Search

Identification of suspects based on partial and smudged fingerprints, commonly referred to as fingermarks or latent fingerprints, presents a significant challenge in the field of fingerprint recognition. Although fixed-length embeddings have shown effectiveness in recognising rolled and slap fingerprints, the methods for matching latent fingerprints have primarily centred around local minutiae-based embeddings, failing to fully exploit global representations for matching purposes. Consequently, enhancing latent fingerprints becomes critical to ensuring robust identification for forensic investigations. Current approaches often prioritise restoring ridge patterns, overlooking the fine-macroeconomic details crucial for accurate fingerprint recognition. To address this, we propose a novel approach that uses generative adversary networks (GANs) to redefine Latent Fingerprint Enhancement (LFE) through a structured approach to fingerprint generation. By directly optimising the minutiae information during the generation process, the model produces enhanced latent fingerprints that exhibit exceptional fidelity to ground-truth instances. This leads to a significant improvement in identification performance. Our framework integrates minutiae locations and orientation fields, ensuring the preservation of both local and structural fingerprint features. Extensive evaluations conducted on two publicly available datasets demonstrate our method's dominance over existing state-of-the-art techniques, highlighting its potential to significantly enhance latent fingerprint recognition accuracy in forensic applications.

This paper introduces the concept of an education tool that utilizes Generative Artificial Intelligence (GenAI) to enhance storytelling for children. The system combines GenAI-driven narrative co-creation, text-to-speech conversion, and text-to-video generation to produce an engaging experience for learners. We describe the co-creation process, the adaptation of narratives into spoken words using text-to-speech models, and the transformation of these narratives into contextually relevant visuals through text-to-video technology. Our evaluation covers the linguistics of the generated stories, the text-to-speech conversion quality, and the accuracy of the generated visuals.

This paper presents a comprehensive evaluation of Urdu Automatic Speech Recognition (ASR) models. We analyze the performance of three ASR model families: Whisper, MMS, and Seamless-M4T using Word Error Rate (WER), along with a detailed examination of the most frequent wrong words and error types including insertions, deletions, and substitutions. Our analysis is conducted using two types of datasets, read speech and conversational speech. Notably, we present the first conversational speech dataset designed for benchmarking Urdu ASR models. We find that seamless-large outperforms other ASR models on the read speech dataset, while whisper-large performs best on the conversational speech dataset. Furthermore, this evaluation highlights the complexities of assessing ASR models for low-resource languages like Urdu using quantitative metrics alone and emphasizes the need for a robust Urdu text normalization system. Our findings contribute valuable insights for developing robust ASR systems for low-resource languages like Urdu.

Big data processing has exposed the limits of compute-centric hardware acceleration due to the memory-to-processor bandwidth bottleneck. Consequently, there has been a shift towards memory-centric architectures, leveraging substantial compute parallelism by processing using the memory elements directly. Computing-in-memory (CIM) proposals for both conventional and emerging memory technologies often target massively parallel operations. However, current CIM solutions face significant challenges. For emerging data-intensive applications, such as advanced machine learning techniques and bioinformatics, where matrix multiplication is a key primitive, memristor crossbars suffer from limited write endurance and expensive write operations. In contrast, while DRAM-based solutions have successfully demonstrated multiplication using additions, they remain prohibitively slow. This paper introduces Count2Multiply, a technology-agnostic digital-CIM method for performing integer-binary and integer-integer matrix multiplications using high-radix, massively parallel counting implemented with bitwise logic operations. In addition, Count2Multiply is designed with fault tolerance in mind and leverages traditional scalable row-wise error correction codes, such as Hamming and BCH codes, to protect against the high error rates of existing CIM designs. We demonstrate Count2Multiply with a detailed application to CIM in conventional DRAM due to its ubiquity and high endurance. We also explore the acceleration potential of racetrack memories due to their shifting properties, which are natural for Count2Multiply, and their high endurance. Compared to the state-of-the-art in-DRAM method, Count2Multiply achieves up to 10x speedup, 3.8x higher GOPS/Watt, and 1.4x higher GOPS/area, while the RTM counterpart offers gains of 10x, 57x, and 3.8x., Comment: 14 pages

This paper presents the concept of Industry 6.0, introducing the world's first fully automated production system that autonomously handles the entire product design and manufacturing process based on user-provided natural language descriptions. By leveraging generative AI, the system automates critical aspects of production, including product blueprint design, component manufacturing, logistics, and assembly. A heterogeneous swarm of robots, each equipped with individual AI through integration with Large Language Models (LLMs), orchestrates the production process. The robotic system includes manipulator arms, delivery drones, and 3D printers capable of generating assembly blueprints. The system was evaluated using commercial and open-source LLMs, functioning through APIs and local deployment. A user study demonstrated that the system reduces the average production time to 119.10 minutes, significantly outperforming a team of expert human developers, who averaged 528.64 minutes (an improvement factor of 4.4). Furthermore, in the product blueprinting stage, the system surpassed human CAD operators by an unprecedented factor of 47, completing the task in 0.5 minutes compared to 23.5 minutes. This breakthrough represents a major leap towards fully autonomous manufacturing., Comment: submitted to IEEE conf

With the rise in the wholesale adoption of Deep Learning (DL) models in nearly all aspects of society, a unique set of challenges is imposed. Primarily centered around the architectures of these models, these risks pose a significant challenge, and addressing these challenges is key to their successful implementation and usage in the future. In this research, we present the security challenges associated with the current DL models deployed into production, as well as anticipate the challenges of future DL technologies based on the advancements in computing, AI, and hardware technologies. In addition, we propose risk mitigation techniques to inhibit these challenges and provide metrical evaluations to measure the effectiveness of these metrics., Comment: 10 pages, 1 table, 6 equations/metrics

In this paper, we propose an algorithm for registering sequential bounding boxes with point cloud streams. Unlike popular point cloud registration techniques, the alignment of the point cloud and the bounding box can rely on the properties of the bounding box, such as size, shape, and temporal information, which provides substantial support and performance gains. Motivated by this, we propose a new approach to tackle this problem. Specifically, we model the registration process through an overall objective function that includes the final goal and all constraints. We then optimize the function using gradient descent. Our experiments show that the proposed method performs remarkably well with a 40\% improvement in IoU and demonstrates more robust registration between point cloud streams and sequential bounding boxes

