Search

Graph analytics are vital in fields such as social networks, biomedical research, and graph neural networks (GNNs). However, traditional CPUs and GPUs struggle with the memory bottlenecks caused by large graph datasets and their fine-grained memory accesses. While specialized graph accelerators address these challenges, they often support only moderate-sized graphs (under 500 million edges). Our paper proposes Swift, a novel scale-up graph accelerator framework that processes large graphs by leveraging the flexibility of FPGA custom datapath and memory resources, and optimizes utilization of high-bandwidth 3D memory (HBM). Swift supports up to 8 FPGAs in a node. Swift introduces a decoupled, asynchronous model based on the Gather-Apply-Scatter (GAS) scheme. It subgraphs across FPGAs, and each subgraph into intervals based on source vertex IDs. Processing on these intervals is decoupled and executed asynchronously, instead of bulk-synchonous operation, where throughput is limited by the slowest task. This enables simultaneous processing within each multi-FPGA node and optimizes the utilization of communication (PCIe), off-chip (HBM), and on-chip BRAM/URAM resources. Swift demonstrates significant performance improvements compared to prior scalable FPGA-based frameworks, performing 12.8 times better than the ForeGraph. Performance against Gunrock on NVIDIA A40 GPUs is mixed, because NVlink gives the GPU system a nearly 5X bandwidth advantage, but the FPGA system nevertheless achieves 2.6x greater energy efficiency., Comment: Accepted in International Conference on Field Programmable Technology (FPT-2024)

In recent years, the development of the Lunar Gateway and Artemis missions has renewed interest in lunar exploration, including both manned and unmanned missions. This interest necessitates accurate initial orbit determination (IOD) and orbit prediction (OP) in this domain, which faces significant challenges such as severe nonlinearity, sensitivity to initial conditions, large state-space volume, and sparse, faint, and unreliable measurements. This paper explores the capability of data-driven Koopman operator-based approximations for OP in these scenarios. Three stable periodic trajectories from distinct cislunar families are analyzed. The analysis includes theoretical justification for using a linear time-invariant system as the data-driven surrogate. This theoretical framework is supported by experimental validation. Furthermore, the accuracy is assessed by comparing the spectral content captured to period estimates derived from the fast Fourier transform (FFT) and Poincare-like sections., Comment: arXiv admin note: text overlap with arXiv:2401.13784

Deep learning (DL) models are popular across various domains due to their remarkable performance and efficiency. However, their effectiveness relies heavily on large amounts of labeled data, which are often time-consuming and labor-intensive to generate manually. To overcome this challenge, it is essential to develop strategies that reduce reliance on extensive labeled data while preserving model performance. In this paper, we propose FisherMask, a Fisher information-based active learning (AL) approach that identifies key network parameters by masking them based on their Fisher information values. FisherMask enhances batch AL by using Fisher information to select the most critical parameters, allowing the identification of the most impactful samples during AL training. Moreover, Fisher information possesses favorable statistical properties, offering valuable insights into model behavior and providing a better understanding of the performance characteristics within the AL pipeline. Our extensive experiments demonstrate that FisherMask significantly outperforms state-of-the-art methods on diverse datasets, including CIFAR-10 and FashionMNIST, especially under imbalanced settings. These improvements lead to substantial gains in labeling efficiency. Hence serving as an effective tool to measure the sensitivity of model parameters to data samples. Our code is available on \url{https://github.com/sgchr273/FisherMask}.

This paper explores static wormhole solutions in f(Q,T) theory, where Q is the non-metricity and T is the trace of energy-momentum tensor. We derive the field equations that describe gravitational phenomena in the existence of non-metricity and matter source terms. We examine different models of this theory to determine the explicit expressions of matter contents, which are useful for analyzing the wormhole structures. We investigate the existence of feasible traversable wormhole solutions for constant and variable redshift functions. To determine whether physically viable wormhole geometry exists, we examine the graphical interpretation of energy constraints for different values of model parameters. It is found that realistic traversable and stable wormhole solutions exist only for the first model of this gravity., Comment: 37 pages, 5 figures

This research paper examines the feasibility and stability of compact stars in the context of $f(\mathcal{Q})$ theory, where $\mathcal{Q}$ represents the non-metricity scalar. To achieve this objective, a static spherical line element is assumed in the interior region and the Schwarzschild spacetime is used in the exterior region of the star. The unknown constants are determined by using the Darmois junction conditions. We consider a specific model of this theory to investigate the viability of compact stars through various physical quantities such as matter contents, energy bounds, anisotropy and state parameters. The stability states for the stellar objects under consideration are determined by the speed of sound and adiabatic index, respectively. The resulting data indicate that the compact stars in this modified framework are physically viable and stable., Comment: 33 pages, 12 figures

Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the user is likely to signal it by rephrasing the request, expressing frustration, or pivoting to an alternative task. Such signals are task-independent and occupy a relatively constrained subspace of language, allowing the LLM to identify them even if it fails on the actual task. This creates an avenue for continually learning from interactions without additional annotations. We introduce ReSpect, a method to learn from such signals in past interactions via retrospection. We deploy ReSpect in a new multimodal interaction scenario, where humans instruct an LLM to solve an abstract reasoning task with a combinatorial solution space. Through thousands of interactions with humans, we show how ReSpect gradually improves task completion rate from 31% to 82%, all without any external annotation.

This article examines the cosmic evolution in the framework of symmetric teleparallel theory, characterized by the function of non-metricity scalar $(\mathcal{Q})$. We use the e-folding number and reconstruction method with a suitable parametrization of the scale factor to obtain the functional form of symmetric teleparallel theory. Using this reconstructed model, we examine the behavior of different cosmographic parameters to demonstrate the bouncing scenarios of the cosmos by considering the contraction and expansion phases of cosmos before and after the bouncing point, respectively. It is found that the null energy condition is violated which shows that the singularity issue can be resolved in this extended theoretical framework. Moreover, we observe that the acceleration occurs near the bouncing point and the reconstructed model aligns with the current cosmic expansion. Finally, we check the validity of second law of thermodynamics in the bouncing framework of our model., Comment: 26 pages, 8 figures, Accepted Eur. Phys. J. C (2024)

Recent advancements in protein structure prediction, particularly AlphaFold2, have revolutionized structural biology by achieving near-experimental accuracy ($\text{average RMSD} < 1.5\text{\AA}$). However, the computational demands of these models (approximately 30 minutes per protein on an RTX 4090) significantly limit their application in high-throughput protein screening. While large language models like ESM (Evolutionary Scale Modeling) have shown promise in extracting structural information directly from protein sequences, rapid assessment of protein structure quality for large-scale analyses remains a major challenge. We introduce pLDDT-Predictor, a high-speed protein screening tool that achieves a $250,000\times$ speedup compared to AlphaFold2 by leveraging pre-trained ESM2 protein embeddings and a Transformer architecture. Our model predicts AlphaFold2's pLDDT (predicted Local Distance Difference Test) scores with a Pearson correlation of 0.7891 and processes proteins in just 0.007 seconds on average. Using a comprehensive dataset of 1.5 million diverse protein sequences (ranging from 50 to 2048 amino acids), we demonstrate that pLDDT-Predictor accurately classifies high-confidence structures (pLDDT $>$ 70) with 91.2\% accuracy and achieves an MSE of 84.8142 compared to AlphaFold2's predictions. The source code and pre-trained models are freely available at \url{https://github.com/jw-chae/pLDDT_Predictor}, enabling the research community to perform rapid, large-scale protein structure quality assessments., Comment: 6 pages main topic, 8 pages including citiation, 4 figures

LSMR is a widely recognized method for solving least squares problems via the double QR decomposition. Various preconditioning techniques have been explored to improve its efficiency. One issue that arises when implementing these preconditioning techniques is the need to solve two linear systems per iterative step. In this paper, to tackle this issue, among others, a modified LSMR method (MLSMR), in which only one linear system per iterative step needs to be solved instead of two, is introduced, and then it is integrated with the idea of flexible GMRES to yield a flexible MLSMR method (FMLSMR). Numerical examples are presented to demonstrate the efficiency of the proposed FMLSMR method., Comment: 19 pages, 2 figures

Systems with both language comprehension and generation capabilities can benefit from the tight connection between the two. This work studies coupling comprehension and generation with focus on continually learning from interaction with users. We propose techniques to tightly integrate the two capabilities for both learning and inference. We situate our studies in two-player reference games, and deploy various models for thousands of interactions with human users, while learning from interaction feedback signals. We show dramatic improvements in performance over time, with comprehension-generation coupling leading to performance improvements up to 26% in absolute terms and up to 17% higher accuracies compared to a non-coupled system. Our analysis also shows coupling has substantial qualitative impact on the system's language, making it significantly more human-like., Comment: 17 pages, 9 figures

