Search

In the developing topic of smart cities, Vehicular Ad-Hoc Networks (VANETs) are crucial for providing successful interaction between vehicles and infrastructure. This research proposes a distributed Blockchain-based Vehicular Ad-hoc Network (DistB-VNET) architecture that includes binary malicious traffic classification, Software Defined Networking (SDN), and Network Function Virtualization (NFV) to ensure safe, scalable, and reliable vehicular networks in smart cities. The suggested framework is the decentralized blockchain for safe data management and SDN-NFV for dynamic network management and resource efficiency and a noble isolation forest algorithm works as an IDS (Intrusion Detection System). Further, "DistB-VNET" offers a dual-layer blockchain system, where a distributed blockchain provides safe communication between vehicles, while a centralized blockchain in the cloud is in charge of data verification and storage. This improves security, scalability, and adaptability, ensuring better traffic management, data security, and privacy in VANETs. Furthermore, the unsupervised isolation forest model achieves a high accuracy of 99.23% for detecting malicious traffic. Additionally, reveals that our method greatly improves network performance, offering decreased latency, increased security, and reduced congestion, an effective alternative for existing smart city infrastructures.

Assessing the importance of individual training samples is a key challenge in machine learning. Traditional approaches retrain models with and without specific samples, which is computationally expensive and ignores dependencies between data points. We introduce LossVal, an efficient data valuation method that computes importance scores during neural network training by embedding a self-weighting mechanism into loss functions like cross-entropy and mean squared error. LossVal reduces computational costs, making it suitable for large datasets and practical applications. Experiments on classification and regression tasks across multiple datasets show that LossVal effectively identifies noisy samples and is able to distinguish helpful from harmful samples. We examine the gradient calculation of LossVal to highlight its advantages. The source code is available at: https://github.com/twibiral/LossVal

Considerable study has already been conducted regarding autonomous driving in modern era. An autonomous driving system must be extremely good at detecting objects surrounding the car to ensure safety. In this paper, classification, and estimation of an object's (pedestrian) position (concerning an ego 3D coordinate system) are studied and the distance between the ego vehicle and the object in the context of autonomous driving is measured. To classify the object, faster Region-based Convolution Neural Network (R-CNN) with inception v2 is utilized. First, a network is trained with customized dataset to estimate the reference position of objects as well as the distance from the vehicle. From camera calibration to computing the distance, cutting-edge technologies of computer vision algorithms in a series of processes are applied to generate a 3D reference point of the region of interest. The foremost step in this process is generating a disparity map using the concept of stereo vision.

This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes semi-supervised learning algorithms in an iterative and adaptive multi-cycle process. The framework integrates multiple semi-supervised retraining algorithms, including FixMatch, FlexMatch, MixMatch, and FullMatch, to automate the retraining, evaluation, and testing of models with specified configurations. To assess the effectiveness of this approach, we conducted experiments on CIFAR-10, CIFAR-100, and MNIST datasets using a variety of image processing models, both pretrained and non-pretrained. Our results demonstrate the potential of metamorphic retraining to significantly improve model robustness as we show in our results that each model witnessed an increase of an additional flat 17 percent on average in our robustness metric.

This work demonstrates a systematic implementation of hybrid quantum-classical computational methods for investigating corrosion inhibition mechanisms on aluminum surfaces. We present an integrated workflow combining density functional theory (DFT) with quantum algorithms through an active space embedding scheme, specifically applied to studying 1,2,4-Triazole and 1,2,4-Triazole-3-thiol inhibitors on Al111 surfaces. Our implementation leverages the ADAPT-VQE algorithm with benchmarking against classical DFT calculations, achieving binding energies of -0.386 eV and -1.279 eV for 1,2,4-Triazole and 1,2,4-Triazole-3-thiol, respectively. The enhanced binding energy of the thiol derivative aligns with experimental observations regarding sulfur-functionalized inhibitors' improved corrosion protection. The methodology employs the orb-d3-v2 machine learning potential for rapid geometry optimizations, followed by accurate DFT calculations using CP2K with PBE functional and Grimme's D3 dispersion corrections. Our benchmarking on smaller systems reveals that StatefulAdaptVQE implementation achieves a 5-6x computational speedup while maintaining accuracy. This work establishes a workflow for quantum-accelerated materials science studying periodic systems, demonstrating the viability of hybrid quantum-classical approaches for studying surface-adsorbate interactions in corrosion inhibition applications. In which, can be transferable to other applications such as carbon capture and battery materials studies., Comment: 11 pages

Software security is crucial in any field where breaches can exploit sensitive data, and lead to financial losses. As a result, vulnerability detection becomes an essential part of the software development process. One of the key steps in maintaining software integrity is identifying vulnerabilities in the source code before deployment. A security breach like CWE-476, which stands for NULL pointer dereferences (NPD), is crucial because it can cause software crashes, unpredictable behavior, and security vulnerabilities. In this scientific era, there are several vulnerability checkers, where, previous tools often fall short in analyzing specific feature connections of the source code, which weakens the tools in real-world scenarios. In this study, we propose another novel approach using a fine-tuned Large Language Model (LLM) termed "DeLLNeuN". This model leverages the advantage of various layers to reduce both overfitting and non-linearity, enhancing its performance and reliability. Additionally, this method provides dropout and dimensionality reduction to help streamline the model, making it faster and more efficient. Our model showed 87% accuracy with 88% precision using the Draper VDISC dataset. As software becomes more complex and cyber threats continuously evolve, the need for proactive security measures will keep growing. In this particular case, the proposed model looks promising to use as an early vulnerability checker in software development.

