Search

Designing generalized in-memory computing (IMC) hardware that efficiently supports a variety of workloads requires extensive design space exploration, which is infeasible to perform manually. Optimizing hardware individually for each workload or solely for the largest workload often fails to yield the most efficient generalized solutions. To address this, we propose a joint hardware-workload optimization framework that identifies optimised IMC chip architecture parameters, enabling more efficient, workload-flexible hardware. We show that joint optimization achieves 36%, 36%, 20%, and 69% better energy-latency-area scores for VGG16, ResNet18, AlexNet, and MobileNetV3, respectively, compared to the separate architecture parameters search optimizing for a single largest workload. Additionally, we quantify the performance trade-offs and losses of the resulting generalized IMC hardware compared to workload-specific IMC designs.

Reconfigurable intelligent surface (RIS) is pivotal for beyond 5G networks in regards to the surge demand for reliable communication in unmanned aerial vehicle (UAV) networks. This paper presents an innovative approach to maximize connectivity of UAV networks using RIS deployment and virtual partitioning, wherein an RIS is deployed to assist in the communications between an user-equipment (UE) and blocked UAVs. Closed-form (CF) expressions for signal-to-noise ratio (SNR) of the two-UAV setup are derived and validated. Then, an optimization problem is formulated to maximize network connectivity by optimizing the 3D deployment of the RIS and its partitioning subject to predefined quality-of-service (QoS) constraints. To tackle this problem, we propose a method of virtually partitioning the RIS given a fixed 3D location, such that the partition phase shifts are configured to create cascaded channels between the UE and the blocked two UAVs. Then, simulated-annealing (SA) method is used to find the 3D location of the RIS. Simulation results demonstrate that the proposed joint RIS deployment and partitioning framework can significantly improve network connectivity compared to benchmarks, including RIS-free and RIS with a single narrow-beam link., Comment: 6 pages, 5 figures, conference

Purpose: Dynamic glucose enhanced (DGE) MRI studies employ chemical exchange saturation transfer (CEST) or spin lock (CESL) to study glucose uptake. Currently, these methods are hampered by low effect size and sensitivity to motion. To overcome this, we propose to utilize exchange-based linewidth (LW) broadening of the direct water saturation (DS) curve of the water saturation spectrum (Z-spectrum) during and after glucose infusion (DS-DGE MRI). Methods: To estimate the glucose-infusion-induced LW changes ($\Delta$LW), Bloch-McConnell simulations were performed for normoglycemia and hyperglycemia in blood, gray matter (GM), white matter (WM), CSF, and malignant tumor tissue. Whole-brain DS-DGE imaging was implemented at 3 tesla using dynamic Z-spectral acquisitions (1.2 s per offset frequency, 38 s per spectrum) and assessed on four brain tumor patients using infusion of 35 g of D-glucose. To assess $\Delta$LW, a deep learning-based Lorentzian fitting approach was employed on voxel-based DS spectra acquired before, during, and post-infusion. Area-under-the-curve (AUC) images, obtained from the dynamic $\Delta$LW time curves, were compared qualitatively to perfusion-weighted imaging (PWI). Results: In simulations, $\Delta$LW was 1.3%, 0.30%, 0.29/0.34%, 7.5%, and 13% in arterial blood, venous blood, GM/WM, malignant tumor tissue, and CSF, respectively. In vivo, $\Delta$LW was approximately 1% in GM/WM, 5-20% for different tumor types, and 40% in CSF. The resulting DS-DGE AUC maps clearly outlined lesion areas. Conclusions: DS-DGE MRI is highly promising for assessing D-glucose uptake. Initial results in brain tumor patients show high-quality AUC maps of glucose-induced line broadening and DGE-based lesion enhancement similar and/or complementary to PWI., Comment: 13 pages, 6 figures

Predicting a ligand's bound pose to a target protein is a key component of early-stage computational drug discovery. Recent developments in machine learning methods have focused on improving pose quality at the cost of model runtime. For high-throughput virtual screening applications, this exposes a capability gap that can be filled by moderately accurate but fast pose prediction. To this end, we developed QuickBind, a light-weight pose prediction algorithm. We assess QuickBind on widely used benchmarks and find that it provides an attractive trade-off between model accuracy and runtime. To facilitate virtual screening applications, we augment QuickBind with a binding affinity module and demonstrate its capabilities for multiple clinically-relevant drug targets. Finally, we investigate the mechanistic basis by which QuickBind makes predictions and find that it has learned key physicochemical properties of molecular docking, providing new insights into how machine learning models generate protein-ligand poses. By virtue of its simplicity, QuickBind can serve as both an effective virtual screening tool and a minimal test bed for exploring new model architectures and innovations. Model code and weights are available at https://github.com/aqlaboratory/QuickBind ., Comment: Proceedings of the 19th Machine Learning in Computational Biology meeting

Large language models (LLMs) are becoming increasingly better at a wide range of Natural Language Processing tasks (NLP), such as text generation and understanding. Recently, these models have extended their capabilities to coding tasks, bridging the gap between natural languages (NL) and programming languages (PL). Foundational models such as the Generative Pre-trained Transformer (GPT) and LLaMA series have set strong baseline performances in various NL and PL tasks. Additionally, several models have been fine-tuned specifically for code generation, showing significant improvements in code-related applications. Both foundational and fine-tuned models are increasingly used in education, helping students write, debug, and understand code. We present a comprehensive systematic literature review to examine the impact of LLMs in computer science and computer engineering education. We analyze their effectiveness in enhancing the learning experience, supporting personalized education, and aiding educators in curriculum development. We address five research questions to uncover insights into how LLMs contribute to educational outcomes, identify challenges, and suggest directions for future research., Comment: Accepted at 56th ACM Technical Symposium on Computer Science Education (SIGCSE TS 2025)

