Search

The challenge in reconfigurable manipulation of sound waves using metasurfaces lies in achieving precise control over acoustic behavior while developing efficient and practical tuning methods for structural configurations. However, most studies on reconfigurable acoustic metasurfaces rely on cumbersome and time-consuming control systems. These approaches often struggle with fabrication techniques, as conventional methods face limitations such as restricted material choices, challenges in achieving complex geometries, and difficulties in incorporating flexible components. This paper proposes a novel approach for developing a reconfigurable metasurface inspired by the Kresling origami pattern, designed for programmable manipulation of acoustic waves at an operating frequency of 2000 Hz. The origami unit cell is fabricated using multi-material 3D printing technology, allowing for the simultaneous printing of two materials with different mechanical properties, thus creating a bistable origami-based structure. Through optimization, two equilibrium states achieve a reflection phase difference of {\pi} through the application of small axial force, F, or torque, T. Various configurations of the metasurface, generated from different combinations of these two equilibria, enable distinct reflective behaviors with switchable and programmable functionalities. The principle of this work simplifies the shaping of acoustic waves through a straightforward mechanical mechanism, eliminating the need for complex control systems and time-consuming adjustments. This innovative approach paves a novel and effective perspective for developing on-demand switchable and tunable devices across diverse fields, including electromagnetics, mechanics, and elastics, leveraging multi-material printing technology.

This paper presents a comprehensive analysis of the well-known extragradient (EG) method for solving both equations and inclusions. First, we unify and generalize EG for [non]linear equations to a wider class of algorithms, encompassing various existing schemes and potentially new variants. Next, we analyze both sublinear ``best-iterate'' and ``last-iterate'' convergence rates for the entire class of algorithms, and derive new convergence results for two well-known instances. Second, we extend our EG framework above to ``monotone'' inclusions, introducing a new class of algorithms and its corresponding convergence results. Third, we also unify and generalize Tseng's forward-backward-forward splitting (FBFS) method to a broader class of algorithms to solve [non]linear inclusions when a weak-Minty solution exists, and establish its ``best-iterate'' convergence rate. Fourth, to complete our picture, we also investigate sublinear rates of two other common variants of EG using our EG analysis framework developed here: the reflected forward-backward splitting and the golden ratio methods. Finally, we conduct an extensive numerical experiment to validate our theoretical findings. Our results demonstrate that several new variants of our proposed algorithms outperform existing schemes in the majority of examples., Comment: 59 pages, 1 table, 9 figures. arXiv admin note: text overlap with arXiv:2303.17192

Code completion is essential in software development, helping developers by predicting code snippets based on context. Among completion tasks, Method Body Completion (MBC) is particularly challenging as it involves generating complete method bodies based on their signatures and context. This task becomes significantly harder in large repositories, where method bodies must integrate repositoryspecific elements such as custom APIs, inter-module dependencies, and project-specific conventions. In this paper, we introduce RAMBO, a novel RAG-based approach for repository-level MBC. Instead of retrieving similar method bodies, RAMBO identifies essential repository-specific elements, such as classes, methods, and variables/fields, and their relevant usages. By incorporating these elements and their relevant usages into the code generation process, RAMBO ensures more accurate and contextually relevant method bodies. Our experimental results with leading code LLMs across 40 Java projects show that RAMBO significantly outperformed the state-of-the-art repository-level MBC approaches, with the improvements of up to 46% in BLEU, 57% in CodeBLEU, 36% in Compilation Rate, and up to 3X in Exact Match. Notably, RAMBO surpassed RepoCoder Oracle method by up to 12% in Exact Match, setting a new benchmark for repository-level MBC.

Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences. Our work introduces a novel problem setting focusing on these moments as turning points (TPs), accompanied by a meticulously curated, high-consensus, human-annotated multi-modal dataset. We provide precise timestamps, descriptions, and visual-textual evidence high-lighting changes in emotions, behaviors, perspectives, and decisions at these turning points. We also propose a framework, TPMaven, utilizing state-of-the-art vision-language models to construct a narrative from the videos and large language models to classify and detect turning points in our multi-modal dataset. Evaluation results show that TPMaven achieves an F1-score of 0.88 in classification and 0.61 in detection, with additional explanations aligning with human expectations., Comment: Accepted by ACL 2024 main conference

Western music is often characterized by a homophonic texture, in which the musical content can be organized into a melody and an accompaniment. In orchestral music, in particular, the composer can select specific characteristics for each instrument's part within the accompaniment, while also needing to adapt the melody to suit the capabilities of the instruments performing it. In this work, we propose METEOR, a model for Melody-aware Texture-controllable Orchestral music generation. This model performs symbolic multi-track music style transfer with a focus on melodic fidelity. We allow bar- and track-level controllability of the accompaniment with various textural attributes while keeping a homophonic texture. We show that the model can achieve controllability performances similar to strong baselines while greatly improve melodic fidelity., Comment: https://dinhviettoanle.github.io/meteor

Energy efficiency of buildings is considered to be one of the major means of achieving the net-zero carbon goal around the world. The big part of the energy savings are supposed to be coming from optimizing the operation of the building heating, ventilation, and air conditioning (HVAC) systems. There is a natural trade-off between the energy efficiency and the indoor comfort level, and finding an optimal operating schedule/regime requires knowing the occupancy of different spaces inside of the building. Moreover, the COVID-19 pandemic has also revealed the need to sustain the high quality of the indoor air in order to reduce the risk of spread of infection. Occupancy detection from indoor sensors is thus an important practical problem. In the present paper, we propose detection of occupancy based on the carbon dioxide measurements inside the building. In particular, a new approach based on the, so-called, switching auto-regressive process with Markov regime is presented and justified by the physical model of the carbon dioxide concentration dynamics. We demonstrate the efficiency of the method compared to simple Hidden Markov approaches on simulated and real-life data. We also show that the model is flexible and can be generalized to account for different ventilation regimes, simultaneously detecting the occupancy and the ventilation rate., Comment: Submitted to Control Systems Letters/American Control Conference