We study multi-component dark matter scenarios and the Galactic 511 keV $\gamma$-ray emission line signal in the framework of a local, dark $U(1)_D$ extension of the Standard Model. A light vector dark matter particle associated with the dark $U(1)_D$ may decay and annihilate to electron-positron pairs. The produced positrons may in turn form positroniums that subsequently annihilate to two photons, accounting for the observed line signal of the Galactic 511 keV $\gamma$-ray emission. Three scenarios are investigated. First, we consider the minimal $U(1)_D$ extension where a dark gauge boson and a dark Higgs boson are newly introduced to the particle content. As a second scenario, we consider WIMP-type dark matter with the introduction of an extra dark fermion which, in addition to the dark gauge boson, may contribute to the dark matter relic abundance. It is thus a multi-component dark matter scenario with a UV-complete dark $U(1)_D$ symmetry. In particular, the vector dark matter may account for a small fraction of the total dark matter relic abundance. Finally, we consider the scenario where the dark matter particles are of the FIMP-type. In this case, both the light vector and fermion dark matter particles may be produced via the freeze-in and super-WIMP mechanisms. Considering theoretical and observational constraints, we explore the allowed parameter space where the Galactic 511 keV $\gamma$-ray line signal and the dark matter relic can both be explained. We also discuss possible observational signatures., Comment: 29 pages

Autonomous robots use simultaneous localization and mapping (SLAM) for efficient and safe navigation in various environments. LiDAR sensors are integral in these systems for object identification and localization. However, LiDAR systems though effective in detecting solid objects (e.g., trash bin, bottle, etc.), encounter limitations in identifying semitransparent or non-tangible objects (e.g., fire, smoke, steam, etc.) due to poor reflecting characteristics. Additionally, LiDAR also fails to detect features such as navigation signs and often struggles to detect certain hazardous materials that lack a distinct surface for effective laser reflection. In this paper, we propose a highly accurate stereo-vision approach to complement LiDAR in autonomous robots. The system employs advanced stereo vision-based object detection to detect both tangible and non-tangible objects and then uses simple machine learning to precisely estimate the depth and size of the object. The depth and size information is then integrated into the SLAM process to enhance the robot's navigation capabilities in complex environments. Our evaluation, conducted on an autonomous robot equipped with LiDAR and stereo-vision systems demonstrates high accuracy in the estimation of an object's depth and size. A video illustration of the proposed scheme is available at: \url{https://www.youtube.com/watch?v=nusI6tA9eSk}., Comment: Accepted version of the published article in IEEE Sensors Letters

The rising use of Large Language Models (LLMs) to create and disseminate malware poses a significant cybersecurity challenge due to their ability to generate and distribute attacks with ease. A single prompt can initiate a wide array of malicious activities. This paper addresses this critical issue through a multifaceted approach. First, we provide a comprehensive overview of LLMs and their role in malware detection from diverse sources. We examine five specific applications of LLMs: Malware honeypots, identification of text-based threats, code analysis for detecting malicious intent, trend analysis of malware, and detection of non-standard disguised malware. Our review includes a detailed analysis of the existing literature and establishes guiding principles for the secure use of LLMs. We also introduce a classification scheme to categorize the relevant literature. Second, we propose performance metrics to assess the effectiveness of LLMs in these contexts. Third, we present a risk mitigation framework designed to prevent malware by leveraging LLMs. Finally, we evaluate the performance of our proposed risk mitigation strategies against various factors and demonstrate their effectiveness in countering LLM-enabled malware. The paper concludes by suggesting future advancements and areas requiring deeper exploration in this fascinating field of artificial intelligence., Comment: 26 pages, 7 figures, 4 tables

We present Shades-of-NULL, a benchmark for responsible missing value imputation. Our benchmark includes state-of-the-art imputation techniques, and embeds them into the machine learning development lifecycle. We model realistic missingness scenarios that go beyond Rubin's classic Missing Completely at Random (MCAR), Missing At Random (MAR) and Missing Not At Random (MNAR), to include multi-mechanism missingness (when different missingness patterns co-exist in the data) and missingness shift (when the missingness mechanism changes between training and test). Another key novelty of our work is that we evaluate imputers holistically, based on the predictive performance, fairness and stability of the models that are trained and tested on the data they produce. We use Shades-of-NULL to conduct a large-scale empirical study involving 20,952 experimental pipelines, and find that, while there is no single best-performing imputation approach for all missingness types, interesting performance patterns do emerge when comparing imputer performance in simpler vs. more complex missingness scenarios. Further, while predictive performance, fairness and stability can be seen as orthogonal, we identify trade-offs among them that arise due to the combination of missingness scenario, the choice of an imputer, and the architecture of the model trained on the data post-imputation. We make Shades-of-NULL publicly available, and hope to enable researchers to comprehensively and rigorously evaluate new missing value imputation methods on a wide range of evaluation metrics, in plausible and socially meaningful missingness scenarios.

The rapid development of Large Language Models (LLMs) for healthcare applications has spurred calls for holistic evaluation beyond frequently-cited benchmarks like USMLE, to better reflect real-world performance. While real-world assessments are valuable indicators of utility, they often lag behind the pace of LLM evolution, likely rendering findings obsolete upon deployment. This temporal disconnect necessitates a comprehensive upfront evaluation that can guide model selection for specific clinical applications. We introduce MEDIC, a framework assessing LLMs across five critical dimensions of clinical competence: medical reasoning, ethics and bias, data and language understanding, in-context learning, and clinical safety. MEDIC features a novel cross-examination framework quantifying LLM performance across areas like coverage and hallucination detection, without requiring reference outputs. We apply MEDIC to evaluate LLMs on medical question-answering, safety, summarization, note generation, and other tasks. Our results show performance disparities across model sizes, baseline vs medically finetuned models, and have implications on model selection for applications requiring specific model strengths, such as low hallucination or lower cost of inference. MEDIC's multifaceted evaluation reveals these performance trade-offs, bridging the gap between theoretical capabilities and practical implementation in healthcare settings, ensuring that the most promising models are identified and adapted for diverse healthcare applications., Comment: Technical report

Despite promising progress in face swapping task, realistic swapped images remain elusive, often marred by artifacts, particularly in scenarios involving high pose variation, color differences, and occlusion. To address these issues, we propose a novel approach that better harnesses diffusion models for face-swapping by making following core contributions. (a) We propose to re-frame the face-swapping task as a self-supervised, train-time inpainting problem, enhancing the identity transfer while blending with the target image. (b) We introduce a multi-step Denoising Diffusion Implicit Model (DDIM) sampling during training, reinforcing identity and perceptual similarities. (c) Third, we introduce CLIP feature disentanglement to extract pose, expression, and lighting information from the target image, improving fidelity. (d) Further, we introduce a mask shuffling technique during inpainting training, which allows us to create a so-called universal model for swapping, with an additional feature of head swapping. Ours can swap hair and even accessories, beyond traditional face swapping. Unlike prior works reliant on multiple off-the-shelf models, ours is a relatively unified approach and so it is resilient to errors in other off-the-shelf models. Extensive experiments on FFHQ and CelebA datasets validate the efficacy and robustness of our approach, showcasing high-fidelity, realistic face-swapping with minimal inference time. Our code is available at https://github.com/Sanoojan/REFace., Comment: Accepted as a conference paper at WACV 2025