Searching for technologically promising crystalline materials with desired thermal transport properties requires an electronic level comprehension of interatomic interactions and chemical intuition to uncover the hidden structure-property relationship. Here, we propose two chemical bonding descriptors, namely negative normalized integrated crystal orbital Hamilton population (normalized -ICOHP) and normalized integrated crystal orbital bond index (normalized ICOBI) and unravel their strong correlation to both lattice thermal conductivity (LTC) and rattling effect characterized by mean squared displacement (MSD). Our new descriptors outperform empirical models and the sole -ICOHP quantity in closely relating to extreme LTCs by testing on a first-principles dataset of over 4,500 materials with 62 distinct species. The Pearson correlation of both descriptors with LTC are significantly higher in magnitude compared with the traditional simple rule of average mass. We further develop crystal attention graph neural networks (CATGNN) model and predict our proposed descriptors of ~200,000 materials from existing databases to screen potentially ultralow and high LTC materials. We select 367 (533) with low (high) normalized -ICOHP and ICOBI for first-principles validation. The validation shows that 106 dynamically stable materials with low normalized -ICOHP and ICOBI have LTC less than 5 W/mK, among which 68% are less than 2 W/mK, while 13 stable materials with high normalized -ICOHP and ICOBI possess LTC higher than 100 W/mK. The proposed normalized -ICOHP and normalized ICOBI descriptors offer deep insights into LTC and MSD from chemical bonding principles. Considering the cheap computational cost, these descriptors offer a new reliable and fast route for high-throughput screening of novel crystalline materials with extreme LTCs for applications such as thermoelectrics and electronic cooling., Comment: 26+13S pages, 7+5S figures, 3+2S tables. S denotes Supplemental Information (SI)

We assign a new polynomial to any checkerboard-colorable 4-valent virtual graph in terms of its Euler circuit expansion. This provides a new combinatorial formulation of the Kauffman-Jones polynomial for checkerboard-colorable virtual links., Comment: 19 pages, 13 figures, 4 tables

Recent years witnessed remarkable progress in computational histopathology, largely fueled by deep learning. This brought the clinical adoption of deep learning-based tools within reach, promising significant benefits to healthcare, offering a valuable second opinion on diagnoses, streamlining complex tasks, and mitigating the risks of inconsistency and bias in clinical decisions. However, a well-known challenge is that deep learning models may contain up to billions of parameters; supervising their training effectively would require vast labeled datasets to achieve reliable generalization and noise resilience. In medical imaging, particularly histopathology, amassing such extensive labeled data collections places additional demands on clinicians and incurs higher costs, which hinders the art's progress. Addressing this challenge, researchers devised various strategies for leveraging deep learning with limited data and annotation availability. In this paper, we present a comprehensive review of deep learning applications in histopathology, with a focus on the challenges posed by data scarcity over the past decade. We systematically categorize and compare various approaches, evaluate their distinct contributions using benchmarking tables, and highlight their respective advantages and limitations. Additionally, we address gaps in existing reviews and identify underexplored research opportunities, underscoring the potential for future advancements in this field., Comment: 36 pages

Large language models (LLM) are increasingly strong contenders in machine translation. We study document-level translation, where some words cannot be translated without context from outside the sentence. We investigate the ability of prominent LLMs to utilize context by analyzing models' robustness to perturbed and randomized document context. We find that LLMs' improved document-translation performance is not always reflected in pronoun translation performance. We highlight the need for context-aware finetuning of LLMs with a focus on relevant parts of the context to improve their reliability for document-level translation., Comment: 4 pages, 2 figures, 2 tables

Lepton flavour universality in rare $b\rightarrow s$ transitions is tested for the first time using $B_s^0$ meson decays. The measurements are performed using $pp$ collision data collected by the LHCb experiment between 2011 and 2018, corresponding to a total integrated luminosity of 9$\,{\rm fb}^{-1}$. Branching fraction ratios between the $B_s^0 \rightarrow \phi e^+e^-$ and $B_s^0 \rightarrow \phi \mu^+\mu^-$ decays are measured in three regions of dilepton mass squared, $q^2$, with $0.1 < q^2 < 1.1$, $1.1 < q^2 < 6.0$, and $15 < q^2 < 19\,{\rm GeV}^2/c^4$. The results agree with the Standard Model expectation of lepton flavour universality., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3513/ (LHCb public pages)

Detecting offensive memes is crucial, yet standard deep neural network systems often remain opaque. Various input attribution-based methods attempt to interpret their behavior, but they face challenges with implicitly offensive memes and non-causal attributions. To address these issues, we propose a framework based on a Structural Causal Model (SCM). In this framework, VisualBERT is trained to predict the class of an input meme based on both meme input and causal concepts, allowing for transparent interpretation. Our qualitative evaluation demonstrates the framework's effectiveness in understanding model behavior, particularly in determining whether the model was right due to the right reason, and in identifying reasons behind misclassification. Additionally, quantitative analysis assesses the significance of proposed modelling choices, such as de-confounding, adversarial learning, and dynamic routing, and compares them with input attribution methods. Surprisingly, we find that input attribution methods do not guarantee causality within our framework, raising questions about their reliability in safety-critical applications. The project page is at: https://newcodevelop.github.io/causality_adventure/, Comment: Accepted at EMNLP Findings 2024

Evaluating machine-generated text remains a significant challenge in NLP, especially for non-English languages. Current methodologies, including automated metrics, human assessments, and LLM-based evaluations, predominantly focus on English, revealing a significant gap in multilingual evaluation frameworks. We introduce the Cross Lingual Auto Evaluation (CIA) Suite, an extensible framework that includes evaluator LLMs (Hercule) and a novel test set (Recon) specifically designed for multilingual evaluation. Our test set features 500 human-annotated instructions spanning various task capabilities along with human judgment scores across six languages. This would enable benchmarking of general-purpose multilingual LLMs and facilitate meta-evaluation of Evaluator LLMs. The proposed model, Hercule, is a cross-lingual evaluation model that addresses the scarcity of reference answers in the target language by learning to assign scores to responses based on easily available reference answers in English. Our experiments demonstrate that Hercule aligns more closely with human judgments compared to proprietary models, demonstrating the effectiveness of such cross-lingual evaluation in low resource scenarios. Further, it is also effective in zero-shot evaluation on unseen languages. This study is the first comprehensive examination of cross-lingual evaluation using LLMs, presenting a scalable and effective approach for multilingual assessment. All code, datasets, and models will be publicly available to enable further research in this important area.