After the introduction of Large Language Models (LLMs), there have been substantial improvements in the performance of Natural Language Generation (NLG) tasks, including Text Summarization and Machine Translation. However, LLMs still produce outputs containing hallucinations, that is, content not grounded in factual information. Therefore, developing methods to assess the factuality of LLMs has become urgent. Indeed, resources for factuality evaluation have recently emerged. Although challenging, these resources face one or more of the following limitations: (i) they are tailored to a specific task or domain; (ii) they are limited in size, thereby preventing the training of new factuality evaluators; (iii) they are designed for simpler verification tasks, such as claim verification. To address these issues, we introduce LLM-Oasis, to the best of our knowledge the largest resource for training end-to-end factuality evaluators. LLM-Oasis is constructed by extracting claims from Wikipedia, falsifying a subset of these claims, and generating pairs of factual and unfactual texts. We then rely on human annotators to both validate the quality of our dataset and to create a gold standard test set for benchmarking factuality evaluation systems. Our experiments demonstrate that LLM-Oasis presents a significant challenge for state-of-the-art LLMs, with GPT-4o achieving up to 60% accuracy in our proposed end-to-end factuality evaluation task, highlighting its potential to drive future research in the field., Comment: 15 pages. To be submitted to CL journal

In this paper, we study the problem of generating structured objects that conform to a complex schema, with intricate dependencies between the different components (facets) of the object. The facets of the object (attributes, fields, columns, properties) can be a mix of short, structured, type-constrained facts, or long natural-language descriptions. The object has to be self-consistent between the different facets in the redundant information it carries (relative consistency), while being grounded with respect to world knowledge (absolute consistency). We frame the problem as a Language Modeling problem (Structured Object Language Modeling) and train an LLM to perform the task natively, without requiring instructions or prompt-engineering. We propose a self-supervised denoising method to train the model from an existing dataset of such objects. The input query can be the existing object itself, in which case the model acts as a regenerator, completing, correcting, normalizing the input, or any unstructured blurb to be structured. We show that the self-supervised denoising training provides a strong baseline, and that additional supervised fine-tuning with small amount of human demonstrations leads to further improvement. Experimental results show that the proposed method matches or outperforms prompt-engineered general-purpose state-of-the-art LLMs (Claude 3, Mixtral-8x7B), while being order-of-magnitude more cost-efficient.

In software, a vulnerability is a defect in a program that attackers might utilize to acquire unauthorized access, alter system functions, and acquire information. These vulnerabilities arise from programming faults, design flaws, incorrect setups, and a lack of security protective measures. To mitigate these vulnerabilities, regular software upgrades, code reviews, safe development techniques, and the use of security tools to find and fix problems have been important. Several ways have been delivered in recent studies to address difficulties related to software vulnerabilities. However, previous approaches have significant limitations, notably in feature embedding and precisely recognizing specific vulnerabilities. To overcome these drawbacks, we present CodeGraphNet, an experimental method that combines GraphCodeBERT and Graph Convolutional Network (GCN) approaches, where, CodeGraphNet reveals data in a high-dimensional vector space, with comparable or related properties grouped closer together. This method captures intricate relationships between features, providing for more exact identification and separation of vulnerabilities. Using this feature embedding approach, we employed four machine learning models, applying both independent testing and 10-fold cross-validation. The DeepTree model, which is a hybrid of a Decision Tree and a Neural Network, outperforms state-of-the-art approaches. In additional validation, we evaluated our model using feature embeddings from LSA, GloVe, FastText, CodeBERT and GraphCodeBERT, and found that the CodeGraphNet method presented improved vulnerability identification with 98% of accuracy. Our model was tested on a real-time dataset to determine its capacity to handle real-world data and to focus on defect localization, which might influence future studies.

Cytology slides are essential tools in diagnosing and staging cancer, but their analysis is time-consuming and costly. Foundation models have shown great potential to assist in these tasks. In this paper, we explore how existing foundation models can be applied to cytological classification. More particularly, we focus on low-rank adaptation, a parameter-efficient fine-tuning method suited to few-shot learning. We evaluated five foundation models across four cytological classification datasets. Our results demonstrate that fine-tuning the pre-trained backbones with LoRA significantly improves model performance compared to fine-tuning only the classifier head, achieving state-of-the-art results on both simple and complex classification tasks while requiring fewer data samples., Comment: 5 pages, 2 figures

In this research, we explored the improvement in terms of multi-class disease classification via pre-trained language models over Medical-Abstracts-TC-Corpus that spans five medical conditions. We excluded non-cancer conditions and examined four specific diseases. We assessed four LLMs, BioBERT, XLNet, and BERT, as well as a novel base model (Last-BERT). BioBERT, which was pre-trained on medical data, demonstrated superior performance in medical text classification (97% accuracy). Surprisingly, XLNet followed closely (96% accuracy), demonstrating its generalizability across domains even though it was not pre-trained on medical data. LastBERT, a custom model based on the lighter version of BERT, also proved competitive with 87.10% accuracy (just under BERT's 89.33%). Our findings confirm the importance of specialized models such as BioBERT and also support impressions around more general solutions like XLNet and well-tuned transformer architectures with fewer parameters (in this case, LastBERT) in medical domain tasks., Comment: 7 Pages, 4 tables and 11 figures. Under review in a IEEE conference

