clustering for handling complex structured datasets. The paper highlights key principles underpinning clustering, outlines widely used tools and frameworks, introduces the workflow of clustering in data science, discusses challenges in practical implementation, and examines various applications of clustering. By focusing on these foundations and applications, the discussion underscores clustering's transformative potential. The paper concludes with insights into future research directions, emphasizing clustering's role in driving innovation and enabling data-driven decision-making.

Hard combinatorial optimization problems, often mapped to Ising models, promise potential solutions with quantum advantage but are constrained by limited qubit counts in near-term devices. We present an innovative quantum-inspired framework that dynamically compresses large Ising models to fit available quantum hardware of different sizes. Thus, we aim to bridge the gap between large-scale optimization and current hardware capabilities. Our method leverages a physics-inspired GNN architecture to capture complex interactions in Ising models and accurately predict alignments among neighboring spins (aka qubits) at ground states. By progressively merging such aligned spins, we can reduce the model size while preserving the underlying optimization structure. It also provides a natural trade-off between the solution quality and size reduction, meeting different hardware constraints of quantum computing devices. Extensive numerical studies on Ising instances of diverse topologies show that our method can reduce instance size at multiple levels with virtually no losses in solution quality on the latest D-wave quantum annealers., Comment: Accepted to AAAI'25

Analytic expressions for the absorption coefficient (AC) of a weak electromagnetic wave (EMW) in 2D Graphene under influence of strong laser radiation are calculated using the quantum kinetic equation (QKE) in the case of electron-optical phonon scattering in both the absence and presence of a magnetic field perpendicular to the graphene sheet. The dependence of the AC on the intensity $E_{02}$ and the frequency $\Omega_2$ of a weak EMW, on the intensity $E_{01}$ and the frequency $\Omega_1$ of a strong laser radiation, on the temperature T of the system is obtained. These results are investigated from low temperature to high temperature. These results are obtained from the QKE method, which broke the limit of the Boltzmann kinetic equations (only investigated in the high-temperature domain). Besides, the numerical results show that the AC of a weak EMW in 2D Graphene can have negative values. This demonstrates the possibility of increasing weak EMW by strong laser radiation in 2D Graphene. This is different from a similar problem in bulk semiconductors and the case without strong laser radiation. In the case of the presence of an external magnetic field, the numerical calculation results also show the appearance of the peak spectral lines that obey the magneto-phonon resonance conditions. The appearance of these resonance peaks provides a model illustrating the dependence of the Half-Width at Half Maximum (HWHM) on the external magnetic field. This is an important criterion for the fabrication of graphene-related electronic components and orientation for future experiments.

We use the Profile numerical method to calculate the spectral line width, or half width at half maximum (HWHM) of the absorption peaks of multi-photon absorption processes in a two-dimensional graphene system (2DGS) according to important external parameters such as magnetic field and temperature in the presence of strong electromagnetic waves (SEMW). The appearance of these absorption peaks is theoretically obtained from magneto-phonon resonance conditions within the framework of the quantum kinetic equation. The results take into account both scattering mechanisms: electron-optical phonon and electron-acoustic phonon. Under the influence of the magnetic field, according to the increasing photon energy of the SEMW, the graph showing the dependence of the multi-photon nonlinear absorption coefficient on photon energy has the form of absorption spectrum lines following magneto-phonon resonance conditions. When increasing the value of the external magnetic field and the intensity of the SEMW, the intensity of the resonance peaks increases. In addition, the HWHM W of the resonance peaks of multi-photon absorption processes increases with increasing magnetic field $\mathrm{B}$ according to the square root law $\mathrm{W} = \kappa\sqrt{\mathrm{B}}$ but is independent of temperature. The value of the HWHM of the one-photon absorption process is larger than the value of the HWHM of the multi-photon absorption processes. The calculations of the HWHM of the one-photon absorption process in this paper are consistent with previous experimental observations and theoretical calculations. Thus, our calculations of the HWHM of multi-photon absorption processes can serve as reliable predictions for future experiments.