This paper presents the findings from the third edition of the Chat Translation Shared Task. As with previous editions, the task involved translating bilingual customer support conversations, specifically focusing on the impact of conversation context in translation quality and evaluation. We also include two new language pairs: English-Korean and English-Dutch, in addition to the set of language pairs from previous editions: English-German, English-French, and English-Brazilian Portuguese. We received 22 primary submissions and 32 contrastive submissions from eight teams, with each language pair having participation from at least three teams. We evaluated the systems comprehensively using both automatic metrics and human judgments via a direct assessment framework. The official rankings for each language pair were determined based on human evaluation scores, considering performance in both translation directions--agent and customer. Our analysis shows that while the systems excelled at translating individual turns, there is room for improvement in overall conversation-level translation quality., Comment: 12 pages, 5 figures, 13 tables

Assemblies of plasmonic nanoparticles (NPs) support hybridized modes of localized surface plasmons (LSPs), which delocalize in geometrically well-ordered arrangements. Here, the hybridization behavior of LSPs in geometrically completely disordered arrangements of Au NPs fabricated by an e-beam synthesis method is studied. Employing electron energy loss spectroscopy in a scanning transmission electron microscope in combination with numerical simulations, the disorder-driven spatial and spectral localization of the coupled LSP modes that depend on the NP thickness is revealed. Below 0.4 nm sample thickness (flat NPs), localization increases towards higher hybridized LSP mode energies. In comparison, above 10 nm thickness, a decrease of localization (an increase of delocalization) with higher mode energies is observed. In the intermediate thickness regime, a transition of the energy dependence of the localization between the two limiting cases, exhibiting a transition mode energy with minimal localization, is observed. This behavior is mainly driven by the energy and thickness dependence of the polarizability of the individual NPs.

Mosques are worship places of Allah and must be preserved clean, immaculate, provide all the comforts of the worshippers in them. The prophet's mosque in Medina/ Saudi Arabia is one of the most important mosques for Muslims. It occupies second place after the sacred mosque in Mecca/ Saudi Arabia, which is in constant overcrowding by all Muslims to visit the prophet Mohammad's tomb. This paper aims to propose a smart dome model to preserve the fresh air and allow the sunlight to enter the mosque using artificial intelligence techniques. The proposed model controls domes movements based on the weather conditions and the overcrowding rates in the mosque. The data have been collected from two different resources, the first one from the database of Saudi Arabia weather's history, and the other from Shanghai Technology Database. Congested Scene Recognition Network (CSRNet) and Fuzzy techniques have applied using Python programming language to control the domes to be opened and closed for a specific time to renew the air inside the mosque. Also, this model consists of several parts that are connected for controlling the mechanism of opening/closing domes according to weather data and the situation of crowding in the mosque. Finally, the main goal of this paper has been achieved, and the proposed model has worked efficiently and specifies the exact duration time to keep the domes open automatically for a few minutes for each hour head.

COVID-19, has led to a global pandemic that strained the healthcare systems. Early and accurate detection is crucial for controlling the spread of the virus. While reverse transcription polymerase chain reaction test is the gold standard for diagnosis, it's limited availability, long processing times and extremely high false negative rate, have prompted the exploration of alternative methods. Chest Xray imaging has emerged as a valuable, non invasive tool for identifying COVID-19 related lung abnormalities. Traditional convolutional neural networks (CNNs) achieve impressive accuracy, but there is a need for more robust solutions to minimize false positives and negatives in critical medical applications. Thus We introduce the MOZART framework, an ensemble learning approach that enhances the virus detection. We trained three CNN architectures InceptionV3, Xception, and ResNet50 on a balanced chest X-ray dataset of 3,616 COVID-19 and 3,616 healthy images. Each model underwent a separate preprocessing pipeline, such as normalizing inputs to a range of -1 to 1. The dataset was split into 70% for training, 20% for validation, and 10% for testing, after training the individual models, we trained a shallow neural network on the predictions and to provide a us with the final predictions. Our results show that the MOZART framework with it's sub-experiments MOZART1 and MOZART2 outperforms individual CNN models in key metrics. It achieved an accuracy of 99.17% and an F1 score of 99.16%. MOZART1 excels at minimizing false positives, while MOZART2 is better for reducing false negatives. This work suggests that the MOZART framework can improve reliability in AI-driven medical imaging tasks and should be explored further for other lung diseases., Comment: This paper was originally intended to be published as part of my B.Sc. graduation project in Electrical and Electronics Engineering at the University of Khartoum in 2021. However, due to political and economic instability, and most recently, the outbreak of conflict in Sudan in April 2023, the publication process was significantly delayed. But yeah, better late than never

In times of crisis, the prompt and precise classification of disaster-related information shared on social media platforms is crucial for effective disaster response and public safety. During such critical events, individuals use social media to communicate, sharing multimodal textual and visual content. However, due to the significant influx of unfiltered and diverse data, humanitarian organizations face challenges in leveraging this information efficiently. Existing methods for classifying disaster-related content often fail to model users' credibility, emotional context, and social interaction information, which are essential for accurate classification. To address this gap, we propose CrisisSpot, a method that utilizes a Graph-based Neural Network to capture complex relationships between textual and visual modalities, as well as Social Context Features to incorporate user-centric and content-centric information. We also introduce Inverted Dual Embedded Attention (IDEA), which captures both harmonious and contrasting patterns within the data to enhance multimodal interactions and provide richer insights. Additionally, we present TSEqD (Turkey-Syria Earthquake Dataset), a large annotated dataset for a single disaster event, containing 10,352 samples. Through extensive experiments, CrisisSpot demonstrated significant improvements, achieving an average F1-score gain of 9.45% and 5.01% compared to state-of-the-art methods on the publicly available CrisisMMD dataset and the TSEqD dataset, respectively.