Our manuscript aims to analysis the viability and stability of anisotropic stellar objects in the modified symmetric teleparallel gravity. A particular model of this extended theory is considered to formulate explicit field equations which govern the interaction between matter and geometry. The configuration of static spherical symmetric structures is examined through the Finch-Skea solution. However, the values of unknown constants in the metric potentials are evaluated by the Darmois junction conditions. For the viability of proposed stellar objects, the physical parameters including density, pressure, anisotropy, mass, energy constraints, compactness function and redshift are analyzed. Furthermore, stability of the proposed stellar objects is investigated by causality condition, Herrera cracking approach and adiabatic index. Our findings indicate that the proposed stellar objects are viable as well as stable in the presence of correction terms., Comment: 24 pages, 11 figures, Accepted

The main objective of this article is to investigate the viability of bouncing cosmological scenarios using different forms of scale factors with perfect matter configuration in the framework of extended symmetric teleparallel theory. This modified proposal is defined by the function $f(Q,T)$, where $Q$ characterizes non-metricity and $T$ denotes the trace of energy-momentum tensor. We investigate the modified field equations of this theory using different parametric values of the Hubble parameter and non-metricity to derive viable solutions. These solutions are relevant in various cosmological bounce models such as symmetric-bounce, super-bounce, oscillatory-bounce, matter-bounce and exponential-bounce models. Furthermore, we examine the behavior of energy density and pressure to analyze the characteristics of dark energy. A comprehensive analysis is also conducted to explore the behavior of the equation of state parameter and deceleration parameter to examine the evolutionary eras of the cosmos. Our findings show that the $f(Q,T)$ gravity describes the cosmic expansion in the vicinity of the bouncing point during the early and late times of cosmic evolution., Comment: 31 pages, 23 figures, The European Physical Journal C (Accepted)

This paper explores the viability and stability of compact stellar objects characterized by anisotropic matter in the framework of $f(\mathrm{Q},\mathrm{T})$ theory, where $\mathrm{Q}$ denotes non-metricity and $\mathrm{T}$ represents the trace of the energy-momentum tensor. We consider a specific model of this theory to obtain explicit expressions for the field equations governing the behavior of matter and geometry in this context. Furthermore, the Karmarkar condition is employed to assess the configuration of static spherically symmetric structures. The values of unknown constants in the metric potentials are determined through matching conditions of the interior and exterior spacetimes. Various physical quantities such as fluid parameters, energy constraints, equation of state parameters, mass, compactness and redshift are graphically analyzed to evaluate the viability of the considered compact stars. The Tolman-Oppenheimer-Volkoff equation is used to examine the equilibrium state of the stellar models. Moreover, the stability of the proposed compact stars is investigated through sound speed and adiabatic index methods. This study concludes that the proposed compact stars analyzed in this theoretical framework are viable and stable, as all the required conditions are satisfied., Comment: 46 pages, 14 figures

InAs quantum wells (QWs) grown on InP substrates are interesting for their applications in devices with high spin-orbit coupling (SOC) and their potential role in creating topologically nontrivial hybrid heterostructures. The highest mobility QWs are limited by interfacial roughness scattering and alloy disorder scattering in the cladding and buffer layers. Increasing QW thickness has been shown to reduce the effect of both of these scattering mechanisms. However, for current state-of-the-art devices with As-based cladding and barrier layers, the critical thickness is limited to $\leq7$ nm. In this report, we demonstrate the use of strain compensation techniques in the InGaAs cladding layers to extend the critical thickness well beyond this limit. We induce tensile strain in the InGaAs cladding layers by reducing the In concentration from In$_{0.81}$Ga$_{0.19}$As to In$_{0.70}$Ga$_{0.30}$As and we observe changes in both the critical thickness of the well and the maximum achievable mobility. The peak electron mobility at 2 K is $1.16\times10^6$ cm$^2/$Vs, with a carrier density of $4.2\times10^{11}$ /cm$^2$. Additionally, we study the quantum lifetime and Rashba spin splitting in the highest mobility device as these parameters are critical to determine if these structures can be used in topologically nontrivial devices.

SARS-CoV-2, the highly contagious pathogen responsible for the COVID-19 pandemic, has persistent effects that begin four weeks after initial infection and last for an undetermined duration. These chronic effects are more harmful than acute ones. This review explores the long-term impact of the virus on various human organs, including the pulmonary, cardiovascular, neurological, reproductive, gastrointestinal, musculoskeletal, endocrine, and lymphoid systems, particularly in older adults. Regarding diagnosis, RT-PCR is the gold standard for detecting COVID-19, though it requires specialized equipment, skilled personnel, and considerable time to produce results. To address these limitations, artificial intelligence in imaging and microfluidics technologies offers promising alternatives for diagnosing COVID-19 efficiently. Pharmacological and non-pharmacological strategies are effective in mitigating the persistent impacts of COVID-19. These strategies enhance immunity in post-COVID-19 patients by reducing cytokine release syndrome, improving T cell response, and increasing the circulation of activated natural killer and CD8 T cells in blood and tissues. This, in turn, alleviates symptoms such as fever, nausea, fatigue, muscle weakness, and pain. Vaccines, including inactivated viral, live attenuated viral, protein subunit, viral vectored, mRNA, DNA, and nanoparticle vaccines, significantly reduce the adverse long-term effects of the virus. However, no vaccine has been reported to provide lifetime protection against COVID-19. Consequently, protective measures such as physical distancing, mask usage, and hand hygiene remain essential strategies. This review offers a comprehensive understanding of the persistent effects of COVID-19 on individuals of varying ages, along with insights into diagnosis, treatment, vaccination, and future preventative measures against the spread of SARS-CoV-2.