Large language models (LLMs) have shown remarkable abilities in different fields, including standard Natural Language Processing (NLP) tasks. To elicit knowledge from LLMs, prompts play a key role, consisting of natural language instructions. Most open and closed source LLMs are trained on available labeled and unlabeled resources--digital content such as text, images, audio, and videos. Hence, these models have better knowledge for high-resourced languages but struggle with low-resourced languages. Since prompts play a crucial role in understanding their capabilities, the language used for prompts remains an important research question. Although there has been significant research in this area, it is still limited, and less has been explored for medium to low-resourced languages. In this study, we investigate different prompting strategies (native vs. non-native) on 11 different NLP tasks associated with 12 different Arabic datasets (9.7K data points). In total, we conducted 197 experiments involving 3 LLMs, 12 datasets, and 3 prompting strategies. Our findings suggest that, on average, the non-native prompt performs the best, followed by mixed and native prompts., Comment: Foundation Models, Large Language Models, Arabic NLP, LLMs, Native, Contextual Understanding, Arabic LLM

The availability of high-quality datasets play a crucial role in advancing research and development especially, for safety critical and autonomous systems. In this paper, we present AssistTaxi, a comprehensive novel dataset which is a collection of images for runway and taxiway analysis. The dataset comprises of more than 300,000 frames of diverse and carefully collected data, gathered from Melbourne (MLB) and Grant-Valkaria (X59) general aviation airports. The importance of AssistTaxi lies in its potential to advance autonomous operations, enabling researchers and developers to train and evaluate algorithms for efficient and safe taxiing. Researchers can utilize AssistTaxi to benchmark their algorithms, assess performance, and explore novel approaches for runway and taxiway analysis. Addition-ally, the dataset serves as a valuable resource for validating and enhancing existing algorithms, facilitating innovation in autonomous operations for aviation. We also propose an initial approach to label the dataset using a contour based detection and line extraction technique.

Recently, the ``Bootstrap" technique was applied in Quantum Mechanics to solve the eigenspectra of Hermitian Hamiltonians and extended to non-Hermitian PT-symmetric systems. However, its application has been limited to real spectra. In this work, we establish bootstrap conditions for the non-Hermitian system and generate eigenspectra for a generic complex polynomial potential, which includes PT-symmetric Hamiltonians as a special case. Additionally, we demonstrate the method's ability to obtain eigenspectra under various boundary conditions imposed on the eigenfunction, including the notable application of capturing the PT-symmetric phase transition.

Deep learning is popularly used for analyzing pathology images, but variations in image properties can limit the effectiveness of the models. The study aims to develop a method that transfers the variability present in the training set to unseen images, improving the model's ability to make accurate inferences. YOLOv5 was trained on peripheral blood and bone marrow sample images and Neural Color Transfer techniques were used to incorporate invariance. The results showed significant improvement in detecting WBCs from untrained samples after normalization, highlighting the potential of deep learning-based normalization techniques for inference robustness.

Machine Learning (ML) has become one of the most impactful fields of data science in recent years. However, a significant concern with ML is its privacy risks due to rising attacks against ML models. Privacy-Preserving Machine Learning (PPML) methods have been proposed to mitigate the privacy and security risks of ML models. A popular approach to achieving PPML uses Homomorphic Encryption (HE). However, the highly publicized inefficiencies of HE make it unsuitable for highly scalable scenarios with resource-constrained devices. Hence, Hybrid Homomorphic Encryption (HHE) -- a modern encryption scheme that combines symmetric cryptography with HE -- has recently been introduced to overcome these challenges. HHE potentially provides a foundation to build new efficient and privacy-preserving services that transfer expensive HE operations to the cloud. This work introduces HHE to the ML field by proposing resource-friendly PPML protocols for edge devices. More precisely, we utilize HHE as the primary building block of our PPML protocols. We assess the performance of our protocols by first extensively evaluating each party's communication and computational cost on a dummy dataset and show the efficiency of our protocols by comparing them with similar protocols implemented using plain BFV. Subsequently, we demonstrate the real-world applicability of our construction by building an actual PPML application that uses HHE as its foundation to classify heart disease based on sensitive ECG data., Comment: Accepted in The 22nd IEEE International Conference on Dependable, Autonomic and Secure Computing (DASC 2024)

Inverse materials design has proven successful in accelerating novel material discovery. Many inverse materials design methods use unsupervised learning where a latent space is learned to offer a compact description of materials representations. A latent space learned this way is likely to be entangled, in terms of the target property and other properties of the materials. This makes the inverse design process ambiguous. Here, we present a semi-supervised learning approach based on a disentangled variational autoencoder to learn a probabilistic relationship between features, latent variables and target properties. This approach is data efficient because it combines all labelled and unlabelled data in a coherent manner, and it uses expert-informed prior distributions to improve model robustness even with limited labelled data. It is in essence interpretable, as the learnable target property is disentangled out of the other properties of the materials, and an extra layer of interpretability can be provided by a post-hoc analysis of the classification head of the model. We demonstrate this new approach on an experimental high-entropy alloy dataset with chemical compositions as input and single-phase formation as the single target property. While single property is used in this work, the disentangled model can be extended to customize for inverse design of materials with multiple target properties.

The reconfigurable intelligent surface (RIS) technology shows great potential in sixth-generation (6G) terrestrial and non-terrestrial networks (NTNs) since it can effectively change wireless settings to improve connectivity. Extensive research has been conducted on traditional RIS systems with diagonal phase response matrices. The straightforward RIS architecture, while cost-effective, has restricted capabilities in manipulating the wireless channels. The beyond diagonal reconfigurable intelligent surface (BD-RIS) greatly improves control over the wireless environment by utilizing interconnected phase response elements. This work proposes the integration of unmanned aerial vehicle (UAV) communications and BD-RIS in 6G NTNs, which has the potential to further enhance wireless coverage and spectral efficiency. We begin with the preliminaries of UAV communications and then discuss the fundamentals of BD-RIS technology. Subsequently, we discuss the potential of BD-RIS and UAV communications integration. We then proposed a case study based on UAV-mounted transmissive BD-RIS communication. Finally, we highlight future research directions and conclude this work., Comment: 7,4

This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.