Feature selection is an essential process in machine learning, especially when dealing with high-dimensional datasets. It helps reduce the complexity of machine learning models, improve performance, mitigate overfitting, and decrease computation time. This paper presents a novel feature selection framework, shap-select. The framework conducts a linear or logistic regression of the target on the Shapley values of the features, on the validation set, and uses the signs and significance levels of the regression coefficients to implement an efficient heuristic for feature selection in tabular regression and classification tasks. We evaluate shap-select on the Kaggle credit card fraud dataset, demonstrating its effectiveness compared to established methods such as Recursive Feature Elimination (RFE), HISEL (a mutual information-based feature selection method), Boruta and a simpler Shapley value-based method. Our findings show that shap-select combines interpretability, computational efficiency, and performance, offering a robust solution for feature selection., Comment: 13 pages, 1 figure

Prior research has demonstrated the effectiveness of end-to-end deep learning for robotic navigation, where the control signals are directly derived from raw sensory data. However, the majority of existing end-to-end navigation solutions are predominantly camera-based. In this paper, we introduce TinyLidarNet, a lightweight 2D LiDAR-based end-to-end deep learning model for autonomous racing. An F1TENTH vehicle using TinyLidarNet won 3rd place in the 12th F1TENTH Autonomous Grand Prix competition, demonstrating its competitive performance. We systematically analyze its performance on untrained tracks and computing requirements for real-time processing. We find that TinyLidarNet's 1D Convolutional Neural Network (CNN) based architecture significantly outperforms widely used Multi-Layer Perceptron (MLP) based architecture. In addition, we show that it can be processed in real-time on low-end micro-controller units (MCUs).

In this work, we look for a spacial SEIAR-type epidemic model consediring quarantined population $(Q)$, namely SQEIAR model. The dynamic of the SQEIAR model involves six partial differential equations that decribe the changes in susceptible, quarantined, exposed, asymptomatic, infected and recovered population. Our goal is to reduce the number of exposed, asymptomatic, and infected population while taking into account the environment, which plays a critical role in the spread of epidemics. Then, we implement a new strategy based on two control actions: regional quarantine for susceptible population and treatment for infected population. To demonstrate the practical utility of the obtained results, a numerical example centered on COVID-19 is presented., Comment: 28 pages, 16 figures, submitted to the International Journal of Control

In recent times, the study of the Casimir effect in quantum field theory has garnered increasing attention because of its potential to be an ideal source of exotic matter needed for stabilizing traversable wormholes. It has been confirmed through experimental evidence that this phenomenon involves fluctuations in the vacuum field, leading to a negative energy density. Motivated by the above, we have investigated Casimir wormholes with corrections from the Generalized Uncertainty Principle (GUP) within the framework of matter-coupled teleparallel gravity. Our analysis includes three well-known GUP models: the Kempf, Mangano, and Mann (KMM) model, the Detournay, Gabriel, and Spindel (DGS) model, and a third model called Model II. For a broader analysis, we have considered two well-known model functions for the teleparallel theory: a linear $f(T,\mathcal{T})=\alpha T+\beta\mathcal{T}$ and a quadratic model $f(T,\mathcal{T})=\eta T^2+\chi\mathcal{T}$. The shape function solutions corresponding to both models are examined in the absence of tidal forces in spacetime. We also demonstrate the crucial role played by the parameters of the $f(T,\mathcal{T})$ models in the violation of the energy conditions. With the increasing interest in detecting gravitational waves from astrophysical objects, we have thoroughly discussed the perturbation of the wormhole solutions in the scalar, electromagnetic, axial gravitational, and Dirac field backgrounds. We employ the $3^{rd}$ order WKB expansion to find the complex frequencies associated with the quasinormal modes of energy dissipation. Additionally, we also calculate the active mass and total gravitational energy for the wormhole geometry. The amount of exotic matter involved in sustaining these wormholes is also found in this paper. Furthermore, the physical stability of such Casimir wormholes is examined using the Tolman-Oppenheimer-Volkoff equation., Comment: EPJC accepted version

This paper introduces a novel method to enhance the connectivity of multi-reconfigurable intelligent surface-assisted device-to-device networks, referred to as multi-RIS-assisted D2D networks, through a unique phase shift determination. The proposed method aims to optimize the power-domain array factor (PDAF), targeting specific azimuth angles of reliable user equipments (UEs) and enhancing network connectivity. We formulate an optimization problem that jointly optimizes RIS beamforming design, RIS-aided link selection, and RIS positioning. This problem is a mixed-integer non-binary programming. The optimization problem is divided into two sub-problems, which are solved individually and iteratively. The first sub-problem of RIS-aided link selection is solved using an efficient perturbation method while developing genetic algorithm (GA) to obtain RIS beamforming design. The GA optimizes the RIS phase shift to generate multiple RIS-aided narrowbeams that exhibit significant PDAF towards azimuth angles of interest while minimizing PDAF towards undesired azimuth angles. The second sub-problem of RIS positioning is addressed using the Adam optimizer. Numerical simulations verify the superiority of the proposed scheme in improving network connectivity compared to other schemes, including those utilizing distributed small RISs, each generating one RIS-aided link., Comment: 6 pages, 5 figures, conference

In this paper, we investigate some hyperstability results, inspired by the concept of Ulam stability, for the following functional equations: \begin{equation} \varphi(x+y)+\varphi(x-y)=2\varphi(x)+2\varphi(y) \end{equation} \begin{equation} \varphi(ax+by) = A\varphi(x)+B\varphi(y)+C \end{equation} \begin{equation}\label{eqnd} f\left(\sum_{i=1}^{m}x_{i}\right)+\sum_{1\leq i

Multi-omics data is increasingly being utilized to advance computational methods for cancer classification. However, multi-omics data integration poses significant challenges due to the high dimensionality, data complexity, and distinct characteristics of various omics types. This study addresses these challenges and evaluates three graph neural network architectures for multi-omics (MO) integration based on graph-convolutional networks (GCN), graph-attention networks (GAT), and graph-transformer networks (GTN) for classifying 31 cancer types and normal tissues. To address the high-dimensionality of multi-omics data, we employed LASSO (Least Absolute Shrinkage and Selection Operator) regression for feature selection, leading to the creation of LASSO-MOGCN, LASSO-MOGAT, and LASSO-MOTGN models. Graph structures for the networks were constructed using gene correlation matrices and protein-protein interaction networks for multi-omics integration of messenger-RNA, micro-RNA, and DNA methylation data. Such data integration enables the networks to dynamically focus on important relationships between biological entities, improving both model performance and interpretability. Among the models, LASSO-MOGAT with a correlation-based graph structure achieved state-of-the-art accuracy (95.9%) and outperformed the LASSO-MOGCN and LASSO-MOTGN models in terms of precision, recall, and F1-score. Our findings demonstrate that integrating multi-omics data in graph-based architectures enhances cancer classification performance by uncovering distinct molecular patterns that contribute to a better understanding of cancer biology and potential biomarkers for disease progression.