Pain is a more intuitive and user-friendly way of communicating problems, making it especially useful in rehabilitation nurse training robots. While most previous methods have focused on classifying or recognizing pain expressions, these approaches often result in unnatural, jiggling robot faces. We introduce PainDiffusion, a model that generates facial expressions in response to pain stimuli, with controllable pain expressiveness and emotion status. PainDiffusion leverages diffusion forcing to roll out predictions over arbitrary lengths using a conditioned temporal U-Net. It operates as a latent diffusion model within EMOCA's facial expression latent space, ensuring a compact data representation and quick rendering time. For training data, we process the BioVid Heatpain Database, extracting expression codes and subject identity configurations. We also propose a novel set of metrics to evaluate pain expressions, focusing on expressiveness, diversity, and the appropriateness of model-generated outputs. Finally, we demonstrate that PainDiffusion outperforms the autoregressive method, both qualitatively and quantitatively. Code, videos, and further analysis are available at: \href{https://damtien444.github.io/paindf/}{https://damtien444.github.io/paindf/}., Comment: Under reviewing

This paper is devoted to studying the well-posedness, (conditional) conservation of magnetic helicity, inviscid limit and asymptotic stability of the generalized Navier-Stokes-Maxwell equations (NSM) under the Hall effect in two and three dimensions. More precisely, in the viscous case we prove the global well-posedness of NSM for small initial data, which allows us to establish a connection with either the Hall-magnetohydrodynamics (H-MHD) system as the speed of light tends to infinity or NSM without the Hall coefficient as this constant goes to zero. In addition, in the inviscid case the local well-posedness of NSM is also obtained for possibly large initial data. Moreover, under suitable conditions on the initial data and additional assumptions of solutions to NSM in three dimensions, the magnetic helicity is conserved as the electric conductivity goes to infinity. It is different to the case of the fractional H-MHD with critical fractional Laplacian exponents for both the velocity and magnetic fields, where the conservation of magnetic helicity can be provided for smooth initial data without any further conditions on the solution. Furthermore, the asymptotic stability of NSM around a constant magnetic field is established in the case of having a velocity damping term., Comment: arXiv admin note: text overlap with arXiv:2401.14839

The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as synthetic speech has become indistinguishable from natural human speech. Several speech-generation programs are utilized for malicious purposes, especially impersonating individuals through phone calls. Therefore, detecting fake audio is crucial to maintain social security and safeguard the integrity of information. Recent research has proposed a D-CAPTCHA system based on the challenge-response protocol to differentiate fake phone calls from real ones. In this work, we study the resilience of this system and introduce a more robust version, D-CAPTCHA++, to defend against fake calls. Specifically, we first expose the vulnerability of the D-CAPTCHA system under transferable imperceptible adversarial attack. Secondly, we mitigate such vulnerability by improving the robustness of the system by using adversarial training in D-CAPTCHA deepfake detectors and task classifiers., Comment: 14 pages

We completely determine the asymptotic depth, equivalently, the asymptotic projective dimension of a chain of edge ideals that is invariant under the action of the monoid Inc of increasing functions on the positive integers. Our results and their proofs also reveal surprising combinatorial and topological properties of corresponding graphs and their independence complexes. In particular, we are able to determine the asymptotic behavior of all reduced homology groups of these independence complexes., Comment: 33 pages

Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within the vision-language domain. Our dataset comprises 530,694 quadruples, i.e., source image, original caption, negative sentence, and target image in total, including 495,694 queries for training and 35,000 queries for benchmarking across multiple vision-language tasks. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and MagicBrush, to generate the target image and a negative clause that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP to remove erroneous samples. Additionally, we introduce an evaluation protocol for negation understanding of image editing models. Extensive experiments using our dataset across multiple VLMs for instruction-based image editing tasks demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries. The project page is: https://tanbuinhat.github.io/NeIn/

We proved convergence rates of linear sampling recovery by extended least squares methods of functions in Bochner space satisfying some $\ell_2$-summability of their generalized polynomial chaos expansion coefficients. As applications we derive convergence rates of linear collocation approximation of solutions to parametric elliptic PDEs with random inputs, and of infinite dimensional holomorphic functions. These convergence rates significantly improve the known results.

Time series data from various domains are increasing continuously. Extracting and analyzing the temporal patterns in these series can reveal significant insights. Temporal pattern mining (TPM) extends traditional pattern mining by incorporating event time intervals into extracted patterns, enhancing their expressiveness but increasing time and space complexities. One valuable type of temporal pattern is known as rare temporal patterns (RTPs), which occur rarely but with high confidence. There exist several challenges when mining rare temporal patterns. The support measure is set very low, leading to a further combinatorial explosion and potentially producing too many uninteresting patterns. Thus, an efficient approach to rare temporal pattern mining is needed. This paper introduces our Rare Temporal Pattern Mining from Time Series (RTPMfTS) method for discovering rare temporal patterns, featuring the following key contributions: (1) An end-to-end RTPMfTS process that takes time series data as input and yields rare temporal patterns as output. (2) An efficient Rare Temporal Pattern Mining (RTPM) algorithm that uses optimized data structures for quick event and pattern retrieval and utilizes effective pruning techniques for much faster mining. (3) A thorough experimental evaluation of RTPM, showing that RTPM outperforms the baseline in terms of runtime and memory usage., Comment: arXiv admin note: substantial text overlap with arXiv:2306.10994