This study aims to explore the Garcia-Salcedo ghost dark energy and generalized ghost dark energy models in the context of $f(\mathrm{R},\mathrm{T^2})$ theory, where $\mathrm{R}$ is the Ricci scalar and $\mathrm{T^2}$ is the self-contraction of stress-energy tensor. We investigate the non-interacting case only corresponding to flat Friedmann-Robertson-Walker universe. We reconstruct the corresponding $f(\mathrm{R},\mathrm{T^2})$ gravity models using the considered dark energy models by taking two particular models of this gravity. The stability analysis is performed for all the cases. The behavior of the equation of state parameter is also checked. It is found that some of the reconstructed $f(\mathrm{R},\mathrm{T^2})$ models successfully describe both the phantom and quintessence epochs of the universe, which support the current cosmic accelerated expansion. This exploration reveals the intricate connections between dark energy models and modified gravitational theory, providing significant understanding into the dynamics of the cosmos on a large scale., Comment: 26 pages, 11 figures, Accepted

This paper investigated the viable traversable wormhole solutions through Karmarkar condition in the context of $f(\mathcal{G},T)$ theory. A static spherical spacetime with anisotropic matter configuration is used to study the wormhole geometry. Karmarkar condition is used to develop a viable shape function for a static wormhole structure. A wormhole geometry is constructed using the resulting shape function that satisfies all the required conditions and connects the asymptotically flat regions of the spacetime. To assess the viability of traversable wormhole geometries, the energy conditions are analyzed by various models of this theory. Further, their stable state is investigated through sound speed and adiabatic index. This investigation demonstrates the presence of viable traversable wormhole solutions in the modified theory., Comment: 31 pages, 26 figures

Cell segmentation is essential in biomedical research for analyzing cellular morphology and behavior. Deep learning methods, particularly convolutional neural networks (CNNs), have revolutionized cell segmentation by extracting intricate features from images. However, the robustness of these methods under microscope optical aberrations remains a critical challenge. This study evaluates cell image segmentation models under optical aberrations from fluorescence and bright field microscopy. By simulating different types of aberrations, including astigmatism, coma, spherical aberration, trefoil, and mixed aberrations, we conduct a thorough evaluation of various cell instance segmentation models using the DynamicNuclearNet (DNN) and LIVECell datasets, representing fluorescence and bright field microscopy cell datasets, respectively. We train and test several segmentation models, including the Otsu threshold method and Mask R-CNN with different network heads (FPN, C3) and backbones (ResNet, VGG, Swin Transformer), under aberrated conditions. Additionally, we provide usage recommendations for the Cellpose 2.0 Toolbox on complex cell degradation images. The results indicate that the combination of FPN and SwinS demonstrates superior robustness in handling simple cell images affected by minor aberrations. In contrast, Cellpose 2.0 proves effective for complex cell images under similar conditions. Furthermore, we innovatively propose the Point Spread Function Image Label Classification Model (PLCM). This model can quickly and accurately identify aberration types and amplitudes from PSF images, assisting researchers without optical training. Through PLCM, researchers can better apply our proposed cell segmentation guidelines.

This paper investigates the central role played by the Hamiltonian in continuous-time nonlinear optimal control problems. We show that the strict convexity of the Hamiltonian in the control variable is a sufficient condition for the existence of a unique optimal trajectory, and the nonlinearity/non-convexity of the dynamics and the cost are immaterial. The analysis is extended to discrete-time problems, revealing that discretization destroys the convex Hamiltonian structure, leading to multiple spurious optima, unless the time discretization is sufficiently small. We present simulated results comparing the "indirect" Iterative Linear Quadratic Regulator (iLQR) and the "direct" Sequential Quadratic Programming (SQP) approach for solving the optimal control problem for the cartpole and pendulum models to validate the theoretical analysis. Results show that the ILQR always converges to the "globally" optimum solution while the SQP approach gets stuck in spurious minima given multiple random initial guesses for a time discretization that is insufficiently small, while both converge to the same unique solution if the discretization is sufficiently small.