Automatic annotation of large-scale datasets can introduce noisy training data labels, which adversely affect the learning process of deep neural networks (DNNs). Consequently, Noisy Labels Learning (NLL) has become a critical research field for Convolutional Neural Networks (CNNs), though it remains less explored for Vision Transformers (ViTs). In this study, we evaluate the vulnerability of ViT fine-tuning to noisy labels and compare its robustness with CNNs. We also investigate whether NLL methods developed for CNNs are equally effective for ViTs. Using linear probing and MLP-K fine-tuning, we benchmark two ViT backbones (ViT-B/16 and ViT-L/16) using three commonly used classification losses: Cross Entropy (CE), Focal Loss (FL), and Mean Absolute Error (MAE), alongside six robust NLL methods: GCE, SCE, NLNL, APL, NCE+AGCE, and ANL-CE. The evaluation is conducted across six datasets including MNIST, CIFAR-10/100, WebVision, Clothing1M, and Food-101N. Furthermore, we explore whether implicit prediction entropy minimization contributes to ViT robustness against noisy labels, noting a general trend of prediction entropy reduction across most NLL methods. Building on this observation, we examine whether explicit entropy minimization could enhance ViT resilience to noisy labels. Our findings indicate that incorporating entropy regularization enhances the performance of established loss functions such as CE and FL, as well as the robustness of the six studied NLL methods across both ViT backbones.

The importance of continuously emerging new distribution is a mandate to understand the world and environment surrounding us. In this paper, the author will discuss a new distribution defined on the interval (0,1) as regards the methodology of deducing its PDF, some of its properties and related functions. A simulation and real data analysis will be highlighted., Comment: It is a new distribution with some of its properties and methods of estimation

The main goal of this paper is to introduce a new fractional anisotropic Sobolev space with variable exponent where the basic qualitative properties (completeness, separability, reflexivity, ...) are established, including the continuous and compact embedding results. Moreover, some functional proprieties of anisotropic fractional $\vec{p}(.,.)$-Laplacian operator are proved. As an application, we use the mountain pass theorem and Ekeland's variational principle to ensure the existence of a weak solution for a nonlocal anisotropic problem with variable exponent.

Large language models (LLMs) can generate fluent summaries across domains using prompting techniques, reducing the need to train models for summarization applications. However, crafting effective prompts that guide LLMs to generate summaries with the appropriate level of detail and writing style remains a challenge. In this paper, we explore the use of salient information extracted from the source document to enhance summarization prompts. We show that adding keyphrases in prompts can improve ROUGE F1 and recall, making the generated summaries more similar to the reference and more complete. The number of keyphrases can control the precision-recall trade-off. Furthermore, our analysis reveals that incorporating phrase-level salient information is superior to word- or sentence-level. However, the impact on hallucination is not universally positive across LLMs. To conduct this analysis, we introduce Keyphrase Signal Extractor (SigExt), a lightweight model that can be finetuned to extract salient keyphrases. By using SigExt, we achieve consistent ROUGE improvements across datasets and open-weight and proprietary LLMs without any LLM customization. Our findings provide insights into leveraging salient information in building prompt-based summarization systems., Comment: Accepted to EMNLP 2024 Industry Track

Using $pp$ collision data at $\sqrt{s}=13$ TeV, recorded by the LHCb experiment between 2016 and 2018 and corresponding to an integrated luminosity of $5.4$ fb$^{-1}$, the forward-backward asymmetry in the $pp \to Z/\gamma^{*} \to \mu^+\mu^-$ process is measured. The measurement is carried out in ten intervals of the difference between the muon pseudorapidities, within a fiducial region covering dimuon masses between $66$ and $116$ GeV, muon pseudorapidities between $2.0$ and $4.5$ and muon transverse momenta above $20$ GeV. These forward-backward asymmetries are compared with predictions, at next-to-leading order in the strong and electroweak couplings. The measured effective leptonic weak mixing angle is $\sin^2\theta_{\rm eff}^\ell = 0.23147 \pm 0.00044 \pm 0.00005 \pm 0.00023$, where the first uncertainty is statistical, the second arises from systematic uncertainties associated with the asymmetry measurement, and the third arises from uncertainties in the fit model used to extract $\sin^2\theta_{\rm eff}^\ell$ from the asymmetry measurement. This result is based on an arithmetic average of results using the CT18, MSHT20, and NNPDF31 parameterisations of the proton internal structure, and is consistent with previous measurements and with predictions from the global electroweak fit., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/3360/ (LHCb public pages)

The advent of large language models (LLMs) has initiated much research into their various financial applications. However, in applying LLMs on long documents, semantic relations are not explicitly incorporated, and a full or arbitrarily sparse attention operation is employed. In recent years, progress has been made in Abstract Meaning Representation (AMR), which is a graph-based representation of text to preserve its semantic relations. Since AMR can represent semantic relationships at a deeper level, it can be beneficially utilized by graph neural networks (GNNs) for constructing effective document-level graph representations built upon LLM embeddings to predict target metrics in the financial domain. We propose FLAG: Financial Long document classification via AMR-based GNN, an AMR graph based framework to generate document-level embeddings for long financial document classification. We construct document-level graphs from sentence-level AMR graphs, endow them with specialized LLM word embeddings in the financial domain, apply a deep learning mechanism that utilizes a GNN, and examine the efficacy of our AMR-based approach in predicting labeled target data from long financial documents. Extensive experiments are conducted on a dataset of quarterly earnings calls transcripts of companies in various sectors of the economy, as well as on a corpus of more recent earnings calls of companies in the S&P 1500 Composite Index. We find that our AMR-based approach outperforms fine-tuning LLMs directly on text in predicting stock price movement trends at different time horizons in both datasets. Our work also outperforms previous work utilizing document graphs and GNNs for text classification., Comment: 8 pages, 3 figures, to be published in CIFEr Conference 2024 as "Semantic Graph Learning for Trend Prediction from Long Financial Documents"