This paper presents a novel Collaborative Cyberattack Detection (CCD) system aimed at enhancing the security of blockchain-based data-sharing networks by addressing the complex challenges associated with noise addition in federated learning models. Leveraging the theoretical principles of differential privacy, our approach strategically integrates noise into trained sub-models before reconstructing the global model through transmission. We systematically explore the effects of various noise types, i.e., Gaussian, Laplace, and Moment Accountant, on key performance metrics, including attack detection accuracy, deep learning model convergence time, and the overall runtime of global model generation. Our findings reveal the intricate trade-offs between ensuring data privacy and maintaining system performance, offering valuable insights into optimizing these parameters for diverse CCD environments. Through extensive simulations, we provide actionable recommendations for achieving an optimal balance between data protection and system efficiency, contributing to the advancement of secure and reliable blockchain networks., Comment: 13 pages

In this paper, our main goal is to achieve the high-order asymptotic expansion of solutions to $\sigma$-evolution equations with different damping types in the $L^2$ framework. Throughout this, we observe the influence of parabolic like models corresponding to $\sigma_1 \in [0, \sigma/2)$ and $\sigma$-evolution like models corresponding to $\sigma_2 \in (\sigma/2, \sigma]$ on the asymptotic behavior of solutions., Comment: 17 pages

To protect patient safety, modern pharmaceutical complexity demands strict prescription verification. We offer a new approach - Rx Strategist - that makes use of knowledge graphs and different search strategies to enhance the power of Large Language Models (LLMs) inside an agentic framework. This multifaceted technique allows for a multi-stage LLM pipeline and reliable information retrieval from a custom-built active ingredient database. Different facets of prescription verification, such as indication, dose, and possible drug interactions, are covered in each stage of the pipeline. We alleviate the drawbacks of monolithic LLM techniques by spreading reasoning over these stages, improving correctness and reliability while reducing memory demands. Our findings demonstrate that Rx Strategist surpasses many current LLMs, achieving performance comparable to that of a highly experienced clinical pharmacist. In the complicated world of modern medications, this combination of LLMs with organized knowledge and sophisticated search methods presents a viable avenue for reducing prescription errors and enhancing patient outcomes., Comment: 17 Pages, 6 Figures, Under Review

In this article, we propose the R2GQA system, a Retriever-Reader-Generator Question Answering system, consisting of three main components: Document Retriever, Machine Reader, and Answer Generator. The Retriever module employs advanced information retrieval techniques to extract the context of articles from a dataset of legal regulation documents. The Machine Reader module utilizes state-of-the-art natural language understanding algorithms to comprehend the retrieved documents and extract answers. Finally, the Generator module synthesizes the extracted answers into concise and informative responses to questions of students regarding legal regulations. Furthermore, we built the ViRHE4QA dataset in the domain of university training regulations, comprising 9,758 question-answer pairs with a rigorous construction process. This is the first Vietnamese dataset in the higher regulations domain with various types of answers, both extractive and abstractive. In addition, the R2GQA system is the first system to offer abstractive answers in Vietnamese. This paper discusses the design and implementation of each module within the R2GQA system on the ViRHE4QA dataset, highlighting their functionalities and interactions. Furthermore, we present experimental results demonstrating the effectiveness and utility of the proposed system in supporting the comprehension of students of legal regulations in higher education settings. In general, the R2GQA system and the ViRHE4QA dataset promise to contribute significantly to related research and help students navigate complex legal documents and regulations, empowering them to make informed decisions and adhere to institutional policies effectively. Our dataset is available for research purposes.

While Multi-Object Tracking (MOT) has made substantial advancements, it is limited by heavy reliance on prior knowledge and limited to predefined categories. In contrast, Generic Multiple Object Tracking (GMOT), tracking multiple objects with similar appearance, requires less prior information about the targets but faces challenges with variants like viewpoint, lighting, occlusion, and resolution. Our contributions commence with the introduction of the \textbf{\text{Refer-GMOT dataset}} a collection of videos, each accompanied by fine-grained textual descriptions of their attributes. Subsequently, we introduce a novel text prompt-based open-vocabulary GMOT framework, called \textbf{\text{TP-GMOT}}, which can track never-seen object categories with zero training examples. Within \text{TP-GMOT} framework, we introduce two novel components: (i) {\textbf{\text{TP-OD}}, an object detection by a textual prompt}, for accurately detecting unseen objects with specific characteristics. (ii) Motion-Appearance Cost SORT \textbf{\text{MAC-SORT}}, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking multiple generic objects with high similarity. Our contributions are benchmarked on the \text{Refer-GMOT} dataset for GMOT task. Additionally, to assess the generalizability of the proposed \text{TP-GMOT} framework and the effectiveness of \text{MAC-SORT} tracker, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models will be publicly available at: https://fsoft-aic.github.io/TP-GMOT

Black-box large language models (LLMs) are increasingly deployed in various environments, making it essential for these models to effectively convey their confidence and uncertainty, especially in high-stakes settings. However, these models often exhibit overconfidence, leading to potential risks and misjudgments. Existing techniques for eliciting and calibrating LLM confidence have primarily focused on general reasoning datasets, yielding only modest improvements. Accurate calibration is crucial for informed decision-making and preventing adverse outcomes but remains challenging due to the complexity and variability of tasks these models perform. In this work, we investigate the miscalibration behavior of black-box LLMs within the healthcare setting. We propose a novel method, \textit{Atypical Presentations Recalibration}, which leverages atypical presentations to adjust the model's confidence estimates. Our approach significantly improves calibration, reducing calibration errors by approximately 60\% on three medical question answering datasets and outperforming existing methods such as vanilla verbalized confidence, CoT verbalized confidence and others. Additionally, we provide an in-depth analysis of the role of atypicality within the recalibration framework.