Comet C/2017 K2 (Pan-STARRS) provided a rare opportunity to investigate the evolution of coma composition and outgassing patterns over a transitional heliocentric distance (Rh) range where activity drivers in comets are thought to change from "hypervolatile" (CO, CH$_4$, C$_2$H$_6$, and/or CO$_2$)-dominated to H2O-dominated. We performed high-resolution, cross-dispersed, near-infrared spectroscopy of C/2017 K2 with iSHELL at the NASA Infrared Telescope Facility (IRTF) and NIRSPEC at the W. M. Keck 2 Observatory. We report gas rotational temperatures (Trot) and molecular production rates (Q; mol/s) or upper limits for the hypervolatile species CH$_4$, CO, and C$_2$H$_6$, together with less volatile ices (CH$_3$OH, H$_2$O, HCN, C$_2$H$_2$, NH$_3$, and OCS) over a range of pre-perihelion distances, Rh= 3.15 - 2.35 au. We also report (or stringently constrain) abundance ratios (mixing ratios) of the targeted species with respect to CO, C$_2$H$_6$, and (when detected) H$_2$O. All volatiles were enriched relative to water in C/2017 K2 when compared to their mean values among Oort Cloud comets, whereas abundances relative to C2H6 were consistent with their average values from other long-period comets., Comment: Submitted to the Astronomical Journal for publication

Contemporary research in autonomous driving has demonstrated tremendous potential in emulating the traits of human driving. However, they primarily cater to areas with well built road infrastructure and appropriate traffic management systems. Therefore, in the absence of traffic signals or in unstructured environments, these self-driving algorithms are expected to fail. This paper proposes a strategy for autonomously navigating multiple vehicles in close proximity to their desired destinations without traffic rules in unstructured environments. Graphical Neural Networks (GNNs) have demonstrated good utility for this task of multi-vehicle control. Among the different alternatives of training GNNs, supervised methods have proven to be most data-efficient, albeit require ground truth labels. However, these labels may not always be available, particularly in unstructured environments without traffic regulations. Therefore, a tedious optimization process may be required to determine them while ensuring that the vehicles reach their desired destination and do not collide with each other or any obstacles. Therefore, in order to expedite the training process, it is essential to reduce the optimization time and select only those samples for labeling that add most value to the training. In this paper, we propose a warm start method that first uses a pre-trained model trained on a simpler subset of data. Inference is then done on more complicated scenarios, to determine the hard samples wherein the model faces the greatest predicament. This is measured by the difficulty vehicles encounter in reaching their desired destination without collision. Experimental results demonstrate that mining for hard samples in this manner reduces the requirement for supervised training data by 10 fold. Videos and code can be found here: \url{https://yininghase.github.io/multiagent-collision-mining/}., Comment: 9 pages

Although linear quantum amplification has proven essential to the processing of weak quantum signals, extracting higher-order quantum features such as correlations in principle demands nonlinear operations. However, nonlinear processing of quantum signals is often associated with non-idealities and excess noise, and absent a general framework to harness nonlinearity, such regimes are typically avoided. Here we present a framework to uncover general quantum signal processing principles of a broad class of bosonic quantum nonlinear processors (QNPs), inspired by a remarkably analogous paradigm in nature: the processing of environmental stimuli by nonlinear, noisy neural ensembles, to enable perception. Using a quantum-coherent description of a QNP monitoring a quantum signal source, we show that quantum nonlinearity can be harnessed to calculate higher-order features of an incident quantum signal, concentrating them into linearly-measurable observables, a transduction not possible using linear amplifiers. Secondly, QNPs provide coherent nonlinear control over quantum fluctuations including their own added noise, enabling noise suppression in an observable without suppressing transduced information, a paradigm that bears striking similarities to optimal neural codings that allow perception even under highly stochastic neural dynamics. Unlike the neural case, we show that QNP-engineered noise distributions can exhibit non-classical correlations, providing a new means to harness resources such as entanglement. Finally, we show that even simple QNPs in realistic measurement chains can provide enhancements of signal-to-noise ratio for practical tasks such as quantum state discrimination. Our work provides pathways to utilize nonlinear quantum systems as general computation devices, and enables a new paradigm for nonlinear quantum information processing., Comment: 25+39 pages, 10+7 figures, and 97 references

Deep learning has shown great potential for automated medical image segmentation to improve the precision and speed of disease diagnostics. However, the task presents significant difficulties due to variations in the scale, shape, texture, and contrast of the pathologies. Traditional convolutional neural network (CNN) models have certain limitations when it comes to effectively modelling multiscale context information and facilitating information interaction between skip connections across levels. To overcome these limitations, a novel deep learning architecture is introduced for medical image segmentation, taking advantage of CNNs and vision transformers. Our proposed model, named TBConvL-Net, involves a hybrid network that combines the local features of a CNN encoder-decoder architecture with long-range and temporal dependencies using biconvolutional long-short-term memory (LSTM) networks and vision transformers (ViT). This enables the model to capture contextual channel relationships in the data and account for the uncertainty of segmentation over time. Additionally, we introduce a novel composite loss function that considers both the segmentation robustness and the boundary agreement of the predicted output with the gold standard. Our proposed model shows consistent improvement over the state of the art on ten publicly available datasets of seven different medical imaging modalities.

We develop a family of mixed finite element methods for a model of nonlinear poroelasticity where, thanks to a rewriting of the constitutive equations, the permeability depends on the total poroelastic stress and on the fluid pressure and therefore we can use the Hellinger--Reissner principle with weakly imposed stress symmetry for Biot's equations. The problem is adequately structured into a coupled system consisting of one saddle-point formulation, one linearised perturbed saddle-point formulation, and two off-diagonal perturbations. This system's unique solvability requires assumptions on regularity and Lipschitz continuity of the inverse permeability, and the analysis follows fixed-point arguments and the Babu\v{s}ka--Brezzi theory. The discrete problem is shown uniquely solvable by applying similar fixed-point and saddle-point techniques as for the continuous case. The method is based on the classical PEERS$_k$ elements, it is exactly momentum and mass conservative, and it is robust with respect to the nearly incompressible as well as vanishing storativity limits. We derive a priori error estimates, we also propose fully computable residual-based a posteriori error indicators, and show that they are reliable and efficient with respect to the natural norms, and robust in the limit of near incompressibility. These a posteriori error estimates are used to drive adaptive mesh refinement. The theoretical analysis is supported and illustrated by several numerical examples in 2D and 3D.

In recent years, financial analysts have been trying to develop models to predict the movement of a stock price index. The task becomes challenging in vague economic, social, and political situations like in Pakistan. In this study, we employed efficient models of machine learning such as long short-term memory (LSTM) and quantum long short-term memory (QLSTM) to predict the Karachi Stock Exchange (KSE) 100 index by taking monthly data of twenty-six economic, social, political, and administrative indicators from February 2004 to December 2020. The comparative results of LSTM and QLSTM predicted values of the KSE 100 index with the actual values suggested QLSTM a potential technique to predict stock market trends.