Gradient descent computed by backpropagation (BP) is a widely used learning method for training artificial neural networks but has several limitations: it is computationally demanding, requires frequent manual tuning of the network architecture, and is prone to catastrophic forgetting when learning incrementally. To address these issues, we introduce a brain-mimetic developmental spiking neural network (BDNN) that mimics the postnatal development of neural circuits. We validate its performance through a neuromorphic tactile system capable of learning to recognize objects through grasping. Unlike traditional BP-based methods, BDNN exhibits strong knowledge transfer, supporting efficient incremental learning of new tactile information. It requires no hyperparameter tuning and dynamically adapts to incoming data. Moreover, compared to the BP-based counterpart, it achieves classification accuracy on par with BP while learning over ten times faster in ideal conditions and up to two or three orders of magnitude faster in practical settings. These features make BDNN well-suited for fast data processing on edge devices., Comment: 24 pages, 8 figures, 2 tables

Knowledge graph (KG) completion aims to identify additional facts that can be inferred from the existing facts in the KG. Recent developments in this field have explored this task in the inductive setting, where at test time one sees entities that were not present during training; the most performant models in the inductive setting have employed path encoding modules in addition to standard subgraph encoding modules. This work similarly focuses on KG completion in the inductive setting, without the explicit use of path encodings, which can be time-consuming and introduces several hyperparameters that require costly hyperparameter optimization. Our approach uses a Transformer-based subgraph encoding module only; we introduce connection-biased attention and entity role embeddings into the subgraph encoding module to eliminate the need for an expensive and time-consuming path encoding module. Evaluations on standard inductive KG completion benchmark datasets demonstrate that our Connection-Biased Link Prediction (CBLiP) model has superior performance to models that do not use path information. Compared to models that utilize path information, CBLiP shows competitive or superior performance while being faster. Additionally, to show that the effectiveness of connection-biased attention and entity role embeddings also holds in the transductive setting, we compare CBLiP's performance on the relation prediction task in the transductive setting.

IJCLab has been leading the development and deployment of low-$\beta$ Superconducting Radio Frequency (SRF) cavities for proton and heavy ion accelerators. We are launching an electron accelerator project for sustainable Energy Recovery Linac (iSAS/PERLE) with state-of-the-art SRF cavities at 800~MHz. Our proposal includes advanced heat treatment of such cavities to reach an excellent quality factor of $3\times 10^{10}$ at $22$~MV/m. In this paper, we overview the status of this activity., Comment: Contribution to LCWS2024 proceedings

A matrix of analytic functions A(z), such as the matrix of transfer functions in a multiple-input multiple-output (MIMO) system, generally admits an analytic singular value decomposition (SVD), where the singular values themselves are functions. When evaluated on the unit circle, for the sake of analyticity, these singular values must be permitted of become negative. In this paper, we address how the estimation of such a matrix, causing a stochastic perturbation of A}(z), results in fundamental changes to the analytic singular values: for the perturbed system, we show that their analytic singular values lose any algebraic multiplicities and are strictly non-negative with probability one. We present examples and highlight the impact that this has on algorithmic solutions to extracting an analytic or approximate analytic SVD.

Climate change has led to an increase in the frequency and severity of extreme weather events, posing significant challenges for power distribution systems. In response, this work presents a planning approach in order to enhance the resilience of distribution systems against climatic hazards. The framework systematically addresses uncertainties during extreme events, including weather variability and line damage. Key strategies include line hardening, backup diesel generators, and sectionalizers to strengthen resilience. We model spatio-temporal dynamics and costs through a hybrid model integrating stochastic processes with deterministic elements. A two-stage stochastic mixed-integer linear approach is developed to optimize resilience investments against load loss, generator operations, and repairs. Case studies on the IEEE 15-bus benchmark system and a realistic distribution grid model in Riyadh, Saudi Arabia demonstrate enhanced system robustness as well as cost efficiency of 10% and 15%, respectively., Comment: CIRED Chicago Workshop 2024: Resilience of Electric Distribution Systems

We study the decay of the exotic Vector-Like Quarks (VLQs) $X$ and $Y$, with $5/3$ and $-4/3$ units of electric charge, respectively, within the 2-Higgs Doublet Model (2HDM). Building on our previous studies of Vector-Like Top and Bottom (VLT and VLB) quarks, we now investigate the characteristics of $X$ and $Y$ in the alignment limit of a Type-II Yukawa structure and show that, in the framework of such a 2HDM, one can have large non-Standard Model (SM) decay rates of the $X$ and$ Y$ states. Our analysis focuses on their potential detection at the Large Hadron Collider (LHC), based on their pair production followed by a variety of both SM and non-SM decay patterns. In order to distinguish between doublet and triplet representations of the VLQs $X$ and $Y$, we uncover specific signatures that can provide insights into this particular architecture of Beyond the SM (BSM) physics., Comment: 22 pages, 10 figures

Unmanned Aerial Vehicles (UAVs) are becoming more popular in various sectors, offering many benefits, yet introducing significant challenges to privacy and safety. This paper investigates state-of-the-art solutions for detecting and tracking quadrotor UAVs to address these concerns. Cutting-edge deep learning models, specifically the YOLOv5 and YOLOv8 series, are evaluated for their performance in identifying UAVs accurately and quickly. Additionally, robust tracking systems, BoT-SORT and Byte Track, are integrated to ensure reliable monitoring even under challenging conditions. Our tests on the DUT dataset reveal that while YOLOv5 models generally outperform YOLOv8 in detection accuracy, the YOLOv8 models excel in recognizing less distinct objects, demonstrating their adaptability and advanced capabilities. Furthermore, BoT-SORT demonstrated superior performance over Byte Track, achieving higher IoU and lower center error in most cases, indicating more accurate and stable tracking. Code: https://github.com/zmanaa/UAV_detection_and_tracking Tracking demo: https://drive.google.com/file/d/1pe6HC5kQrgTbA2QrjvMN-yjaZyWeAvDT/view?usp=sharing

Secure navigation is pivotal for several applications including autonomous vehicles, robotics, and aviation. The inertial navigation system estimates position, velocity, and attitude through dead reckoning especially when external references like GPS are unavailable. However, the three accelerometers and three gyroscopes that compose the system are exposed to various types of errors including bias errors, scale factor errors, and noise, which can significantly degrade the accuracy of navigation constituting also a key vulnerability of this system. This work aims to adopt a supervised convolutional neural network (ConvNet) to address this vulnerability inherent in inertial navigation systems. In addition to this, this paper evaluates the impact of the ConvNet layer's depth on the accuracy of these corrections. This evaluation aims to determine the optimal layer configuration maximizing the effectiveness of error correction in INS (Inertial Navigation System) leading to precise navigation solutions.