The rapid spread of misinformation, particularly through online platforms, underscores the urgent need for reliable detection systems. This study explores the utilization of machine learning and natural language processing, specifically Support Vector Machines (SVM) and BERT, to detect news that are fake. We employ three distinct text vectorization methods for SVM: Term Frequency Inverse Document Frequency (TF-IDF), Word2Vec, and Bag of Words (BoW) evaluating their effectiveness in distinguishing between genuine and fake news. Additionally, we compare these methods against the transformer large language model, BERT. Our comprehensive approach includes detailed preprocessing steps, rigorous model implementation, and thorough evaluation to determine the most effective techniques. The results demonstrate that while BERT achieves superior accuracy with 99.98% and an F1-score of 0.9998, the SVM model with a linear kernel and BoW vectorization also performs exceptionally well, achieving 99.81% accuracy and an F1-score of 0.9980. These findings highlight that, despite BERT's superior performance, SVM models with BoW and TF-IDF vectorization methods come remarkably close, offering highly competitive performance with the advantage of lower computational requirements., Comment: 6 pages, 3 tables and 6 Figures. Submitted to a conference

6G's AI native vision of embedding advance intelligence in the network while bringing it closer to the user requires a systematic evaluation of Generative AI (GenAI) models on edge devices. Rapidly emerging solutions based on Open RAN (ORAN) and Network-in-a-Box strongly advocate the use of low-cost, off-the-shelf components for simpler and efficient deployment, e.g., in provisioning rural connectivity. In this context, conceptual architecture, hardware testbeds and precise performance quantification of Large Language Models (LLMs) on off-the-shelf edge devices remains largely unexplored. This research investigates computationally demanding LLM inference on a single commodity Raspberry Pi serving as an edge testbed for ORAN. We investigate various LLMs, including small, medium and large models, on a Raspberry Pi 5 Cluster using a lightweight Kubernetes distribution (K3s) with modular prompting implementation. We study its feasibility and limitations by analyzing throughput, latency, accuracy and efficiency. Our findings indicate that CPU-only deployment of lightweight models, such as Yi, Phi, and Llama3, can effectively support edge applications, achieving a generation throughput of 5 to 12 tokens per second with less than 50\% CPU and RAM usage. We conclude that GenAI on the edge offers localized inference in remote or bandwidth-constrained environments in 6G networks without reliance on cloud infrastructure.

In order to address issues with manual vote counting during election procedures, this study intends to examine the viability of using advanced image processing techniques for automated voter counting. The study aims to shed light on how automated systems that utilize cutting-edge technologies like OpenCV, CVZone, and the MOG2 algorithm could greatly increase the effectiveness and openness of electoral operations. The empirical findings demonstrate how automated voter counting can enhance voting processes and rebuild public confidence in election outcomes, particularly in places where trust is low. The study also emphasizes how rigorous metrics, such as the F1 score, should be used to systematically compare the accuracy of automated systems against manual counting methods. This methodology enables a detailed comprehension of the differences in performance between automated and human counting techniques by providing a nuanced assessment. The incorporation of said measures serves to reinforce an extensive assessment structure, guaranteeing the legitimacy and dependability of automated voting systems inside the electoral sphere., Comment: 13 Pages, 4 Figures

We study the rate-distortion problem for both scalar and vector memoryless heavy-tailed $\alpha$-stable sources ($0 < \alpha < 2$). Using a recently defined notion of ``strength" as a power measure, we derive the rate-distortion function for $\alpha$-stable sources subject to a constraint on the strength of the error, and show it to be logarithmic in the strength-to-distortion ratio. We showcase how our framework paves the way to finding optimal quantizers for $\alpha$-stable sources and more generally to heavy-tailed ones. In addition, we study high-rate scalar quantizers and show that uniform ones are asymptotically optimal under the strength measure. We compare uniform Gaussian and Cauchy quantizers and show that more representation points for the Cauchy source are required to guarantee the same quantization quality. Our findings generalize the well-known rate-distortion and quantization results of Gaussian sources ($\alpha = 2$) under a quadratic distortion measure., Comment: 28 pages, 6 figures

This work investigates the reproducibility of the paper 'Explaining RL decisions with trajectories'. The original paper introduces a novel approach in explainable reinforcement learning based on the attribution decisions of an agent to specific clusters of trajectories encountered during training. We verify the main claims from the paper, which state that (i) training on less trajectories induces a lower initial state value, (ii) trajectories in a cluster present similar high-level patterns, (iii) distant trajectories influence the decision of an agent, and (iv) humans correctly identify the attributed trajectories to the decision of the agent. We recover the environments used by the authors based on the partial original code they provided for one of the environments (Grid-World), and implemented the remaining from scratch (Seaquest, HalfCheetah, Breakout and Q*Bert). While we confirm that (i), (ii), and (iii) partially hold, we extend on the largely qualitative experiments from the authors by introducing a quantitative metric to further support (iii), and new experiments and visual results for (i). Moreover, we investigate the use of different clustering algorithms and encoder architectures to further support (ii). We could not support (iv), given the limited extent of the original experiments. We conclude that, while some of the claims can be supported, further investigations and experiments could be of interest. We recognise the novelty of the work from the authors and hope that our work paves the way for clearer and more transparent approaches.