In two-dimensional space, we consider a system of $N$ anyons interacts via a short range attractive two-body interaction. In the stable regime, we derive the average-field Pauli functional as the mean-field limit of many-body quantum mechanics. Furthermore, we investigate the collapse phenomenon in the collapse regime where the strength of attractions tends to a critical value (defined by the cubic NLS equation) while simultaneously considering the weak field regime where the strength of the self-generated magnetic field tends to zero.

The clustering of categorical data is a common and important task in computer science, offering profound implications across a spectrum of applications. Unlike purely numerical data, categorical data often lack inherent ordering as in nominal data, or have varying levels of order as in ordinal data, thus requiring specialized methodologies for efficient organization and analysis. This review provides a comprehensive synthesis of categorical data clustering in the past twenty-five years, starting from the introduction of K-modes. It elucidates the pivotal role of categorical data clustering in diverse fields such as health sciences, natural sciences, social sciences, education, engineering and economics. Practical comparisons are conducted for algorithms having public implementations, highlighting distinguishing clustering methodologies and revealing the performance of recent algorithms on several benchmark categorical datasets. Finally, challenges and opportunities in the field are discussed.

Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional Neural Networks (CNNs) and Transformers in Natural Language Processing and general sequence modeling. Various attempts have been made to adapt Mamba to Computer Vision tasks, including medical image segmentation (MIS). Vision Mamba (VM)-based networks are particularly attractive due to their ability to achieve global receptive fields, similar to Vision Transformers, while also maintaining linear complexity in the number of tokens. However, the existing VM models still struggle to maintain both spatially local and global dependencies of tokens in high dimensional arrays due to their sequential nature. Employing multiple and/or complicated scanning strategies is computationally costly, which hinders applications of SSMs to high-dimensional 2D and 3D images that are common in MIS problems. In this work, we propose Local-Global Vision Mamba, LoG-VMamba, that explicitly enforces spatially adjacent tokens to remain nearby on the channel axis, and retains the global context in a compressed form. Our method allows the SSMs to access the local and global contexts even before reaching the last token while requiring only a simple scanning strategy. Our segmentation models are computationally efficient and substantially outperform both CNN and Transformers-based baselines on a diverse set of 2D and 3D MIS tasks. The implementation of LoG-VMamba is available at \url{https://github.com/Oulu-IMEDS/LoG-VMamba}., Comment: 20 pages

The ability to estimate 3D movements of users over edge computing-enabled networks, such as 5G/6G networks, is a key enabler for the new era of extended reality (XR) and Metaverse applications. Recent advancements in deep learning have shown advantages over optimization techniques for estimating 3D human poses given spare measurements from sensor signals, i.e., inertial measurement unit (IMU) sensors attached to the XR devices. However, the existing works lack applicability to wireless systems, where transmitting the IMU signals over noisy wireless networks poses significant challenges. Furthermore, the potential redundancy of the IMU signals has not been considered, resulting in highly redundant transmissions. In this work, we propose a novel approach for redundancy removal and lightweight transmission of IMU signals over noisy wireless environments. Our approach utilizes a random Gaussian matrix to transform the original signal into a lower-dimensional space. By leveraging the compressive sensing theory, we have proved that the designed Gaussian matrix can project the signal into a lower-dimensional space and preserve the Set-Restricted Eigenvalue condition, subject to a power transmission constraint. Furthermore, we develop a deep generative model at the receiver to recover the original IMU signals from noisy compressed data, thus enabling the creation of 3D human body movements at the receiver for XR and Metaverse applications. Simulation results on a real-world IMU dataset show that our framework can achieve highly accurate 3D human poses of the user using only $82\%$ of the measurements from the original signals. This is comparable to an optimization-based approach, i.e., Lasso, but is an order of magnitude faster.

Enforcing guidance throughout the entire sampling process often proves counterproductive due to the model-fitting issue., where samples are generated to match the classifier's parameters rather than generalizing the expected condition. This work identifies and quantifies the problem, demonstrating that reducing or excluding guidance at numerous timesteps can mitigate this issue. By distributing the guidance densely in the early stages of the process, we observe a significant improvement in image quality and diversity while also reducing the required guidance timesteps by nearly 40%. This approach addresses a major challenge in applying guidance effectively to generative tasks. Consequently, our proposed method, termed Compress Guidance, allows for the exclusion of a substantial number of guidance timesteps while still surpassing baseline models in image quality. We validate our approach through benchmarks on label conditional and text-to-image generative tasks across various datasets and models., Comment: 10 pages, 5 figures, Computer Vision and Machine Learning

Network energy saving has received great attention from operators and vendors to reduce energy consumption and CO2 emissions to the environment as well as significantly reduce costs for mobile network operators. However, the design of energy-saving networks also needs to ensure the mobile users' (MUs) QoS requirements such as throughput requirements (TR). This work considers a mobile cellular network including many ground base stations (GBSs), and some GBSs are intentionally turned off due to network energy saving (NES) or crash, so the MUs located in these outage GBSs are not served in time. Based on this observation, we propose the problem of maximizing the total achievable throughput in the network by optimizing the GBSs' antenna tilt and adaptive transmission power with a given number of served MUs satisfied. Notice that, the MU is considered successfully served if its Reference Signal Received Power (RSRP) and throughput requirement are satisfied. The formulated optimization problem becomes difficult to solve with multiple binary variables and non-convex constraints along with random throughput requirements and random placement of MUs. We propose a Deep Q-learning-based algorithm to help the network learn the uncertainty and dynamics of the transmission environment. Extensive simulation results show that our proposed algorithm achieves much better performance than the benchmark schemes., Comment: 7 pages, 4 figures

Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.