This paper presents a cascaded control architecture, based on nonlinear dynamic inversion (NDI), for rigid body attitude control. The proposed controller works directly with the rotation matrix parameterization, that is, with elements of the Special Orthogonal Group $\mathsf{SO(3)}$, and avoids problems related to singularities and non-uniqueness which affect other commonly used attitude representations such as Euler angles, unit quaternions, modified Rodrigues parameters, etc. The proposed NDI-based controller is capable of imposing desired linear dynamics of any order for the outer attitude loop and the inner rate loop, and gives control designers the flexibility to choose higher-order dynamic compensators in both loops. In addition, sufficient conditions are presented in the form of linear matrix inequalities (LMIs) which ensure that the outer loop controller renders the attitude loop almost globally asymptotically stable (AGAS) and the rate loop globally asymptotically stable (GAS). Furthermore, the overall cascaded control architecture is shown to be AGAS in the case of attitude error regulation. Lastly, the proposed scheme is compared with an Euler angles-based NDI scheme from literature for a tracking problem involving agile maneuvering of a multicopter in a high-fidelity nonlinear simulation., Comment: 7 pages, 6 figures, accepted in IEEE Conference on Decision and Control (CDC), 2024

Stable diffusion has demonstrated strong image synthesis ability to given text descriptions, suggesting it to contain strong semantic clue for grouping objects. Inspired by this, researchers have explored employing stable diffusion for trainingfree segmentation. Most existing approaches either simply employ cross-attention map or refine it by self-attention map, to generate segmentation masks. We believe that iterative refinement with self-attention map would lead to better results. However, we mpirically demonstrate that such a refinement is sub-optimal likely due to the self-attention map containing irrelevant global information which hampers accurately refining cross-attention map with multiple iterations. To address this, we propose an iterative refinement framework for training-free segmentation, named iSeg, having an entropy-reduced self-attention module which utilizes a gradient descent scheme to reduce the entropy of self-attention map, thereby suppressing the weak responses corresponding to irrelevant global information. Leveraging the entropy-reduced self-attention module, our iSeg stably improves refined crossattention map with iterative refinement. Further, we design a category-enhanced cross-attention module to generate accurate cross-attention map, providing a better initial input for iterative refinement. Extensive experiments across different datasets and diverse segmentation tasks reveal the merits of proposed contributions, leading to promising performance on diverse segmentation tasks. For unsupervised semantic segmentation on Cityscapes, our iSeg achieves an absolute gain of 3.8% in terms of mIoU compared to the best existing training-free approach in literature. Moreover, our proposed iSeg can support segmentation with different kind of images and interactions., Comment: Project Page: https://linsun449.github.io/iSeg/ Code: https://github.com/linsun449/iseg.code

Unarguably, deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor, we study the challenging problem of semi-supervised domain generalization (SSDG), where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. Domain generalization (DG) methods show subpar performance under the SSDG setting, whereas semi-supervised learning (SSL) methods demonstrate relatively better performance, however, they are considerably poor compared to the fully-supervised DG methods. Towards handling this new, but challenging problem of SSDG, we propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts. This is accomplished by retaining the domain-level specialism in the classifier during training corresponding to each source domain. Specifically, we first create domain-level information vectors on the fly which are then utilized to learn a domain-aware mask for modulating the classifier's weights. We provide a mathematical interpretation for the effect of this modulation procedure on both pseudo-labeling and model training. Our method is plug-and-play and can be readily applied to different SSL baselines for SSDG. Extensive experiments on six challenging datasets in two different SSDG settings show that our method provides visible gains over the various strong SSL-based SSDG baselines., Comment: Accepted at WACV25

Simulations of coronary hemodynamics have improved non-invasive clinical risk stratification and treatment outcomes for coronary artery disease, compared to relying on anatomical imaging alone. However, simulations typically use empirical approaches to distribute total coronary flow amongst the arteries in the coronary tree. This ignores patient variability, the presence of disease, and other clinical factors. Further, uncertainty in the clinical data often remains unaccounted for in the modeling pipeline. We present an end-to-end uncertainty-aware pipeline to (1) personalize coronary flow simulations by incorporating branch-specific coronary flows as well as cardiac function; and (2) predict clinical and biomechanical quantities of interest with improved precision, while accounting for uncertainty in the clinical data. We assimilate patient-specific measurements of myocardial blood flow from CT myocardial perfusion imaging to estimate branch-specific coronary flows. We use adaptive Markov Chain Monte Carlo sampling to estimate the joint posterior distributions of model parameters with simulated noise in the clinical data. Additionally, we determine the posterior predictive distribution for relevant quantities of interest using a new approach combining multi-fidelity Monte Carlo estimation with non-linear, data-driven dimensionality reduction. Our framework recapitulates clinically measured cardiac function as well as branch-specific coronary flows under measurement uncertainty. We substantially shrink the confidence intervals for estimated quantities of interest compared to single-fidelity and state-of-the-art multi-fidelity Monte Carlo methods. This is especially true for quantities that showed limited correlation between the low- and high-fidelity model predictions. Moreover, the proposed estimators are significantly cheaper to compute for a specified confidence level or variance.

The rapid evolution of the International Mobile Telecommunications (IMT) landscape has prompted the International Telecommunications Union Working Party 5D (ITU WP5D) to outline the framework for IMT-2030 and beyond. This next-generation initiative seeks to meet the diverse demands of future networks, with key objectives including hyper-low latency, enhanced energy efficiency, and robust support for high mobility. Current 5th generation (5G) technologies employ waveforms like Orthogonal Frequency Division Multiplexing (OFDM) and Discrete Fourier Transform Spread Orthogonal Frequency Division Multiplexing (DFT-s-OFDM). However, these waveforms are insufficient to fully meet the stringent requirements of next-generation communication systems. This paper introduces a novel waveform, Orthogonal Time Frequency Division Multiplexing (OTFDM), designed to address the limitations of existing waveforms. OTFDM achieves ultra-low latency by enabling single-shot transmission of data and Reference Signals (RS) within a single symbol. Furthermore, OTFDM supports high mobility with improved resilience to Doppler shifts and enhances power amplifier efficiency through its low Peak-to-Average Power Ratio (PAPR) characteristics. The proposed waveform incorporates advanced signal processing techniques, including time-frequency multiplexing and frequency domain spectrum shaping, to mitigate inter-symbol interference (ISI). These techniques enable accurate per-symbol channel estimation, thus supporting higher-order modulations even at higher user speeds. Extensive simulations validate the efficacy of OTFDM, demonstrating its capability to support user speeds up to 500 Km/h with minimal RS overhead. This paper explores the technical aspects of OTFDM and discusses its potential implications for the next-generation wireless communication systems.