In light of its many benefits, home automation systems are one of the subjects that are becoming ever more prevalent. The term "home automation" describes the remote monitoring and management of household equipment. The Internet and its usages are constantly expanding, which means there is a lot of room for remote access, management, and surveillance of these network-enabled systems. Nowadays, scientists and researchers are developing cutting-edge prototypes of home automation system which includes smart lighting system, smart kitchen, smart fire protection devices, smart lawn mower, smart health monitor system and so on. Each automated system's primary objective is its ability to reduce human labor, effort, time, and mistakes brought on by carelessness. The objective of this study is to provide in-depth evaluation of the newly developed home automation system. Moreover, state-of-the-art home automation topologies such as ZigBee, Z-wave, Wi-Fi and Bluetooth are also discussed here. The authors are optimistic that this study would have a major impact on the present advances in home automation technology.

We explore synergies between the Nancy Grace Roman Space Telescope High Latitude Wide Area Survey (HLWAS) and CMB experiments, specifically Simons Observatory (SO) and CMB-Stage4 (S4). Our simulated analyses include weak lensing, photometric galaxy clustering, CMB lensing, thermal SZ, and cross-correlations between these probes. While we assume the nominal 16,500 square degree area for SO and S4, we consider multiple survey designs for Roman that overlap with Rubin Observatory's Legacy Survey of Space and Time (LSST): the 2000 square degree reference survey using four photometric bands, and two shallower single-band surveys that cover 10,000 and 18,000 square degree, respectively. We find a ~2x increase in the dark energy figure of merit when including CMB-S4 data for all Roman survey designs. We further find a strong increase in constraining power for the Roman wide survey scenario cases, despite the reduction in galaxy number density, and the increased systematic uncertainties assumed due to the single band coverage. Even when tripling the already worse systematic uncertainties in the Roman wide scenarios, which reduces the 10,000 square degree FoM from 269 to 178, we find that the larger survey area is still significantly preferred over the reference survey (FoM 64). We conclude that for the specific analysis choices and metrics of this paper, a Roman wide survey is unlikely to be systematics-limited (in the sense that one saturates the improvement that can be obtained by increasing survey area). We outline several specific implementations of a two-tier Roman survey (1000 square degree with 4 bands, and a second wide tier in one band) that can further mitigate the risk of systematics for Roman wide concepts., Comment: Comments welcome!

A high resolution fourth-order Pad\'e scheme is used to simulate locally isothermal 3D disk turbulence driven by the vertical shear instability (VSI) using 268.4 M points. In the early non-linear period of axisymmetric VSI, angular momentum transport by vertical jets creates correlated N-shaped radial profiles of perturbation vertical and azimuthal velocity. This implies dominance of positive perturbation vertical vorticity layers and a recently discovered angular momentum staircase with respect to radius ($r$). These features are present in 3D in a weaker form. The 3D flow consists of vertically and azimuthally coherent turbulent shear layers containing small vortices with all three vorticity components active. Previously observed large persistent vortices in the interior of the domain driven by the Rossby wave instability are absent. We speculate that this is due to a weaker angular momentum staircase in 3D in the present simulations compared to a previous simulation. The turbulent viscosity parameter $\alpha(r)$ increases linearly with $r$. At intermediate resolution, the value of $\alpha(r)$ at midradius is close to that of a previous simulation. The specific kinetic energy spectrum with respect to radial wavenumber has a power law region with exponent $-1.84$, close to the value $-2$ expected for shear layers. The spectrum with respect to azimuthal wavenumber has a $-5/3$ region and lacks a $-5$ region reported in an earlier study. Finally, it is found that axisymmetric VSI has artifacts at late times, including a very strong angular momentum staircase, which in 3D is present weakly in the disk's upper layers.

Personalized medicine (PM) promises to transform healthcare by providing treatments tailored to individual genetic, environmental, and lifestyle factors. However, its high costs and infrastructure demands raise concerns about exacerbating health disparities, especially between high-income countries (HICs) and low- and middle-income countries (LMICs). While HICs benefit from advanced PM applications through AI and genomics, LMICs often lack the resources necessary to adopt these innovations, leading to a widening healthcare divide. This paper explores the financial and ethical challenges of PM implementation, with a focus on ensuring equitable access. It proposes strategies for global collaboration, infrastructure development, and ethical frameworks to support LMICs in adopting PM, aiming to prevent further disparities in healthcare accessibility and outcomes., Comment: 30 pages, 1 figure

Philosophers have claimed that: (a) the Born-Oppenheimer approximation methods for solving molecular Schr\"odinger equations violate the Heisenberg uncertainty relations; therefore (b) so-called `quantum chemistry' is not fully quantum; and so (c) chemistry does not reduce to physics. This paper analyses the reasoning behind Born-Oppenheimer methods and shows that they are internally consistent and fully quantum mechanical, contrary to (a)-(c). Our analysis addresses important issues of mathematical rigour, physical idealisation, reduction, and classicality in the quantum theory of molecules, and we propose an agenda for the philosophy of quantum chemistry more solidly grounded in scientific practice.

This paper consider a new and deeply challenging face of the problem of time in the context of cosmology drawing on the work of Thiemann (2006). Thiemann argues for a radical response to cosmic problem of time that requires us to modify the classical Friedmann equations. By contrast, we offer a conservative proposal for solution of the problem by bringing together ideas from the contemporary literature regarding reference frames (Bamonti 2023; Bamonti and Gomes 2024), complete observables (Gryb and Th\'ebault 2016, 2023), and the model-based account of time measurement (Tal 2016). On our approach, we must reinterpret our criteria of observability in light of the clock hypothesis and the model-based account of measurement in order to preserve the Friedmann equations as the dynamical equations for the universe.