This paper presents a fast and robust numerical method for reconstructing point-like sources in the time-harmonic Maxwell's equations given Cauchy data at a fixed frequency. This is an electromagnetic inverse source problem with broad applications, such as antenna synthesis and design, medical imaging, and pollution source tracing. We introduce new imaging functions and a computational algorithm to determine the number of point sources, their locations, and associated moment vectors, even when these vectors have notably different magnitudes. The number of sources and locations are estimated using significant peaks of the imaging functions, and the moment vectors are computed via explicitly simple formulas. The theoretical analysis and stability of the imaging functions are investigated, where the main challenge lies in analyzing the behavior of the dot products between the columns of the imaginary part of the Green's tensor and the unknown moment vectors. Additionally, we extend our method to reconstruct small-volume sources using an asymptotic expansion of their radiated electric field. We provide numerical examples in three dimensions to demonstrate the performance of our method., Comment: 23 pages

Interdisciplinary collaboration is crucial for addressing complex scientific challenges. Recent advancements in large language models (LLMs) have shown significant potential in benefiting researchers across various fields. To explore the application of LLMs in scientific disciplines and their implications for interdisciplinary collaboration, we collect and analyze 50,391 papers from OpenAlex, an open-source platform for scholarly metadata. We first employ Shannon entropy to assess the diversity of collaboration in terms of authors' institutions and departments. Our results reveal that most fields have exhibited varying degrees of increased entropy following the release of ChatGPT, with Computer Science displaying a consistent increase. Other fields such as Social Science, Decision Science, Psychology, Engineering, Health Professions, and Business, Management & Accounting have shown minor to significant increases in entropy in 2024 compared to 2023. Statistical testing further indicates that the entropy in Computer Science, Decision Science, and Engineering is significantly lower than that in health-related fields like Medicine and Biochemistry, Genetics & Molecular Biology. In addition, our network analysis based on authors' affiliation information highlights the prominence of Computer Science, Medicine, and other Computer Science-related departments in LLM research. Regarding authors' institutions, our analysis reveals that entities such as Stanford University, Harvard University, University College London, and Google are key players, either dominating centrality measures or playing crucial roles in connecting research networks. Overall, this study provides valuable insights into the current landscape and evolving dynamics of collaboration networks in LLM research.

Laser-plasma accelerators represent a promising technology for future compact accelerating systems, enabling the acceleration of tens of pC to above $1\,$GeV over just a few centimeters. Nonetheless, these devices currently lack the stability, beam quality and average current of conventional systems. While many efforts have focused on improving acceleration stability and quality, little progress has been made in increasing the beam's average current, which is essential for future laser-plasma-based applications. In this paper, we investigate a laser-plasma acceleration regime aimed at increasing the beam average current with energies up to few-MeVs, efficiently enhancing the beam charge. We present experimental results on configurations that allow reaching charges of $5-30\,$nC and a maximum conversion efficiency of around $14\,$%. Through comprehensive Particle-In-Cell simulations, we interpret the experimental results and present a detailed study on electron dynamics. From our analysis, we show that most electrons are not trapped in a plasma wave; rather, they experience ponderomotive acceleration. Thus, we prove the laser pulse as the main driver of the particles' energy gain process.

We study linear polynomial approximation of functions in weighted Sobolev spaces $W^r_{p,w}(\mathbb{R}^d)$ of mixed smoothness $r \in \mathbb{N}$, and their optimality in terms of Kolmogorov and linear $n$-widths of the unit ball $\boldsymbol{W}^r_{p,w}(\mathbb{R}^d)$ in these spaces. The approximation error is measured by the norm of the weighted Lebesgue space $L_{q,w}(\mathbb{R}^d)$. The weight $w$ is a tensor-product Freud weight. For $1\le p,q \le \infty$ and $d=1$, we prove that the polynomial approximation by de la Vall\'ee Poussin sums of the orthonormal polynomial expansion of functions with respect to the weight $w^2$, is asymptotically optimal in terms of relevant linear $n$-widths $\lambda_n\big(\boldsymbol{W}^r_{p,w}(\mathbb{R}, L_{q,w}(\mathbb{R})\big)$ and Kolmogorov $n$-widths $d_n\big(\boldsymbol{W}^r_{p,w}(\mathbb{R}), L_{q,w}(\mathbb{R})\big)$ for $1\le q \le p <\infty$. For $1\le p,q \le \infty$ and $d\ge 2$, we construct linear methods of hyperbolic cross polynomial approximation based on tensor product of successive differences of dyadic-scaled de la Vall\'ee Poussin sums, which are counterparts of hyperbolic cross trigonometric linear polynomial approximation, and give some upper bounds of the error of these approximations for various pair $p,q$ with $1 \le p, q \le \infty$. For some particular weights $w$ and $d \ge 2$, we prove the right convergence rate of $\lambda_n\big(\boldsymbol{W}^r_{2,w}(\mathbb{R}^d), L_{2,w}(\mathbb{R}^d)\big)$ and $d_n\big(\boldsymbol{W}^r_{2,w}(\mathbb{R}^d), L_{2,w}(\mathbb{R}^d)\big)$ which is performed by a constructive hyperbolic cross polynomial approximation.

This paper aims to propose a novel framework to address the data privacy issue for Federated Learning (FL)-based Intrusion Detection Systems (IDSs) in Internet-of-Vehicles(IoVs) with limited computational resources. In particular, in conventional FL systems, it is usually assumed that the computing nodes have sufficient computational resources to process the training tasks. However, in practical IoV systems, vehicles usually have limited computational resources to process intensive training tasks, compromising the effectiveness of deploying FL in IDSs. While offloading data from vehicles to the cloud can mitigate this issue, it introduces significant privacy concerns for vehicle users (VUs). To resolve this issue, we first propose a highly-effective framework using homomorphic encryption to secure data that requires offloading to a centralized server for processing. Furthermore, we develop an effective training algorithm tailored to handle the challenges of FL-based systems with encrypted data. This algorithm allows the centralized server to directly compute on quantum-secure encrypted ciphertexts without needing decryption. This approach not only safeguards data privacy during the offloading process from VUs to the centralized server but also enhances the efficiency of utilizing FL for IDSs in IoV systems. Our simulation results show that our proposed approach can achieve a performance that is as close to that of the solution without encryption, with a gap of less than 0.8%.