Natural language and visualization are two complementary modalities of human communication that play a crucial role in conveying information effectively. While visualizations help people discover trends, patterns, and anomalies in data, natural language descriptions help explain these insights. Thus, combining text with visualizations is a prevalent technique for effectively delivering the core message of the data. Given the rise of natural language generation (NLG), there is a growing interest in automatically creating natural language descriptions for visualizations, which can be used as chart captions, answering questions about charts, or telling data-driven stories. In this survey, we systematically review the state of the art on NLG for visualizations and introduce a taxonomy of the problem. The NLG tasks fall within the domain of Natural Language Interfaces (NLI) for visualization, an area that has garnered significant attention from both the research community and industry. To narrow down the scope of the survey, we primarily concentrate on the research works that focus on text generation for visualizations. To characterize the NLG problem and the design space of proposed solutions, we pose five Wh-questions, why and how NLG tasks are performed for visualizations, what the task inputs and outputs are, as well as where and when the generated texts are integrated with visualizations. We categorize the solutions used in the surveyed papers based on these "five Wh-questions." Finally, we discuss the key challenges and potential avenues for future research in this domain.

Advancements in generative modeling are pushing the state-of-the-art in synthetic medical image generation. These synthetic images can serve as an effective data augmentation method to aid the development of more accurate machine learning models for medical image analysis. While the fidelity of these synthetic images has progressively increased, the diversity of these images is an understudied phenomenon. In this work, we propose the SDICE index, which is based on the characterization of similarity distributions induced by a contrastive encoder. Given a synthetic dataset and a reference dataset of real images, the SDICE index measures the distance between the similarity score distributions of original and synthetic images, where the similarity scores are estimated using a pre-trained contrastive encoder. This distance is then normalized using an exponential function to provide a consistent metric that can be easily compared across domains. Experiments conducted on the MIMIC-chest X-ray and ImageNet datasets demonstrate the effectiveness of SDICE index in assessing synthetic medical dataset diversity., Comment: Accepted at BMVC 2024 - PFATCV

The early detection and nuanced subtype classification of non-small cell lung cancer (NSCLC), a predominant cause of cancer mortality worldwide, is a critical and complex issue. In this paper, we introduce an innovative integration of multi-modal data, synthesizing fused medical imaging (CT and PET scans) with clinical health records and genomic data. This unique fusion methodology leverages advanced machine learning models, notably MedClip and BEiT, for sophisticated image feature extraction, setting a new standard in computational oncology. Our research surpasses existing approaches, as evidenced by a substantial enhancement in NSCLC detection and classification precision. The results showcase notable improvements across key performance metrics, including accuracy, precision, recall, and F1-score. Specifically, our leading multi-modal classifier model records an impressive accuracy of 94.04%. We believe that our approach has the potential to transform NSCLC diagnostics, facilitating earlier detection and more effective treatment planning and, ultimately, leading to superior patient outcomes in lung cancer care.

This study aims to comprehensively review and empirically evaluate the application of multimodal large language models (MLLMs) and Large Vision Models (VLMs) in object detection for transportation systems. In the first fold, we provide a background about the potential benefits of MLLMs in transportation applications and conduct a comprehensive review of current MLLM technologies in previous studies. We highlight their effectiveness and limitations in object detection within various transportation scenarios. The second fold involves providing an overview of the taxonomy of end-to-end object detection in transportation applications and future directions. Building on this, we proposed empirical analysis for testing MLLMs on three real-world transportation problems that include object detection tasks namely, road safety attributes extraction, safety-critical event detection, and visual reasoning of thermal images. Our findings provide a detailed assessment of MLLM performance, uncovering both strengths and areas for improvement. Finally, we discuss practical limitations and challenges of MLLMs in enhancing object detection in transportation, thereby offering a roadmap for future research and development in this critical area.

Context: The advent of Large Language Model-driven tools like ChatGPT offers software engineers an interactive alternative to community question-answering (CQA) platforms like Stack Overflow. While Stack Overflow provides benefits from the accumulated crowd-sourced knowledge, it often suffers from unpleasant comments, reactions, and long waiting times. Objective: In this study, we assess the efficacy of ChatGPT in providing solutions to software engineering questions by analyzing its performance specifically against human solutions. Method: We empirically analyze 2564 Python and JavaScript questions from StackOverflow that were asked between January 2022 and December 2022. We parse the questions and answers from Stack Overflow, then collect the answers to the same questions from ChatGPT through API, and employ four textual and four cognitive metrics to compare the answers generated by ChatGPT with the accepted answers provided by human subject matter experts to find out the potential reasons for which future knowledge seekers may prefer ChatGPT over CQA platforms. We also measure the accuracy of the answers provided by ChatGPT. We also measure user interaction on StackOverflow over the past two years using three metrics to determine how ChatGPT affects it. Results: Our analysis indicates that ChatGPT's responses are 66% shorter and share 35% more words with the questions, showing a 25% increase in positive sentiment compared to human responses. ChatGPT's answers' accuracy rate is between 71 to 75%, with a variation in response characteristics between JavaScript and Python. Additionally, our findings suggest a recent 38% decrease in comment interactions on Stack Overflow, indicating a shift in community engagement patterns. A supplementary survey with 14 Python and JavaScript professionals validated these findings.