Differential diagnosis is crucial for medicine as it helps healthcare providers systematically distinguish between conditions that share similar symptoms. This study assesses the impact of lab test results on differential diagnoses (DDx) made by large language models (LLMs). Clinical vignettes from 50 case reports from PubMed Central were created incorporating patient demographics, symptoms, and lab results. Five LLMs GPT-4, GPT-3.5, Llama-2-70b, Claude-2, and Mixtral-8x7B were tested to generate Top 10, Top 5, and Top 1 DDx with and without lab data. A comprehensive evaluation involving GPT-4, a knowledge graph, and clinicians was conducted. GPT-4 performed best, achieving 55% accuracy for Top 1 diagnoses and 60% for Top 10 with lab data, with lenient accuracy up to 80%. Lab results significantly improved accuracy, with GPT-4 and Mixtral excelling, though exact match rates were low. Lab tests, including liver function, metabolic/toxicology panels, and serology/immune tests, were generally interpreted correctly by LLMs for differential diagnosis.

To learn large sets of scenes, Tri-Planes are commonly employed for their planar structure that enables an interoperability with image models, and thus diverse 3D applications. However, this advantage comes at the cost of resource efficiency, as Tri-Planes are not the most computationally efficient option. In this paper, we introduce Fused-Planes, a new planar architecture that improves Tri-Planes resource-efficiency in the framework of learning large sets of scenes, which we call "multi-scene inverse graphics". To learn a large set of scenes, our method divides it into two subsets and operates as follows: (i) we train the first subset of scenes jointly with a compression model, (ii) we use that compression model to learn the remaining scenes. This compression model consists of a 3D-aware latent space in which Fused-Planes are learned, enabling a reduced rendering resolution, and shared structures across scenes that reduce scene representation complexity. Fused-Planes present competitive resource costs in multi-scene inverse graphics, while preserving Tri-Planes rendering quality, and maintaining their widely favored planar structure. Our codebase is publicly available as open-source. Our project page can be found at https://fused-planes.github.io .

This work focuses on the efficiency of the knowledge distillation approach in generating a lightweight yet powerful BERT based model for natural language processing applications. After the model creation, we applied the resulting model, LastBERT, to a real-world task classifying severity levels of Attention Deficit Hyperactivity Disorder (ADHD)-related concerns from social media text data. Referring to LastBERT, a customized student BERT model, we significantly lowered model parameters from 110 million BERT base to 29 million, resulting in a model approximately 73.64% smaller. On the GLUE benchmark, comprising paraphrase identification, sentiment analysis, and text classification, the student model maintained strong performance across many tasks despite this reduction. The model was also used on a real-world ADHD dataset with an accuracy and F1 score of 85%. When compared to DistilBERT (66M) and ClinicalBERT (110M), LastBERT demonstrated comparable performance, with DistilBERT slightly outperforming it at 87%, and ClinicalBERT achieving 86% across the same metrics. These findings highlight the LastBERT model's capacity to classify degrees of ADHD severity properly, so it offers a useful tool for mental health professionals to assess and comprehend material produced by users on social networking platforms. The study emphasizes the possibilities of knowledge distillation to produce effective models fit for use in resource-limited conditions, hence advancing NLP and mental health diagnosis. Furthermore underlined by the considerable decrease in model size without appreciable performance loss is the lower computational resources needed for training and deployment, hence facilitating greater applicability. Especially using readily available computational tools like Google Colab. This study shows the accessibility and usefulness of advanced NLP methods in pragmatic world applications., Comment: 20 figures, 31 pages, review 1 from plos one journal

Organizational success in todays competitive employment market depends on choosing the right staff. This work evaluates software engineer profiles using an automated staff selection method based on advanced natural language processing (NLP) techniques. A fresh dataset was generated by collecting LinkedIn profiles with important attributes like education, experience, skills, and self-introduction. Expert feedback helped transformer models including RoBERTa, DistilBERT, and a customized BERT variation, LastBERT, to be adjusted. The models were meant to forecast if a candidate's profile fit the selection criteria, therefore allowing automated ranking and assessment. With 85% accuracy and an F1 score of 0.85, RoBERTa performed the best; DistilBERT provided comparable results at less computing expense. Though light, LastBERT proved to be less effective, with 75% accuracy. The reusable models provide a scalable answer for further categorization challenges. This work presents a fresh dataset and technique as well as shows how transformer models could improve recruiting procedures. Expanding the dataset, enhancing model interpretability, and implementing the system in actual environments will be part of future activities., Comment: 6 pages, 12 figures, conference paper

While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides reducing the training and rendering complexity, applying inverse graphics in the latent space enables a valuable interoperability with other latent-based 2D methods. The major challenge is that inverse graphics cannot be directly applied to such image latent spaces because they lack an underlying 3D geometry. In this paper, we propose an Inverse Graphics Autoencoder (IG-AE) that specifically addresses this issue. To this end, we regularize an image autoencoder with 3D-geometry by aligning its latent space with jointly trained latent 3D scenes. We utilize the trained IG-AE to bring NeRFs to the latent space with a latent NeRF training pipeline, which we implement in an open-source extension of the Nerfstudio framework, thereby unlocking latent scene learning for its supported methods. We experimentally confirm that Latent NeRFs trained with IG-AE present an improved quality compared to a standard autoencoder, all while exhibiting training and rendering accelerations with respect to NeRFs trained in the image space. Our project page can be found at https://ig-ae.github.io ., Comment: Accepted at ICLR 2025. Available at https://openreview.net/forum?id=LTDtjrv02Y