Expensive multi-objective optimization problems (EMOPs) are common in real-world scenarios where evaluating objective functions is costly and involves extensive computations or physical experiments. Current Pareto set learning methods for such problems often rely on surrogate models like Gaussian processes to approximate the objective functions. These surrogate models can become fragmented, resulting in numerous small uncertain regions between explored solutions. When using acquisition functions such as the Lower Confidence Bound (LCB), these uncertain regions can turn into pseudo-local optima, complicating the search for globally optimal solutions. To address these challenges, we propose a novel approach called SVH-PSL, which integrates Stein Variational Gradient Descent (SVGD) with Hypernetworks for efficient Pareto set learning. Our method addresses the issues of fragmented surrogate models and pseudo-local optima by collectively moving particles in a manner that smooths out the solution space. The particles interact with each other through a kernel function, which helps maintain diversity and encourages the exploration of underexplored regions. This kernel-based interaction prevents particles from clustering around pseudo-local optima and promotes convergence towards globally optimal solutions. Our approach aims to establish robust relationships between trade-off reference vectors and their corresponding true Pareto solutions, overcoming the limitations of existing methods. Through extensive experiments across both synthetic and real-world MOO benchmarks, we demonstrate that SVH-PSL significantly improves the quality of the learned Pareto set, offering a promising solution for expensive multi-objective optimization problems., Comment: Accepted to AAAI-25

Based on the quantum kinetic equation for electrons, we theoretically study the quantum multi-photon non-linear absorption of a strong electromagnetic wave (EMW) in two-dimensional graphene. Two cases of the electron scattering mechanism are considered: Electron-optical phonon scattering and electron-acoustic phonon scattering. The general multi-photon absorption coefficient is presented as a function of the temperature, the external magnetic field, the photon energy and the amplitude of external EMW. These analytical expressions for multi-photon non-linear absorption coefficient (MNAC) are numerically calculated and the results are discussed in both the absence and presence of a magnetic field perpendicular to the graphene sheet. The results show that there is no absorption peak in the absence of the magnetic field, which contrasts with previous results in 2D systems such as quantum wells or superlattices. However, when there is a strong magnetic field along the direction perpendicular to the 2D graphene, absorption spectral lines appear consistent with the magneto-phonon resonance conditions. Our calculations show that the MPA's effect is stronger than mono-photon absorption. Besides, the quantum multi-photon non-linear absorption phenomenon has been studied from low to high temperatures. This transcends the limits of the classical BKE which is studied in the high-temperature domain. The computational results show that the dependence of MNAC on the above quantities is consistent with the previous theoretical investigation. Another novel feature of this work is that the general analytic expression for MNAC shows the Half Width at Half Maximum dependence on the magnetic field which is in good agreement with the previous experimental observations. Thus, our estimation might give a critical prediction for future experimental observations in 2D graphene.

We present a systematic theoretical study of the multi-photon nonlinear optical absorption properties of a $\text{GaAs/A}{{\text{l}}_{x}}\text{G}{{\text{a}}_{1-x}}\text{As}$ based quantum well (QW) structure with Morse confinement potential under the influence of a magnetic field. Based on the stationary states due to the electron confinement in Morse QWs and the Landau levels obtained by solving the Schrodinger equation in the effective mass approximation, we have developed calculations for the optical absorption power with MPA using second-order perturbation theory. Our model accounts for electron-phonon interactions and considers both optical and acoustic phonon mechanisms in the MPA process. Our findings show that the one-photon absorption (1PA) peaks are larger and appear to the right of the two-photon absorption (2PA) peaks, whereas 2PA peaks are larger and occur to the right of three-photon absorption (3PA) peaks. The resonance peak positions follow the magneto-phonon resonance condition and are temperature-independent. Increasing the magnetic field and aluminum concentration induces a blue shift in the absorption spectra, whereas increasing the QW width leads to a red shift. Variations in magnetic field, aluminum concentration, and QW width also affect the peak intensities and full-width at half maximum (FWHM), with increasing values of the former two enhancing the FWHM, while expanding the QW width reduces it. Thermal excitations increase peak intensity without shifting their positions. Our study highlights the significance of nonlinear absorption processes (2PA, 3PA) in understanding optical absorption, despite their smaller FWHM compared to linear absorption (1PA). Overall, the Morse QW model demonstrates promising magneto-optical properties, making it a strong candidate for future optoelectronic device applications., Comment: Micro and Nanostructures