A search for the very rare $B^{*0}\to\mu^+\mu^-$ and $B_{s}^{*0}\to\mu^+\mu^-$ decays is conducted by analysing the $B_c^+\to \pi^+\mu^+\mu^-$ process. The analysis uses proton-proton collision data collected with the LHCb detector between 2011 and 2018, corresponding to an integrated luminosity of 9$\text{\,fb}^{-1}$. The signal signatures correspond to simultaneous peaks in the $\mu^+\mu^-$ and $\pi^+\mu^+\mu^-$ invariant masses. No evidence for an excess of events over background is observed for either signal decay mode. Upper limits at the $90\%$ confidence level are set on the branching fractions relative to that for $B_c^+\to J\mskip -3mu/\mskip -2mu\psi\pi^+$ decays, \begin{align*} {\cal R}_{B^{*0}(\mu^+\mu^-)\pi^+/J\mskip -3mu/\mskip -2mu\psi\pi^+} &< 3.8\times 10^{-5}\ \text{ and } {\cal R}_{B_{s}^{*0}(\mu^+\mu^-)\pi^+/J\mskip -3mu/\mskip -2mu\psi\pi^+} &< 5.0\times 10^{-5}\,. \end{align*}, Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/1796/ (LHCb public pages)

The democratization of fabrication equipment has spurred recent interest in maskless grayscale lithography for both 2D and 3D microfabrication. However, the design of suitable template images remains a challenge. This work presents a simplified method for encoding 3D objects into grayscale image files optimized for grayscale lithography. Leveraging the widely used, open-source 3D modeling software Blender, we developed a robust approach to convert geometric heights into grayscale levels and generate image files through top-view rendering. Our method accurately reproduced the overall shape of simple structures like stairs and ramps compared to the original designs. We extended this approach to complex 3D sinusoidal surfaces, achieving similar results. Given the increasing accessibility and user-friendliness of digital rendering tools, this study offers a promising strategy for rapid prototyping of initial designs with minimal effort., Comment: 12 pages, 6 figures

A fundamental idea in wave mechanics is that propagation in a periodic medium can be described by Bloch waves whose conserved crystal momenta define their transformations when displaced by the set of discrete lattice translations. In ordered materials where incommensurate spatial periods compete, this general principle is rendered ineffective, often with dramatic consequences. Examples are crystals with broken symmetries from charge or spin density waves, quasiperiodic lattices that produce diffraction patterns with crystallographically forbidden point symmetries, and stacks of two-dimensional lattices with a relative rotation (twist) between layers. In special cases when there is a small difference between the competing periods, a useful work-around is a continuum description where a periodic long-wavelength field produces Bragg scattering that coherently mixes short-wavelength carrier waves. In this work, we advocate an alternative approach to study three-dimensional twisted crystals that replaces their spectrally congested momentum-space Bloch band structures with a representation using squeezed coherent states in a Fock space of free-particle vortex states. This reorganization of the Hilbert space highlights the crucial role of the Coriolis force in the equations of motion that leads to unconventional phase space dynamics and edge state structure generic to a family of complex crystals., Comment: 9 + 16 pages; 4 + 6 figures. Comments are very appreciated!

Peg-in-hole assembly in unknown environments is a challenging task due to onboard sensor errors, which result in uncertainty and variations in task parameters such as the hole position and orientation. Meta Reinforcement Learning (Meta RL) has been proposed to mitigate this problem as it learns how to quickly adapt to new tasks with different parameters. However, previous approaches either depend on a sample-inefficient procedure or human demonstrations to perform the task in the real world. Our work modifies the data used by the Meta RL agent and uses simple features that can be easily measured in the real world even with an uncalibrated camera. We further adapt the Meta RL agent to use data from a force/torque sensor, instead of the camera, to perform the assembly, using a small amount of training data. Finally, we propose a fine-tuning method that consistently and safely adapts to out-of-distribution tasks with parameters that differ by a factor of 10 from the training tasks. Our results demonstrate that the proposed data modification significantly enhances the training and adaptation efficiency and enables the agent to achieve 100% success in tasks with different hole positions and orientations. Experiments on a real robot confirm that both camera- and force/torque sensor-equipped agents achieve 100% success in tasks with unknown hole positions, matching their simulation performance and validating the approach's robustness and applicability. Compared to the previous work with sample-inefficient adaptation, our proposed methods are 10 times more sample-efficient in the real-world tasks., Comment: 8 pages, 9 figures, submitted to ICRA 2025

Tracking statements in the commit history of a project is in many cases useful for supporting various software maintenance, comprehension, and evolution tasks. A high level of accuracy can facilitate the adoption of code tracking tools by developers and researchers. To this end, we propose CodeTracker, a refactoring-aware tool that can generate the commit change history for code blocks. To evaluate its accuracy, we created an oracle with the change history of 1,280 code blocks found within 200 methods from 20 popular open-source project repositories. Moreover, we created a baseline based on the current state-of-the-art Abstract Syntax Tree diff tool, namely GumTree 3.0, in order to compare the accuracy and execution time. Our experiments have shown that CodeTracker has a considerably higher precision/recall and faster execution time than the GumTree-based baseline, and can extract the complete change history of a code block with a precision and recall of 99.5% within 3.6 seconds on average., Comment: IEEE Transactions on Software Engineering (submitted major revision)

We prove the universality of the joint distribution of an eigenvalue and the corresponding diagonal eigenvector overlap, in the bulk and at the edge, for eigenvalues of complex matrices and real eigenvalues of real matrices. As part of the proof we obtain a bound for the least non-zero singular value of $X-z$ when $z$ is an edge eigenvalue and a bound for the inner product between left and right singular vectors of $X-z$ when $|z|=1+O(N^{-1/2})$.

We explore the phenomenology of charged Higgs bosons ($H^\pm$) and Vector-Like Quarks (VLQs), specifically the top-like $T$, within the Two Higgs Doublet Model Type-II (2HDM-II). We consider both a singlet VLQ $(T)$ and a doublet $(TB)$ scenario, demonstrating that the presence of VLQs influences the scalar sector, particularly by alleviating the stringent mass constraints on $H^\pm$ imposed by $B$-physics observables such as $B\to X_s\gamma$. This relaxation arises from modifications in the couplings between $H^\pm$ and Standard Model (SM) quarks, with the magnitude of the effect differing between the singlet and doublet cases. We further analyse the constraints from the oblique parameters $S$ and $T$ on VLQ mixing angles., Comment: 6 pages, 4 figures, contribution to the 42nd International Conference on High Energy physics (ICHEP-2024)