Robust modeling of non-linear scales is critical for accurate cosmological inference in Stage IV surveys. For weak lensing analyses in particular, a key challenge arises from the incomplete understanding of how non-gravitational processes, such as supernovae and active galactic nuclei - collectively known as baryonic feedback - affect the matter distribution. Several existing methods for modeling baryonic feedback treat it independently from the underlying cosmology, an assumption which has been found to be inaccurate by hydrodynamical simulations. In this work, we examine the impact of this coupling between baryonic feedback and cosmology on parameter inference at LSST Y1 precision. We build mock 3$\times$2pt data vectors using the Magneticum suite of hydrodynamical simulations, which span a wide range of cosmologies while keeping subgrid parameters fixed. We perform simulated likelihood analyses for two baryon mitigation techniques: (i) the Principal Component Analysis (PCA) method which identifies eigenmodes for capturing the effect baryonic feedback on the data vector and (ii) HMCode2020 (Mead et al. 2021) which analytically models the modification in the matter distribution using a halo model approach. Our results show that the PCA method is robust to the coupling between cosmology and baryonic feedback, whereas, when using HMCode2020 there can be up to $0.5\sigma$ bias in $\Omega_\text{m}$-$S_8$. For HMCode2020, the bias also correlates with the input cosmology while for PCA we find no such correlation., Comment: correction to acknowledgements

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. However, achieving effective dual-arm manipulation is challenging due to the need for precise coordination, dynamic adaptability, and the ability to manage interaction forces between the arms and the objects being manipulated. We propose a novel pipeline that combines the advantages of policy learning based on environment feedback and gradient-based optimization to learn controller gains required for the control outputs. This allows the robotic system to dynamically modulate its impedance in response to task demands, ensuring stability and dexterity in dual-arm operations. We evaluate our pipeline on a trajectory-tracking task involving a variety of large, complex objects with different masses and geometries. The performance is then compared to three other established methods for controlling dual-arm robots, demonstrating superior results.

Decision-making for automated driving remains a challenging task. For their integration into real platforms, these algorithms must guarantee passenger safety and comfort while ensuring interpretability and an appropriate computational time. To model and solve this decision-making problem, we have developed a novel approach called COR-MP (Conservation of Resources model for Maneuver Planning). This model is based on the Conservation of Resources theory, a psychological concept applied to human behavior. COR-MP is based on various driving parameters, such as comfort, safety, or energy, and provides in real-time a profit value that enables us to quantify the impact of a decision on the decision-maker. Our method has been tested and validated through closed-loop simulations using RTMaps middleware, and preliminary results have been obtained by testing COR-MP on a real vehicle., Comment: 8 pages, 6 figures

Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improving the efficiency of LLM inference by enabling next token prediction at intermediate layers. Yet, the large vocabulary size in modern LLMs makes the confidence estimation required for exit decisions computationally expensive, diminishing the efficiency gains. To address this, we propose dynamically pruning the vocabulary at test time for each token. Specifically, the vocabulary is pruned at one of the initial layers, and the smaller vocabulary is then used throughout the rest of the forward pass. Our experiments demonstrate that such post-hoc dynamic vocabulary pruning improves the efficiency of confidence estimation in early-exit LLMs while maintaining competitive performance.

Experimental searches for supersymmetry (SUSY) are entering a new era. The failure to observe signals of sparticle production at the Large Hadron Collider (LHC) has eroded the central motivation for SUSY breaking at the weak scale. However, String Theory requires SUSY at the fundamental scale $M_s$ and hence SUSY could be broken at some high scale below $M_s$. Actually, if this were the case, the lack of experimental evidence for low-energy SUSY could have been anticipated, because most stringy models with high-scale SUSY breaking predict that sparticles would start popping up above about 10 TeV, well beyond the reach of current LHC experiments. We show that using next generation LHC experiments currently envisioned for the Forward Physics Facility (FPF) we could search for signals of neutrino-modulino oscillations to probe models with string scale in the grand unification region and SUSY breaking driven by sequestered gravity in gauge mediation. This is possible because of the unprecedented flux of neutrinos to be produced as secondary products in LHC collisions during the high-luminosity era and the capability of FPF experiments to detect and identify their flavors., Comment: Matching version to be published in EPJC. arXiv admin note: text overlap with arXiv:2308.11476

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. To mitigate the extensive computational and communication overhead often associated with LLMs, we utilize a parameter-efficient fine-tuning method, specifically Low-Rank Adaptation (LoRA), reducing the number of trainable parameters. Experimental results, with different datasets and models, demonstrate the proposed method's effectiveness compared to existing frameworks for federated fine-tuning of LLMs in terms of average and local performances. The proposed scheme outperforms existing baselines by achieving lower local loss for each client while maintaining comparable global performance.