We report on IXPE and NuSTAR observations that began forty days following the onset of the 2024 outburst of the magnetar 1E 1841-045, marking the first ever IXPE observation of a magnetar in an enhanced state. Our spectropolarimetric analysis indicates that a non-thermal double power-law (PL) spectral model can fit the phase-averaged intensity data well, with the soft and hard components dominating below and above around 5 keV, respectively. We find that the soft PL exhibits a polarization degree (PD) of about 20% while the hard X-ray PL displays a PD of about 50%; both components have a polarization angle (PA) compatible with 0 degree. These results are supported through model-independent polarization analysis which shows an increasing PD from about 15% to 70% in the 2-3 keV and 6-8 keV ranges, respectively, while the PA remains consistent with 0 degree. We find marginal evidence for variability in the polarization properties with pulse phase, namely a higher PD at spin phases coinciding with the peak in the hard X-ray pulse. We compare the hard X-ray PL to the expectation from direct resonant inverse Compton scattering (RICS) and secondary pair cascade synchrotron radiation from primary high-energy RICS photons, finding that both can provide reasonable spectropolarimetric agreement with the data, yet, the latter more naturally. Finally, we suggest that the soft power law X-ray component may be emission emanating from a Comptonized corona in the inner magnetosphere., Comment: Submitted to ApJL together with a companion paper by Rigoselli et al. Comments are welcome

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We find that multimodal machine learning applications have overwhelmingly turned to web-crawled, synthetic, and social media platforms, such as YouTube, for their training sets, eclipsing all other sources since 2019. Secondly, tracing the chain of dataset derivations we find that while less than 33% of datasets are restrictively licensed, over 80% of the source content in widely-used text, speech, and video datasets, carry non-commercial restrictions. Finally, counter to the rising number of languages and geographies represented in public AI training datasets, our audit demonstrates measures of relative geographical and multilingual representation have failed to significantly improve their coverage since 2013. We believe the breadth of our audit enables us to empirically examine trends in data sourcing, restrictions, and Western-centricity at an ecosystem-level, and that visibility into these questions are essential to progress in responsible AI. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire multimodal audit, allowing practitioners to trace data provenance across text, speech, and video., Comment: 10 pages, 5 figures (main paper)

This article studies one-generator and two-generator quasi-cyclic codes over finite fields. We present two versions of necessary and sufficient conditions for the symplectic selforthogonality of one-generator quasi-cyclic codes, using both matrix and polynomial approaches. We provide two versions of necessary and sufficient conditions for two-generator quasi-cyclic codes for symplectic self-orthogonality and the symplectic dual-containing condition. Additionally, using these necessary and sufficient conditions, we construct new quantum codes with record-breaking parameters that improve upon current records.

We study the mean-field limit of the 1D bosonic canonical ensemble in a superharmonic trap. This is the regime with temperature proportional to particle number, both diverging to infinity, and correspondingly scaled interactions. We prove that the limit model is a classical field theory based on a non-linear Schr{\"o}dinger-Gibbs measure conditioned on the L2 mass, thereby obtaining a canonical analogue of previous results for the grand-canonical ensemble. We take advantage of this set-up with fixed mass to include focusing/attractive interactions/non-linearities in our study.