Accurate segmentation of skin lesions within dermoscopic images plays a crucial role in the timely identification of skin cancer for computer-aided diagnosis on mobile platforms. However, varying shapes of the lesions, lack of defined edges, and the presence of obstructions such as hair strands and marker colors make this challenge more complex. \textcolor{red}Additionally, skin lesions often exhibit subtle variations in texture and color that are difficult to differentiate from surrounding healthy skin, necessitating models that can capture both fine-grained details and broader contextual information. Currently, melanoma segmentation models are commonly based on fully connected networks and U-Nets. However, these models often struggle with capturing the complex and varied characteristics of skin lesions, such as the presence of indistinct boundaries and diverse lesion appearances, which can lead to suboptimal segmentation performance.To address these challenges, we propose a novel lightweight network specifically designed for skin lesion segmentation utilizing mobile devices, featuring a minimal number of learnable parameters (only 0.8 million). This network comprises an encoder-decoder architecture that incorporates conformer-based focal modulation attention, self-aware local and global spatial attention, and split channel-shuffle. The efficacy of our model has been evaluated on four well-established benchmark datasets for skin lesion segmentation: ISIC 2016, ISIC 2017, ISIC 2018, and PH2. Empirical findings substantiate its state-of-the-art performance, notably reflected in a high Jaccard index.

Partitioning is a known problem in computer science and is critical in chip design workflows, as advancements in this area can significantly influence design quality and efficiency. Deep Learning (DL) techniques, particularly those involving Graph Neural Networks (GNNs), have demonstrated strong performance in various node, edge, and graph prediction tasks using both inductive and transductive learning methods. A notable area of recent interest within GNNs are pooling layers and their application to graph partitioning. While these methods have yielded promising results across social, computational, and other random graphs, their effectiveness has not yet been explored in the context of VLSI hypergraph netlists. In this study, we introduce a new set of synthetic partitioning benchmarks that emulate real-world netlist characteristics and possess a known upper bound for solution cut quality. We distinguish these benchmarks with the prior work and evaluate existing state-of-the-art partitioning algorithms alongside GNN-based approaches, highlighting their respective advantages and disadvantages.

The field of computer vision applied to videos of minimally invasive surgery is ever-growing. Workflow recognition pertains to the automated recognition of various aspects of a surgery: including which surgical steps are performed; and which surgical instruments are used. This information can later be used to assist clinicians when learning the surgery; during live surgery; and when writing operation notes. The Pituitary Vision (PitVis) 2023 Challenge tasks the community to step and instrument recognition in videos of endoscopic pituitary surgery. This is a unique task when compared to other minimally invasive surgeries due to the smaller working space, which limits and distorts vision; and higher frequency of instrument and step switching, which requires more precise model predictions. Participants were provided with 25-videos, with results presented at the MICCAI-2023 conference as part of the Endoscopic Vision 2023 Challenge in Vancouver, Canada, on 08-Oct-2023. There were 18-submissions from 9-teams across 6-countries, using a variety of deep learning models. A commonality between the top performing models was incorporating spatio-temporal and multi-task methods, with greater than 50% and 10% macro-F1-score improvement over purely spacial single-task models in step and instrument recognition respectively. The PitVis-2023 Challenge therefore demonstrates state-of-the-art computer vision models in minimally invasive surgery are transferable to a new dataset, with surgery specific techniques used to enhance performance, progressing the field further. Benchmark results are provided in the paper, and the dataset is publicly available at: https://doi.org/10.5522/04/26531686.

In the realm of dermatology, the complexity of diagnosing skin conditions manually necessitates the expertise of dermatologists. Accurate identification of various skin ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly in accurately diagnosing diseases across diverse skin tones, with a notable performance gap in darker skin. Additionally, the scarcity of publicly available, unbiased datasets hampers the development of inclusive AI diagnostic tools. To tackle the challenges in accurately predicting skin conditions across diverse skin tones, we employ a transfer-learning approach that capitalizes on the rich, transferable knowledge from various image domains. Our method integrates multiple pre-trained models from a wide range of sources, including general and specific medical images, to improve the robustness and inclusiveness of the skin condition predictions. We rigorously evaluated the effectiveness of these models using the Diverse Dermatology Images (DDI) dataset, which uniquely encompasses both underrepresented and common skin tones, making it an ideal benchmark for assessing our approach. Among all methods, Med-ViT emerged as the top performer due to its comprehensive feature representation learned from diverse image sources. To further enhance performance, we conducted domain adaptation using additional skin image datasets such as HAM10000. This adaptation significantly improved model performance across all models.

In this work, we investigate the $hp$-discontinuous Galerkin (DG) time-stepping method for the generalized Burgers-Huxley equation with memory, a non-linear advection-diffusion-reaction problem featuring weakly singular kernels. We derive a priori error estimates for the semi-discrete scheme using $hp$-DG time-stepping, with explicit dependence on the local mesh size, polynomial degree, and solution regularity, achieving optimal convergence in the energy norm. For the fully-discrete scheme, we initially implement the $hp$-finite element method (conforming), followed by the $hp$-discontinuous Galerkin method. We establish the well-posedness and stability of the fully-discrete scheme and provide corresponding a priori estimates. The effectiveness of the proposed method is demonstrated through numerical validation on a series of test problems.

Patterns of human motion in outdoor and indoor environments are substantially different due to the scope of the environment and the typical intentions of people therein. While outdoor trajectory forecasting has received significant attention, indoor forecasting is still an underexplored research area. This paper proposes SITUATE, a novel approach to cope with indoor human trajectory prediction by leveraging equivariant and invariant geometric features and a self-supervised vision representation. The geometric learning modules model the intrinsic symmetries and human movements inherent in indoor spaces. This concept becomes particularly important because self-loops at various scales and rapid direction changes often characterize indoor trajectories. On the other hand, the vision representation module is used to acquire spatial-semantic information about the environment to predict users' future locations more accurately. We evaluate our method through comprehensive experiments on the two most famous indoor trajectory forecasting datasets, i.e., TH\"OR and Supermarket, obtaining state-of-the-art performance. Furthermore, we also achieve competitive results in outdoor scenarios, showing that indoor-oriented forecasting models generalize better than outdoor-oriented ones. The source code is available at https://github.com/intelligolabs/SITUATE., Comment: Accepted at the 27th International Conference on Pattern Recognition (ICPR 2024)

Cardiac auscultation, an integral tool in diagnosing cardiovascular diseases (CVDs), often relies on the subjective interpretation of clinicians, presenting a limitation in consistency and accuracy. Addressing this, we introduce the BUET Multi-disease Heart Sound (BMD-HS) dataset - a comprehensive and meticulously curated collection of heart sound recordings. This dataset, encompassing 864 recordings across five distinct classes of common heart sounds, represents a broad spectrum of valvular heart diseases, with a focus on diagnostically challenging cases. The standout feature of the BMD-HS dataset is its innovative multi-label annotation system, which captures a diverse range of diseases and unique disease states. This system significantly enhances the dataset's utility for developing advanced machine learning models in automated heart sound classification and diagnosis. By bridging the gap between traditional auscultation practices and contemporary data-driven diagnostic methods, the BMD-HS dataset is poised to revolutionize CVD diagnosis and management, providing an invaluable resource for the advancement of cardiac health research. The dataset is publicly available at this link: https://github.com/mHealthBuet/BMD-HS-Dataset., Comment: 14 pages, 13 figures