Resilience is defined as the ability of a network to resist, adapt, and quickly recover from disruptions, and to continue to maintain an acceptable level of services from users' perspective. With the advent of future radio networks, including advanced 5G and upcoming 6G, critical services become integral to future networks, requiring uninterrupted service delivery for end users. Unfortunately, with the growing network complexity, user mobility and diversity, it becomes challenging to scale current resilience management techniques that rely on local optimizations to large dense network deployments. This paper aims to address this problem by globally optimizing the resilience of a dense multi-cell network based on multi-agent deep reinforcement learning. Specifically, our proposed solution can dynamically tilt cell antennas and reconfigure transmit power to mitigate outages and increase both coverage and service availability. A multi-objective optimization problem is formulated to simultaneously satisfy resiliency constraints while maximizing the service quality in the network area in order to minimize the impact of outages on neighbouring cells. Extensive simulations then demonstrate that with our proposed solution, the average service availability in terms of user throughput can be increased by up to 50-60% on average, while reaching a coverage availability of 99% in best cases.

This paper presents our proposed approach to the Discharge Me! shared task, collocated with the 23th Workshop on Biomedical Natural Language Processing (BioNLP). In this work, we develop an LLM-based framework for solving the Discharge Summary Documentation (DSD) task, i.e., generating the two critical target sections `Brief Hospital Course' and `Discharge Instructions' in the discharge summary. By streamlining the recent instruction-finetuning process on LLMs, we explore several prompting strategies for optimally adapting LLMs to specific generation task of DSD. Experimental results show that providing a clear output structure, complimented by a set of comprehensive Chain-of-Thoughts (CoT) questions, effectively improves the model's reasoning capability, and thereby, enhancing the structural correctness and faithfulness of clinical information in the generated text. Source code is available at: https://github.com/antangrocket1312/Discharge_LLM, Comment: Accepted by BioNLP2024 Workshop

Diffusion-based generative modeling has been achieving state-of-the-art results on various generation tasks. Most diffusion models, however, are limited to a single-generation modeling. Can we generalize diffusion models with the ability of multi-modal generative training for more generalizable modeling? In this paper, we propose a principled way to define a diffusion model by constructing a unified multi-modal diffusion model in a common diffusion space. We define the forward diffusion process to be driven by an information aggregation from multiple types of task-data, e.g., images for a generation task and labels for a classification task. In the reverse process, we enforce information sharing by parameterizing a shared backbone denoising network with additional modality-specific decoder heads. Such a structure can simultaneously learn to generate different types of multi-modal data with a multi-task loss, which is derived from a new multi-modal variational lower bound that generalizes the standard diffusion model. We propose several multimodal generation settings to verify our framework, including image transition, masked-image training, joint image-label and joint image-representation generative modeling. Extensive experimental results on ImageNet indicate the effectiveness of our framework for various multi-modal generative modeling, which we believe is an important research direction worthy of more future explorations., Comment: Published as a conference paper at ICLR 2024

Treating the trion problem as an effective two-body system with exciton and electron components, we identify component exchange as the reason leading to trion formation. This mechanism can be visualized as a hole that toggles back and forth between two electrons. The coined term component exchange is meant to inform that the repeated change of the electron component of the exciton originates from the exchange interaction. We develop a Bethe-Salpeter Equation for trions, showing that a bound trion state emerges if the electron and electron of the exciton are distinguishable particles (e.g., having opposite spins or residing in different valleys of the Brillouin zone). Similar to numerical techniques that treat the trion as a three-body problem, the trion Bethe-Salpeter Equation yields similar binding energy without using parameters beyond effective masses and dielectric constants., Comment: 12 pages, 7 figures. We welcome your feedback. If we missed a citation to a RELEVANT paper, please mention a specific place in the text that we should add the citation

Nuclei segmentation, despite its fundamental role in histopathological image analysis, is still a challenge work. The main challenge of this task is the existence of overlapping areas, which makes separating independent nuclei more complicated. In this paper, we propose a new two-branch architecture by combining the Unet and TransUnet networks for nuclei segmentation task. In the proposed architecture, namely Trans2Unet, the input image is first sent into the Unet branch whose the last convolution layer is removed. This branch makes the network combine features from different spatial regions of the input image and localizes more precisely the regions of interest. The input image is also fed into the second branch. In the second branch, which is called TransUnet branch, the input image will be divided into patches of images. With Vision transformer (ViT) in architecture, TransUnet can serve as a powerful encoder for medical image segmentation tasks and enhance image details by recovering localized spatial information. To boost up Trans2Unet efficiency and performance, we proposed to infuse TransUnet with a computational-efficient variation called "Waterfall" Atrous Spatial Pooling with Skip Connection (WASP-KC) module, which is inspired by the "Waterfall" Atrous Spatial Pooling (WASP) module. Experiment results on the 2018 Data Science Bowl benchmark show the effectiveness and performance of the proposed architecture while compared with previous segmentation models., Comment: ICCAIS 2022