This Research proposes a Novel Reinforcement Learning (RL) model to optimise malware forensics investigation during cyber incident response. It aims to improve forensic investigation efficiency by reducing false negatives and adapting current practices to evolving malware signatures. The proposed RL framework leverages techniques such as Q-learning and the Markov Decision Process (MDP) to train the system to identify malware patterns in live memory dumps, thereby automating forensic tasks. The RL model is based on a detailed malware workflow diagram that guides the analysis of malware artefacts using static and behavioural techniques as well as machine learning algorithms. Furthermore, it seeks to address challenges in the UK justice system by ensuring the accuracy of forensic evidence. We conduct testing and evaluation in controlled environments, using datasets created with Windows operating systems to simulate malware infections. The experimental results demonstrate that RL improves malware detection rates compared to conventional methods, with the RL model's performance varying depending on the complexity and learning rate of the environment. The study concludes that while RL offers promising potential for automating malware forensics, its efficacy across diverse malware types requires ongoing refinement of reward systems and feature extraction methods., Comment: v3, 8 pages. arXiv admin note: substantial text overlap with arXiv:2408.01999

Road Extraction is a sub-domain of Remote Sensing applications; it is a subject of extensive and ongoing research. The procedure of automatically extracting roads from satellite imagery encounters significant challenges due to the multi-scale and diverse structures of roads; improvement in this field is needed. The DeepLab series, known for its proficiency in semantic segmentation due to its efficiency in interpreting multi-scale objects' features, addresses some of these challenges caused by the varying nature of roads. The present work proposes the utilization of DeepLabV3+, the latest version of the DeepLab series, by introducing an innovative Dense Depthwise Dilated Separable Spatial Pyramid Pooling (DenseDDSSPP) module and integrating it in place of the conventional Atrous Spatial Pyramid Pooling (ASPP) module. This modification enhances the extraction of complex road structures from satellite images. This study hypothesizes that the integration of DenseDDSSPP, combined with an appropriately selected backbone network and a Squeeze-and-Excitation block, will generate an efficient dense feature map by focusing on relevant features, leading to more precise and accurate road extraction from Remote Sensing images. The results section presents a comparison of our model's performance against state-of-the-art models, demonstrating better results that highlight the effectiveness and success of the proposed approach., Comment: 9 pages, 5 figures

Markov processes serve as a universal model for many real-world random processes. This paper presents a data-driven approach for learning these models through the spectral decomposition of the infinitesimal generator (IG) of the Markov semigroup. The unbounded nature of IGs complicates traditional methods such as vector-valued regression and Hilbert-Schmidt operator analysis. Existing techniques, including physics-informed kernel regression, are computationally expensive and limited in scope, with no recovery guarantees for transfer operator methods when the time-lag is small. We propose a novel method that leverages the IG's resolvent, characterized by the Laplace transform of transfer operators. This approach is robust to time-lag variations, ensuring accurate eigenvalue learning even for small time-lags. Our statistical analysis applies to a broader class of Markov processes than current methods while reducing computational complexity from quadratic to linear in the state dimension. Finally, we illustrate the behaviour of our method in two experiments., Comment: 35 pages

In 2020, Coregliano and Razborov introduced a general framework to study limits of combinatorial objects, using logic and model theory. They introduced the abstract chromatic number and proved/reproved multiple Erd\H{o}s-Stone-Simonovits-type theorems in different settings. In 2022, Coregliano extended this by showing that similar results hold when we count copies of $K_t$ instead of edges. Our aim is threefold. First, we provide a purely combinatorial approach. Second, we extend their results by showing several other graph parameters and other settings where Erd\H{o}s-Stone-Simonovits-type theorems follow. Third, we go beyond determining asymptotics and obtain corresponding stability, supersaturation, and sometimes even exact results., Comment: 12 pages

Deep learning is making a profound impact in the physical layer of wireless communications. Despite exhibiting outstanding empirical performance in tasks such as MIMO receive processing, the reasons behind the demonstrated superior performance improvement remain largely unclear. In this work, we advance the field of Explainable AI (xAI) in the physical layer of wireless communications utilizing signal processing principles. Specifically, we focus on the task of MIMO-OFDM receive processing (e.g., symbol detection) using reservoir computing (RC), a framework within recurrent neural networks (RNNs), which outperforms both conventional and other learning-based MIMO detectors. Our analysis provides a signal processing-based, first-principles understanding of the corresponding operation of the RC. Building on this fundamental understanding, we are able to systematically incorporate the domain knowledge of wireless systems (e.g., channel statistics) into the design of the underlying RNN by directly configuring the untrained RNN weights for MIMO-OFDM symbol detection. The introduced RNN weight configuration has been validated through extensive simulations demonstrating significant performance improvements. This establishes a foundation for explainable RC-based architectures in MIMO-OFDM receive processing and provides a roadmap for incorporating domain knowledge into the design of neural networks for NextG systems.

Mediation is a dispute resolution method featuring a neutral third-party (mediator) who intervenes to help the individuals resolve their dispute. In this paper, we investigate to which extent large language models (LLMs) are able to act as mediators. We investigate whether LLMs are able to analyze dispute conversations, select suitable intervention types, and generate appropriate intervention messages. Using a novel, manually created dataset of 50 dispute scenarios, we conduct a blind evaluation comparing LLMs with human annotators across several key metrics. Overall, the LLMs showed strong performance, even outperforming our human annotators across dimensions. Specifically, in 62% of the cases, the LLMs chose intervention types that were rated as better than or equivalent to those chosen by humans. Moreover, in 84% of the cases, the intervention messages generated by the LLMs were rated as better than or equal to the intervention messages written by humans. LLMs likewise performed favourably on metrics such as impartiality, understanding and contextualization. Our results demonstrate the potential of integrating AI in online dispute resolution (ODR) platforms.