Deep supervised learning models require high volume of labeled data to attain sufficiently good results. Although, the practice of gathering and annotating such big data is costly and laborious. Recently, the application of self supervised learning (SSL) in vision tasks has gained significant attention. The intuition behind SSL is to exploit the synchronous relationships within the data as a form of self-supervision, which can be versatile. In the current big data era, most of the data is unlabeled, and the success of SSL thus relies in finding ways to utilize this vast amount of unlabeled data available. Thus it is better for deep learning algorithms to reduce reliance on human supervision and instead focus on self-supervision based on the inherent relationships within the data. With the advent of ViTs, which have achieved remarkable results in computer vision, it is crucial to explore and understand the various SSL mechanisms employed for training these models specifically in scenarios where there is limited labelled data available. In this survey, we develop a comprehensive taxonomy of systematically classifying the SSL techniques based upon their representations and pre-training tasks being applied. Additionally, we discuss the motivations behind SSL, review popular pre-training tasks, and highlight the challenges and advancements in this field. Furthermore, we present a comparative analysis of different SSL methods, evaluate their strengths and limitations, and identify potential avenues for future research., Comment: 34 Pages, 5 Figures, 7 Tables

Here we critically examine the geophysical and geochemical properties of the Moon in order to identify the extent to which dynamical scenarios satisfy these observations. New joint inversions of existing lunar geophysical data (mean mass, moment of inertia, and tidal response) assuming a laterally- and vertically homogeneous lunar mantle show that, in all cases, a core with a radius of 300$\pm$20 km ($\sim$0.8 to 1.5 % the mass of the Moon) is required. However, an Earth-like Mg# (0.89) in the lunar mantle results in core densities (7800$\pm$100 kg/m$^3$) consistent with that of Fe-Ni alloy, whereas FeO-rich compositions (Mg# = 0.80--0.84) require lower densities (6100$\pm$800 kg/m$^3$). Geochemically, we use new data on mare basalts to reassess the bulk composition of the Moon for 70 elements, and show that the lunar core likely formed near 5 GPa, 2100 K and $\sim$1 log unit below the iron-w\"ustite buffer. Moreover, the Moon is depleted relative to the Earth's mantle in elements with volatilities higher than that of Li, with this volatile loss likely having occurred at low temperatures (1400$\pm$100 K), consistent with mass-dependent stable isotope fractionation of moderately volatile elements (e.g., Zn, K, Rb). The identical nucleosynthetic (O, Cr, Ti) and radiogenic (W) isotope compositions of the lunar and terrestrial mantles, strongly suggest the two bodies were made from the same material, rather than from an Earth-like impactor. Rb-Sr in FANs and Lu-Hf and Pb-Pb zircon ages point Moon formation close to $\sim$4500 Ma. Taken together, there is no unambiguous geochemical or isotopic evidence for the role of an impactor in the formation of the Moon, implying perfect equilibration between the proto-Earth and Moon-forming material or alternative scenarios for its genesis., Comment: 62 pages, 23 figures, 5 tables. Treatise of Geochemistry, vol. 3, in press

The behavioural and psychological symptoms of dementia, such as agitation and aggression, present a significant health and safety risk in residential care settings. Many care facilities have video cameras in place for digital monitoring of public spaces, which can be leveraged to develop an automated behaviours of risk detection system that can alert the staff to enable timely intervention and prevent the situation from escalating. However, one of the challenges in our previous study was the presence of false alarms due to obstruction of view by activities happening close to the camera. To address this issue, we proposed a novel depth-weighted loss function to train a customized convolutional autoencoder to enforce equivalent importance to the events happening both near and far from the cameras; thus, helping to reduce false alarms and making the method more suitable for real-world deployment. The proposed method was trained using data from nine participants with dementia across three cameras situated in a specialized dementia unit and achieved an area under the curve of receiver operating characteristic of $0.852$, $0.81$ and $0.768$ for the three cameras. Ablation analysis was conducted for the individual components of the proposed method and the performance of the proposed method was investigated for participant-specific and sex-specific behaviours of risk detection. The proposed method performed reasonably well in detecting behaviours of risk in people with dementia motivating further research toward the development of a behaviours of risk detection system suitable for deployment in video surveillance systems in care facilities.

As the field of artificial intelligence progresses, assistive technologies are becoming more widely used across all industries. The healthcare industry is no different, with numerous studies being done to develop assistive tools for healthcare professionals. Automatic diagnostic systems are one such beneficial tool that can assist with a variety of tasks, including collecting patient information, analyzing test results, and diagnosing patients. However, the idea of developing systems that can provide a differential diagnosis has been largely overlooked in most of these research studies. In this study, we propose a transformer-based approach for providing differential diagnoses based on a patient's age, sex, medical history, and symptoms. We use the DDXPlus dataset, which provides differential diagnosis information for patients based on 49 disease types. Firstly, we propose a method to process the tabular patient data from the dataset and engineer them into patient reports to make them suitable for our research. In addition, we introduce two data modification modules to diversify the training data and consequently improve the robustness of the models. We approach the task as a multi-label classification problem and conduct extensive experiments using four transformer models. All the models displayed promising results by achieving over 97% F1 score on the held-out test set. Moreover, we design additional behavioral tests to get a broader understanding of the models. In particular, for one of our test cases, we prepared a custom test set of 100 samples with the assistance of a doctor. The results on the custom set showed that our proposed data modification modules improved the model's generalization capabilities. We hope our findings will provide future researchers with valuable insights and inspire them to develop reliable systems for automatic differential diagnosis., Comment: 25 pages, 7 figures

This research paper introduces a novel word-level Optical Character Recognition (OCR) model specifically designed for digital Urdu text, leveraging transformer-based architectures and attention mechanisms to address the distinct challenges of Urdu script recognition, including its diverse text styles, fonts, and variations. The model employs a permuted autoregressive sequence (PARSeq) architecture, which enhances its performance by enabling context-aware inference and iterative refinement through the training of multiple token permutations. This method allows the model to adeptly manage character reordering and overlapping characters, commonly encountered in Urdu script. Trained on a dataset comprising approximately 160,000 Urdu text images, the model demonstrates a high level of accuracy in capturing the intricacies of Urdu script, achieving a CER of 0.178. Despite ongoing challenges in handling certain text variations, the model exhibits superior accuracy and effectiveness in practical applications. Future work will focus on refining the model through advanced data augmentation techniques and the integration of context-aware language models to further enhance its performance and robustness in Urdu text recognition.