Recently, window-based attention methods have shown great potential for computer vision tasks, particularly in Single Image Super-Resolution (SISR). However, it may fall short in capturing long-range dependencies and relationships between distant tokens. Additionally, we find that learning on spatial domain does not convey the frequency content of the image, which is a crucial aspect in SISR. To tackle these issues, we propose a new Channel-Partitioned Attention Transformer (CPAT) to better capture long-range dependencies by sequentially expanding windows along the height and width of feature maps. In addition, we propose a novel Spatial-Frequency Interaction Module (SFIM), which incorporates information from spatial and frequency domains to provide a more comprehensive information from feature maps. This includes information about the frequency content and enhances the receptive field across the entire image. Experimental findings show the effectiveness of our proposed modules and architecture. In particular, CPAT surpasses current state-of-the-art methods by up to 0.31dB at x2 SR on Urban100., Comment: Camera ready version, BMVC 2024

In the first part of this paper, we establish some results around generalized Borel's Theorem. As an application, in the second part, we construct example of smooth surface of degree $d\geq 19$ in $\mathbb{CP}^3$ whose complements is hyperbolically embedded in $\mathbb{CP}^3$. This improves the previous construction of Shirosaki where the degree bound $d=31$ was gave. In the last part, for a Fermat-Waring type hypersurface $D$ in $\mathbb{CP}^n$ defined by the homogeneous polynomial \[ \sum_{i=1}^m h_i^d, \] where $m,n,d$ are positive integers with $m\geq 3n-1$ and $d\geq m^2-m+1$, where $h_i$ are homogeneous generic linear forms on $\mathbb{C}^{n+1}$, for a nonconstant holomorphic function $f\colon\mathbb{C}\rightarrow\mathbb{CP}^n$ whose image is not contained in the support of $D$, we establish a Second Main Theorem type estimate: \[ \big(d-m(m-1)\big)\,T_f(r)\leq N_f^{[m-1]}(r,D)+S_f(r). \] This quantifies the hyperbolicity result due to Shiffman-Zaidenberg and Siu-Yeung., Comment: 17 pages, all comments are welcome

Blockchain-based supply chain (BSC) systems have tremendously been developed recently and can play an important role in our society in the future. In this study, we develop an anomaly detection model for BSC systems. Our proposed model can detect cyber-attacks at various levels, including the network layer, consensus layer, and beyond, by analyzing only the traffic data at the network layer. To do this, we first build a BSC system at our laboratory to perform experiments and collect datasets. We then propose a novel semi-supervised DAE-MLP (Deep AutoEncoder-Multilayer Perceptron) that combines the advantages of supervised and unsupervised learning to detect anomalies in BSC systems. The experimental results demonstrate the effectiveness of our model for anomaly detection within BSCs, achieving a detection accuracy of 96.5%. Moreover, DAE-MLP can effectively detect new attacks by improving the F1-score up to 33.1% after updating the MLP component.

General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora. Our audit of 14,000 web domains provides an expansive view of crawlable web data and how codified data use preferences are changing over time. We observe a proliferation of AI-specific clauses to limit use, acute differences in restrictions on AI developers, as well as general inconsistencies between websites' expressed intentions in their Terms of Service and their robots.txt. We diagnose these as symptoms of ineffective web protocols, not designed to cope with the widespread re-purposing of the internet for AI. Our longitudinal analyses show that in a single year (2023-2024) there has been a rapid crescendo of data restrictions from web sources, rendering ~5%+ of all tokens in C4, or 28%+ of the most actively maintained, critical sources in C4, fully restricted from use. For Terms of Service crawling restrictions, a full 45% of C4 is now restricted. If respected or enforced, these restrictions are rapidly biasing the diversity, freshness, and scaling laws for general-purpose AI systems. We hope to illustrate the emerging crises in data consent, for both developers and creators. The foreclosure of much of the open web will impact not only commercial AI, but also non-commercial AI and academic research., Comment: 41 pages (13 main), 5 figures, 9 tables

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a large training set is not available. However, it often leads to overfitting on the small calibration dataset. Several methods have been proposed to address this issue, yet they still rely on only the calibration set for the quantization and they do not validate the quantized model due to the lack of a validation set. In this work, we propose a novel meta-learning based approach to enhance the performance of post-training quantization. Specifically, to mitigate the overfitting problem, instead of only training the quantized model using the original calibration set without any validation during the learning process as in previous PTQ works, in our approach, we both train and validate the quantized model using two different sets of images. In particular, we propose a meta-learning based approach to jointly optimize a transformation network and a quantized model through bi-level optimization. The transformation network modifies the original calibration data and the modified data will be used as the training set to learn the quantized model with the objective that the quantized model achieves a good performance on the original calibration data. Extensive experiments on the widely used ImageNet dataset with different neural network architectures demonstrate that our approach outperforms the state-of-the-art PTQ methods., Comment: Accepted by ECCV 2024

Key Point Analysis (KPA) aims for quantitative summarization that provides key points (KPs) as succinct textual summaries and quantities measuring their prevalence. KPA studies for arguments and reviews have been reported in the literature. A majority of KPA studies for reviews adopt supervised learning to extract short sentences as KPs before matching KPs to review comments for quantification of KP prevalence. Recent abstractive approaches still generate KPs based on sentences, often leading to KPs with overlapping and hallucinated opinions, and inaccurate quantification. In this paper, we propose Prompted Aspect Key Point Analysis (PAKPA) for quantitative review summarization. PAKPA employs aspect sentiment analysis and prompted in-context learning with Large Language Models (LLMs) to generate and quantify KPs grounded in aspects for business entities, which achieves faithful KPs with accurate quantification, and removes the need for large amounts of annotated data for supervised training. Experiments on the popular review dataset Yelp and the aspect-oriented review summarization dataset SPACE show that our framework achieves state-of-the-art performance. Source code and data are available at: https://github.com/antangrocket1312/PAKPA, Comment: Accepted by ACL 2024 Main Conference