Amorphous solids form an enormous and underutilized class of materials. In order to drive the discovery of new useful amorphous materials further we need to achieve a closer convergence between computational and experimental methods. In this review, we highlight some of the important gaps between computational simulations and experiments, discuss popular state-of-the-art computational techniques such as the Activation Relaxation Technique nouveau (ARTn) and Reverse Monte Carlo (RMC), and introduce more recent advances: machine learning interatomic potentials (MLIPs) and generative machine learning for simulations of amorphous matter, e.g., the Morphological Autoregressive Protocol (MAP). Examples are drawn from the amorphous silicon and silica literature as well as from molecular glasses. Our outlook stresses the need for new computational methods to extend the time- and length- scales accessible through numerical simulations.

This study examines the challenges hospitals encounter in managing human resources and proposes potential solutions. It provides an overview of current HR practices in hospitals, highlighting key issues affecting recruitment, retention, and professional development of medical staff. The study further explores how these challenges impact patient outcomes and overall hospital performance. A comprehensive framework for effective human resource man agement is presented, outlining strategies for recruiting, retaining, training, and advancing medical professionals. This framework is informed by industry best practices and the latest research in healthcare HR management. The findings underscore that effective HR management is crucial for hospital success and offer recommendations for executives and policymakers to enhance their HR strategies. Additionally, our project introduces a Dropbox feature to facilitate patient care. This allows patients to report their issues, enabling doctors to quickly address ailments via our app. Patients can easily identify local doctors and schedule appointments. The app will also provide emergency medical services and accept online payments, while maintaining a record of patient interactions. Both patients and doctors can file complaints through the app, ensuring appropriate follow-up actions., Comment: 13 pages, 12 figures

Vehicle-to-everything (V2X) communication technology is revolutionizing transportation by enabling interactions between vehicles, devices, and infrastructures. This connectivity enhances road safety, transportation efficiency, and driver assistance systems. V2X benefits from Machine Learning, enabling real-time data analysis, better decision-making, and improved traffic predictions, making transportation safer and more efficient. In this paper, we study the problem of joint channel selection, where vehicles with different technologies choose one or more Access Points (APs) to transmit messages in a network. In this problem, vehicles must learn a strategy for channel selection, based on observations that incorporate vehicles' information (position and speed), network and communication data (Signal-to-Interference-plus-Noise Ratio from past communications), and environmental data (road type). We propose an approach based on Federated Deep Reinforcement Learning (FedDRL), which enables each vehicle to benefit from other vehicles' experiences. Specifically, we apply the federated Proximal Policy Optimization (FedPPO) algorithm to this task. We show that this method improves communication reliability while minimizing transmission costs and channel switches. The efficiency of the proposed solution is assessed via realistic simulations, highlighting the potential of FedDRL to advance V2X technology.

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. We release our code at \url{https://github.com/amazon-science/SigExt}, Comment: Accepted to EMNLP 2024 Industry Track. Code available at https://github.com/amazon-science/SigExt

This paper introduces a new hybrid descriptor for 3D point matching and point cloud registration, combining local geometrical properties and learning-based feature propagation for each point's neighborhood structure description. The proposed architecture first extracts prior geometrical information by computing each point's planarity, anisotropy, and omnivariance using a Principal Components Analysis (PCA). This prior information is completed by a descriptor based on the normal vectors estimated thanks to constructing a neighborhood based on triangles. The final geometrical descriptor is propagated between the points using local graph convolutions and attention mechanisms. The new feature extractor is evaluated on ModelNet40, Bunny Stanford dataset, KITTI and MVP (Multi-View Partial)-RG for point cloud registration and shows interesting results, particularly on noisy and low overlapping point clouds.

One cannot justifiably presuppose the physical salience of structures derived via decoherence theory based upon an entirely uninterpreted use of the quantum formalism. Non-probabilistic accounts of the emergence of probability via decoherence are unconvincing. An alternative account of the emergence of probability involves the combination of a partially interpreted decoherence model and an averaging of observables with respect to a positive-definite quasi-probability function and neglect of terms $O(\hbar)$. Our analysis delimits the context in which the combination of decoherence and a semi-classical averaging allows us to recover a classical probability model within an emergent coarse-grained description.

Extending many-body numerical techniques which are powerful in the context of simple model calculations to the realm of realistic material simulations can be a challenging task. Realistic systems often involve multiple active orbitals, which increases the complexity and numerical cost because of the large local Hilbert space and the large number of interaction terms or sign-changing off-diagonal Green's functions. The two-particle self-consistent approach (TPSC) is one such many-body numerical technique, for which multi-orbital extensions have proven to be involved due to the substantially more complex structure of the local interaction tensor. In this paper we extend earlier multi-orbital generalizations of TPSC by setting up two different variants of a fully self-consistent theory for TPSC in multi-orbital systems. We first investigate the strengths and limitations of the approach analytically and then benchmark both variants against dynamical mean-field theory (DMFT) and D-TRILEX results. We find that the exact behavior of the system can be faithfully reproduced in the weak-coupling regime, while at stronger couplings the performance of the two TPSC variants strongly depends on details of the system., Comment: 17 pages, 5 figures