This work proposes a T-RIS-equipped LEO satellite communication in cognitive radio-enabled integrated NTNs. In the proposed system, a GEO satellite operates as a primary network, and a T-RIS-equipped LEO satellite operates as a secondary IoT network. The objective is to maximize the sum rate of T-RIS-equipped LEO satellite communication using downlink NOMA while ensuring the service quality of GEO cellular users. Our framework simultaneously optimizes the total transmit power of LEO, NOMA power allocation for LEO IoT (LIoT) and T-RIS phase shift design subject to the service quality of LIoT and interference temperature to the primary GEO network. To solve the non-convex sum rate maximization problem, we first adopt successive convex approximations to reduce the complexity of the formulated optimization. Then, we divide the problem into two parts, i.e., power allocation of LEO and phase shift design of T-RIS. The power allocation problem is solved using KKT conditions, while the phase shift problem is handled by Taylor approximation and semidefinite programming. Numerical results are provided to validate the proposed optimization framework., Comment: 7,5

We obtain an asymptotic for the fourth moment of truncated Eisenstein series of large Laplacian eigenvalue, verifying for the first time that the main term corresponds to Gaussian random behavior. This is a manifestation of the Random Wave Conjecture, which for Eisenstein series was formulated by Hejhal and Rackner over thirty years ago., Comment: 23 pages

Intermediate Mass Black Hole (IMBH) mergers with masses $10^4 - 10^6$ $M_{\odot}$ are expected to produce gravitational waves (GWs) detectable by the Laser Interferometer Space Antenna (LISA) with high signal to noise ratios out to redshift 20. IMBH mergers are expected to take place within dwarf galaxies, however, the dynamics, timescales, and effect on their hosts are largely unexplored. In a previous study, we examined how IMBHs would pair and merge within nucleated dwarf galaxies. IMBHs in nucleated hosts evolve very efficiently, forming a binary system and coalescing within a few hundred million years. Although the fraction of dwarf galaxies ($10^7$ M$_{\odot} \leq$ $M_{\star} \leq 10^{10}$ M$_{\odot}$) hosting nuclear star clusters is between 60-100\%, this fraction drops to 20-70\% for lower-mass dwarfs ($M_{\star}\approx 10^7$ M$_{\odot}$), with the largest drop in low-density environments. Here, we extend our previous study by performing direct $N-$body simulations to explore the dynamics and evolution of IMBHs within non-nucleated dwarf galaxies, under the assumption that IMBHs exist within these dwarfs. To our surprise, none of IMBHs in our simulation suite merge within a Hubble time, despite many attaining high eccentricities $e \sim 0.7-0.95$. We conclude that extremely low stellar density environments in the centers of non-nucleated dwarfs do not provide an ample supply of stars to interact with IMBHs binary resulting in its stalling, in spite of triaxiality and high eccentricity, common means to drive a binary to coalescence. Our findings underline the importance of considering all detailed host properties to predict IMBH merger rates for LISA., Comment: Submitted to ApJ

In the rapidly evolving field of cybersecurity, the integration of flow-level and packet-level information for real-time intrusion detection remains a largely untapped area of research. This paper introduces "XG-NID," a novel framework that, to the best of our knowledge, is the first to fuse flow-level and packet-level data within a heterogeneous graph structure, offering a comprehensive analysis of network traffic. Leveraging a heterogeneous graph neural network (GNN) with graph-level classification, XG-NID uniquely enables real-time inference while effectively capturing the intricate relationships between flow and packet payload data. Unlike traditional GNN-based methodologies that predominantly analyze historical data, XG-NID is designed to accommodate the heterogeneous nature of network traffic, providing a robust and real-time defense mechanism. Our framework extends beyond mere classification; it integrates Large Language Models (LLMs) to generate detailed, human-readable explanations and suggest potential remedial actions, ensuring that the insights produced are both actionable and comprehensible. Additionally, we introduce a new set of flow features based on temporal information, further enhancing the contextual and explainable inferences provided by our model. To facilitate practical application and accessibility, we developed "GNN4ID," an open-source tool that enables the extraction and transformation of raw network traffic into the proposed heterogeneous graph structure, seamlessly integrating flow and packet-level data. Our comprehensive quantitative comparative analysis demonstrates that XG-NID achieves an F1 score of 97\% in multi-class classification, outperforming existing baseline and state-of-the-art methods. This sets a new standard in Network Intrusion Detection Systems by combining innovative data fusion with enhanced interpretability and real-time capabilities., Comment: 19 pages, 6 figures

This report examines the fine-tuning of Large Language Models (LLMs), integrating theoretical insights with practical applications. It outlines the historical evolution of LLMs from traditional Natural Language Processing (NLP) models to their pivotal role in AI. A comparison of fine-tuning methodologies, including supervised, unsupervised, and instruction-based approaches, highlights their applicability to different tasks. The report introduces a structured seven-stage pipeline for fine-tuning LLMs, spanning data preparation, model initialization, hyperparameter tuning, and model deployment. Emphasis is placed on managing imbalanced datasets and optimization techniques. Parameter-efficient methods like Low-Rank Adaptation (LoRA) and Half Fine-Tuning are explored for balancing computational efficiency with performance. Advanced techniques such as memory fine-tuning, Mixture of Experts (MoE), and Mixture of Agents (MoA) are discussed for leveraging specialized networks and multi-agent collaboration. The report also examines novel approaches like Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO), which align LLMs with human preferences, alongside pruning and routing optimizations to improve efficiency. Further sections cover validation frameworks, post-deployment monitoring, and inference optimization, with attention to deploying LLMs on distributed and cloud-based platforms. Emerging areas such as multimodal LLMs, fine-tuning for audio and speech, and challenges related to scalability, privacy, and accountability are also addressed. This report offers actionable insights for researchers and practitioners navigating LLM fine-tuning in an evolving landscape.

In this paper, we aim to investigate the properties of an almost $*$-Ricci-Bourguignon soliton (almost $*-$R-B-S for short) on a Kenmotsu manifold (K-M). We start by proving that if a Kenmotsu manifold (K-M) obeys an almost $*-$R-B-S, then the manifold is $\eta$-Einstein. Furthermore, we establish that if a $(\kappa, -2)'$-nullity distribution, where $\kappa<-1$, has an almost $*$-Ricci-Bourguignon soliton (almost $*-$R-B-S), then the manifold is Ricci flat. Moreover, we establish that if a K-M has almost $*$-Ricci-Bourguignon soliton gradient and the vector field $\xi$ preserves the scalar curvature $r$, then the manifold is an Einstein manifold with a constant scalar curvature given by $r=-n(2n-1)$. Finaly, we have given en example of a almost $*-$R-B-S gradient on the Kenmotsu manifold., Comment: 22 pages