Computations of chemical systems' equilibrium properties and non-equilibrium dynamics have been suspected of being a "killer app" for quantum computers. This review highlights the recent advancements of quantum algorithms tackling complex sampling tasks in the key areas of computational chemistry: ground state, thermal state properties, and quantum dynamics calculations. We review a broad range of quantum algorithms, from hybrid quantum-classical to fully quantum, focusing on the traditional Monte Carlo family, including Markov chain Monte Carlo, variational Monte Carlo, projector Monte Carlo, path integral Monte Carlo, etc. We also cover other relevant techniques involving complex sampling tasks, such as quantum-selected configuration interaction, minimally entangled typical thermal states, entanglement forging, and Monte Carlo-flavored Lindbladian dynamics. We provide a comprehensive overview of these algorithms' classical and quantum counterparts, detailing their theoretical frameworks and discussing the potentials and challenges in achieving quantum computational advantages., Comment: 35 pages, 12 figures

We present results from a search for X-ray/gamma-ray counterparts of gravitational-wave (GW) candidates from the third observing run (O3) of the LIGO-Virgo-KAGRA (LVK) network using the Swift Burst Alert Telescope (Swift-BAT). The search includes 636 GW candidates received in low latency, 86 of which have been confirmed by the offline analysis and included in the third cumulative Gravitational-Wave Transient Catalogs (GWTC-3). Targeted searches were carried out on the entire GW sample using the maximum--likelihood NITRATES pipeline on the BAT data made available via the GUANO infrastructure. We do not detect any significant electromagnetic emission that is temporally and spatially coincident with any of the GW candidates. We report flux upper limits in the 15-350 keV band as a function of sky position for all the catalog candidates. For GW candidates where the Swift-BAT false alarm rate is less than 10$^{-3}$ Hz, we compute the GW--BAT joint false alarm rate. Finally, the derived Swift-BAT upper limits are used to infer constraints on the putative electromagnetic emission associated with binary black hole mergers., Comment: 50 pages, 10 figures, 4 tables

Due to increased reliance on private vehicles and growing travel demand, parking remains a longstanding urban challenge globally. Quantifying parking perceptions is paramount as it enables decision-makers to identify problematic areas and make informed decisions on parking management. This study introduces a cost-effective and widely accessible data source, crowdsourced online reviews, to investigate public perceptions of parking across the U.S. Specifically, we examine 4,987,483 parking-related reviews for 1,129,460 points of interest (POIs) across 911 core-based statistical areas (CBSAs) sourced from Google Maps. We employ the Bidirectional Encoder Representations from Transformers (BERT) model to classify the parking sentiment and conduct regression analyses to explore its relationships with socio-spatial factors. Findings reveal significant variations in parking sentiment across POI types and CBSAs, with Restaurant POIs showing the most negative. Regression results further indicate that denser urban areas with higher proportions of African Americans and Hispanics and lower socioeconomic status are more likely to exhibit negative parking sentiment. Interestingly, an opposite relationship between parking supply and sentiment is observed, indicating increasing supply does not necessarily improve parking experiences. Finally, our textual analysis identifies keywords associated with positive or negative sentiments and highlights disparities between urban and rural areas. Overall, this study demonstrates the potential of a novel data source and methodological framework in measuring parking sentiment, offering valuable insights that help identify hyperlocal parking issues and guide targeted parking management strategies.

With the ever-increasing popularity of blockchain applications, securing blockchain networks plays a critical role in these cyber systems. In this paper, we first study cyberattacks (e.g., flooding of transactions, brute pass) in blockchain networks and then propose an efficient collaborative cyberattack detection model to protect blockchain networks. Specifically, we deploy a blockchain network in our laboratory to build a new dataset including both normal and attack traffic data. The main aim of this dataset is to generate actual attack data from different nodes in the blockchain network that can be used to train and test blockchain attack detection models. We then propose a real-time collaborative learning model that enables nodes in the network to share learning knowledge without disclosing their private data, thereby significantly enhancing system performance for the whole network. The extensive simulation and real-time experimental results show that our proposed detection model can detect attacks in the blockchain network with an accuracy of up to 97%.

Large Language Models for Code (code LLMs) have demonstrated remarkable performance across various software engineering (SE) tasks, increasing the application of code LLMs in software development. Despite the success of code LLMs, there remain significant concerns about the actual capabilities and reliability of these models, "whether these models really learn the semantics of code from the training data and leverage the learned knowledge to perform the SE tasks". In this paper, we introduce EMPICA, a comprehensive framework designed to systematically and empirically evaluate the capabilities of code LLMs in understanding code semantics. Specifically, EMPICA systematically introduces controlled modifications/transformations into the input code and examines the models' responses. Generally, code LLMs must be robust to semantically equivalent code inputs and be sensitive to non-equivalent ones for all SE tasks. Specifically, for every SE task, given an input code snippet c and its semantic equivalent variants, code LLMs must robustly produce consistent/equivalent outputs while they are expected to generate different outputs for c and its semantic non-equivalent variants. Our experimental results on three representative code understanding tasks, including code summarization, method name prediction, and output prediction, reveal that the robustness and sensitivity of the state-of-the-art code LLMs to code transformations vary significantly across tasks and transformation operators. In addition, the code LLMs exhibit better robustness to the semantic preserving transformations than their sensitivity to the semantic non-preserving transformations. These results highlight a need to enhance the model's capabilities of understanding code semantics, especially the sensitivity property.

Under a natural assumption on the dynamical degrees, we prove that the Green currents associated to any H\'enon-like map in any dimension have H\"older continuous super-potentials, i.e., give H\"older continuous linear functionals on suitable spaces of forms and currents. As a consequence, the unique measure of maximal entropy is the Monge-Amp\`ere of a H\"older continuous plurisubharmonic function and has strictly positive Hausdorff dimension. Under the same assumptions, we also prove that the Green currents are woven. When they are of bidegree $(1,1)$, they are laminar. In particular, our results generalize results known until now only in algebraic settings, or in dimension 2.