This work proposes a novel privacy-preserving cyberattack detection framework for blockchain-based Internet-of-Things (IoT) systems. In our approach, artificial intelligence (AI)-driven detection modules are strategically deployed at blockchain nodes to identify real-time attacks, ensuring high accuracy and minimal delay. To achieve this efficiency, the model training is conducted by a cloud service provider (CSP). Accordingly, blockchain nodes send their data to the CSP for training, but to safeguard privacy, the data is encrypted using homomorphic encryption (HE) before transmission. This encryption method allows the CSP to perform computations directly on encrypted data without the need for decryption, preserving data privacy throughout the learning process. To handle the substantial volume of encrypted data, we introduce an innovative packing algorithm in a Single-Instruction-Multiple-Data (SIMD) manner, enabling efficient training on HE-encrypted data. Building on this, we develop a novel deep neural network training algorithm optimized for encrypted data. We further propose a privacy-preserving distributed learning approach based on the FedAvg algorithm, which parallelizes the training across multiple workers, significantly improving computation time. Upon completion, the CSP distributes the trained model to the blockchain nodes, enabling them to perform real-time, privacy-preserved detection. Our simulation results demonstrate that our proposed method can not only mitigate the training time but also achieve detection accuracy that is approximately identical to the approach without encryption, with a gap of around 0.01%. Additionally, our real implementations on various blockchain consensus algorithms and hardware configurations show that our proposed framework can also be effectively adapted to real-world systems.

Microscale hydrogels comprised of macromolecular networks have increasingly been used for applications involving cell encapsulation, tissue engineering and for the storage and release of active cargo molecules. However, the majority of such microgels are formed from nonbiodegradable synthetic polymers, involving harmful solvents, or using animal proteins, such as silk and gelatin, which can have a negative environmental impact and lack sustainability. Furthermore, most encapsulation techniques involve either protecting hydrophobic or hydrophilic cargo, but rarely both. In order to address these issues, we employed droplet-microfluidics to develop novel, plant protein microcapsules capable of containing both hydrophilic and hydrophobic cargo molecules. The microcapsule structure and cargo release rates were controlled by balancing osmotic pressures between the outer and inner phases of the capsules. Moreover, the digestibility of the microcapsules was comparable with that of pure pea protein, thereby enabling the use of these microcapsules for food and beverage applications. In addition, digestive enzymes can trigger the release of the encapsulated active ingredients, and hence, these microcapsules are well suited for the controlled delivery of active nutraceutical or pharmaceutical ingredients. Finally, we investigated the biodegradability of the microcapsules. It was determined that the plant protein microcapsules exhibited 98.0% biodegradability (as compared with cellulose), thereby fulfilling the biodegradability standards stipulated by the International Organization for Standardization (ISO 14851) for microplastics in freshwater conditions (90%). Hence, the plant protein microcapsules can have numerous applications in the food, nutraceutical, pharmaceutical, cosmetic, personal care, and agriculture industries.

With the advent of portable 360{\deg} cameras, panorama has gained significant attention in applications like virtual reality (VR), virtual tours, robotics, and autonomous driving. As a result, wide-baseline panorama view synthesis has emerged as a vital task, where high resolution, fast inference, and memory efficiency are essential. Nevertheless, existing methods are typically constrained to lower resolutions (512 $\times$ 1024) due to demanding memory and computational requirements. In this paper, we present PanSplat, a generalizable, feed-forward approach that efficiently supports resolution up to 4K (2048 $\times$ 4096). Our approach features a tailored spherical 3D Gaussian pyramid with a Fibonacci lattice arrangement, enhancing image quality while reducing information redundancy. To accommodate the demands of high resolution, we propose a pipeline that integrates a hierarchical spherical cost volume and Gaussian heads with local operations, enabling two-step deferred backpropagation for memory-efficient training on a single A100 GPU. Experiments demonstrate that PanSplat achieves state-of-the-art results with superior efficiency and image quality across both synthetic and real-world datasets. Code will be available at \url{https://github.com/chengzhag/PanSplat}., Comment: Project Page: https://chengzhag.github.io/publication/pansplat/ Code: https://github.com/chengzhag/PanSplat

An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. Compared with other recurrent neural networks, one great advantage of ESN is the simplicity of its training process. Yet, despite the seemingly restricted learnable parameters, ESN has been shown to successfully capture the spatial-temporal dynamics of complex patterns. Here we build an ESN to model the coarsening dynamics of charge-density waves (CDW) in a semi-classical Holstein model, which exhibits a checkerboard electron density modulation at half-filling stabilized by a commensurate lattice distortion. The inputs to the ESN are local CDW order-parameters in a finite neighborhood centered around a given site, while the output is the predicted CDW order of the center site at the next time step. Special care is taken in the design of couplings between hidden layer and input nodes to ensure lattice symmetries are properly incorporated into the ESN model. Since the model predictions depend only on CDW configurations of a finite domain, the ESN is scalable and transferrable in the sense that a model trained on dataset from a small system can be directly applied to dynamical simulations on larger lattices. Our work opens a new avenue for efficient dynamical modeling of pattern formations in functional electron materials., Comment: 13 pages, 8 figures

This paper addresses the inverse scattering problem for Maxwell's equations. We first show that a bianisotropic scatterer can be uniquely determined from multi-static far-field data through the factorization analysis of the far-field operator. Next, we investigate a modified version of the orthogonality sampling method, as proposed in Le [2022 Inverse Problems 38 025007], for the numerical reconstruction of the scatterer. Finally, we apply this sampling method to invert unprocessed 3D experimental data obtained from the Fresnel Institute. Numerical examples with synthetic scattering data for bianisotropic targets are also presented to demonstrate the effectiveness of the method., Comment: 13 pages, 5 figures

Model inference systems are essential for implementing end-to-end data analytics pipelines that deliver the benefits of machine learning models to users. Existing cloud-based model inference systems are costly, not easy to scale, and must be trusted in handling the models and user request data. Serverless computing presents a new opportunity, as it provides elasticity and fine-grained pricing. Our goal is to design a serverless model inference system that protects models and user request data from untrusted cloud providers. It offers high performance and low cost, while requiring no intrusive changes to the current serverless platforms. To realize our goal, we leverage trusted hardware. We identify and address three challenges in using trusted hardware for serverless model inference. These challenges arise from the high-level abstraction of serverless computing, the performance overhead of trusted hardware, and the characteristics of model inference workloads. We present SeSeMI, a secure, efficient, and cost-effective serverless model inference system. It adds three novel features non-intrusively to the existing serverless infrastructure and nothing else.The first feature is a key service that establishes secure channels between the user and the serverless instances, which also provides access control to models and users' data. The second is an enclave runtime that allows one enclave to process multiple concurrent requests. The final feature is a model packer that allows multiple models to be executed by one serverless instance. We build SeSeMI on top of Apache OpenWhisk, and conduct extensive experiments with three popular machine learning models. The results show that SeSeMI achieves low latency and low cost at scale for realistic workloads.

In the evolving landscape of customer service within the digital economy, traditional methods of service quality assessment have shown significant limitations, this research proposes a novel deep-learning approach to service quality assessment, focusing on the Vietnamese service sector. By leveraging a multi-modal pipeline that transcends traditional evaluation methods, the research addresses the limitations of conventional assessments by analyzing speech, speaker interactions and emotional content, offering a more comprehensive and objective means of understanding customer service interactions. This aims to provide organizations with a sophisticated tool for evaluating and improving service quality in the digital economy., Comment: I am writing to request the withdrawal of my preprint due to the discovery of significant inaccuracies in the results. These errors could mislead future research and applications, which compromises the integrity of my work. I believe withdrawing the paper is essential to uphold scientific standards and prevent the dissemination of misleading information. Thank you for your understanding

Major depressive disorder is a prevalent and serious mental health condition that negatively impacts your emotions, thoughts, actions, and overall perception of the world. It is complicated to determine whether a person is depressed due to the symptoms of depression not apparent. However, their voice can be one of the factor from which we can acknowledge signs of depression. People who are depressed express discomfort, sadness and they may speak slowly, trembly, and lose emotion in their voices. In this study, we proposed the Dynamic Convolutional Block Attention Module (Dynamic-CBAM) to utilized with in an Attention-GRU Network to classify the emotions by analyzing the audio signal of humans. Based on the results, we can diagnose which patients are depressed or prone to depression then so that treatment and prevention can be started as soon as possible. The research delves into the intricate computational steps involved in implementing a Attention-GRU deep learning architecture. Through experimentation, the model has achieved an impressive recognition with Unweighted Accuracy (UA) rate of 0.87 and 0.86 Weighted Accuracy (WA) rate and F1 rate of 0.87 in the VNEMOS dataset. Training code is released in https://github.com/fiyud/Emotional-Vietnamese-Speech-Based-Depression-Diagnosis-Using-Dynamic-Attention-Mechanism, Comment: 9 Page, 5 Figures

Physics-based dynamic models (PBDMs) are simplified representations of complex dynamical systems. PBDMs take specific processes within a complex system and assign a fragment of variables and an accompanying set of parameters to depict the processes. As this often leads to suboptimal parameterisation of the system, a key challenge requires refining the empirical parameters and variables to reduce uncertainties while maintaining the model s explainability and enhancing its predictive accuracy. We demonstrate that a hybrid mosquito population dynamics model, which integrates a PBDM with Physics-Informed Neural Networks (PINN), retains the explainability of the PBDM by incorporating the PINN-learned model parameters in place of its empirical counterparts. Specifically, we address the limitations of traditional PBDMs by modelling the parameters of larva and pupa development rates using a PINN that encodes complex, learned interactions of air temperature, precipitation and humidity. Our results demonstrate improved mosquito population simulations including the difficult-to-predict mosquito population peaks. This opens the possibility of hybridisation concept application on other complex systems based on PBDMs such as cancer growth to address the challenges posed by scarce and noisy data, and to numerical weather prediction and climate modelling to overcome the gap between physics-based and data-driven weather prediction models.

Network slicing is a critical feature in 5G and beyond communication systems, enabling the creation of multiple virtual networks (i.e., slices) on a shared physical network infrastructure. This involves efficiently mapping each slice component, including virtual network functions (VNFs) and their interconnections (virtual links), onto the physical network. This paper considers slice embedding problem in which the order of VNFs can be adjusted, providing increased flexibility for service deployment on the infrastructure. This also complicates embedding, as the best order has to be selected. We propose an innovative optimization framework to tackle the challenges of jointly optimizing slice admission control and embedding with flexible VNF ordering. Additionally, we introduce a near-optimal branch-and-bound (BnB) algorithm, combined with the A* search algorithm, to generate embedding solutions efficiently. Extensive simulations on both small and large-scale scenarios demonstrate that flexible VNF ordering significantly increases the number of deployable slices within the network infrastructure, thereby improving resource utilization and meeting diverse demands across varied network topologies., Comment: Submitted to IEEE Transactions on Network and Service Management

Autonomous vehicles (AVs) have demonstrated significant potential in revolutionizing transportation, yet ensuring their safety and reliability remains a critical challenge, especially when exposed to dynamic and unpredictable environments. Real-world testing of an Autonomous Driving System (ADS) is both expensive and risky, making simulation-based testing a preferred approach. In this paper, we propose AVASTRA, a Reinforcement Learning (RL)-based approach to generate realistic critical scenarios for testing ADSs in simulation environments. To capture the complexity of driving scenarios, AVASTRA comprehensively represents the environment by both the internal states of an ADS under-test (e.g., the status of the ADS's core components, speed, or acceleration) and the external states of the surrounding factors in the simulation environment (e.g., weather, traffic flow, or road condition). AVASTRA trains the RL agent to effectively configure the simulation environment that places the AV in dangerous situations and potentially leads it to collisions. We introduce a diverse set of actions that allows the RL agent to systematically configure both environmental conditions and traffic participants. Additionally, based on established safety requirements, we enforce heuristic constraints to ensure the realism and relevance of the generated test scenarios. AVASTRA is evaluated on two popular simulation maps with four different road configurations. Our results show AVASTRA's ability to outperform the state-of-the-art approach by generating 30% to 115% more collision scenarios. Compared to the baseline based on Random Search, AVASTRA achieves up to 275% better performance. These results highlight the effectiveness of AVASTRA in enhancing the safety testing of AVs through realistic comprehensive critical scenario generation.