Managing the limited energy on mobile platforms executing long-running, resource intensive streaming applications requires adapting an application's operators in response to their power consumption. For example, the frame refresh rate may be reduced if the rendering operation is consuming too much power. Currently, predicting an application's power consumption requires (1) building a device-specific power model for each hardware component, and (2) analyzing the application's code. This approach can be complicated and error-prone given the complexity of an application's logic and the hardware platforms with heterogeneous components that it may execute on. We propose eScope, an alternative method to directly estimate power consumption by each operator in an application. Specifically, eScope correlates an application's execution traces with its device-level energy draw. We implement eScope as a tool for Android platforms and evaluate it using workloads on several synthetic applications as well as two video stream analytics applications. Our evaluation suggests that eScope predicts an application's power use with 97% or better accuracy while incurring a compute time overhead of less than 3%.

The main objective of this manuscript is to investigate the bouncing cosmology in the background of $f(\mathcal{Q})$ gravity, where $\mathcal{Q}$ defines the non-metricity. For this purpose, we use the reconstruction approach and consider a flat Friedmann-Robertson-Walker spacetime with perfect matter configuration. We examine how the first contracting phase gives the expansion by using a temporal derivative of the scale factor, i.e., $\dot{a}<0$, $\dot{a}=0$ and $\dot{a}>0$ give contraction, bounce point and expansion phases, respectively. Further, we use the order reduction method to solve the modified field equations as these are very difficult due to the presence of additional non-linear expressions. It is analyzed that the original singularity of the universe diminishes for the required bounce conditions. We conclude that the acceleration occurs near the bouncing point and the considered $f(\mathcal{Q})$ models are consistent with the current cosmic accelerated expansion., Comment: 23 pages, 8 figures

The main objective of this article is to study the viable compact stellar structures in non-Riemannian geometry, i.e., $f(\mathbb{Q},T)$ theory, where $\mathbb{Q}$ defines the non-metricity and $T$ represents trace of the stress-energy tensor. In this perspective, we consider a static spherical metric with anisotropic matter configuration to examine the geometry of considered compact stars. A specific model of this theory is used to derive the explicit expressions of energy density and pressure components that govern the relationship between matter and geometry. The unknown parameters are evaluated by using the continuity of inner and outer spacetimes to examine the configuration of spherical stellar structures. Physical parameters such as fluid characteristics, energy constraints and equation of state parameters are analyzed to examine the viability of the considered stellar objects. Further, we use Tolman-Oppenheimer-Volkoff equation, sound speed and adiabatic index methods to analyze the equilibrium state and stability of the proposed stellar objects. The rigorous analysis and satisfaction of necessary conditions lead to the conclusion that the stellar objects studied in this framework are viable and stable., Comment: 39 pages, 9 figures

High In content InGaAs quantum wells (In $\geq$ 75%) are potentially useful for topological quantum computing and spintronics applications. In high mobility InGaAs quantum wells, alloy disorder scattering is a limiting factor. In this report, we demonstrate that by growing the InGaAs quantum wells as a digital alloy, or a short period superlattice, we can reduce the alloy disorder scattering within the quantum well and increase the peak 2 K electron mobility to 545,000 cm^2/V s, which is the highest reported mobility for high In content InGaAs quantum wells to the best of the authors' knowledge. Our results demonstrate that the digital alloy approach can be used to increase the mobility of quantum wells in random alloy ternary materials.

This paper considers the infinite horizon optimal control problem for nonlinear systems. Under the condition of nonlinear controllability of the system to any terminal set containing the origin and forward invariance of the terminal set, we establish a regularized solution approach consisting of a ``finite free final time" optimal transfer problem to the terminal set which renders the set globally asymptotically stable. Further, we show that the approximations converge to the optimal infinite horizon cost as the size of the terminal set decreases to zero. We also perform the analysis for the discounted problem and show that the terminal set is asymptotically stable only for a subset of the state space and not globally. The theory is empirically evaluated on various nonholonomic robotic systems to show that the cost of our approximate problem converges and the transfer time into the terminal set is dependent on the initial state of the system, necessitating the free final time formulation.

Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these models exhibit a bias for contrast-based images, with diminished performance on texture-based medical images. This study introduces the notion of a population-level context for pathology detection and employs a graph theoretic approach to model and incorporate it into the latent code of an autoencoder via a refinement module we term PopuSense. PopuSense seeks to capture additional intra-group variations inherent in biomedical data that a local or global context of the convolutional model might miss or smooth out. Proof-of-concept experiments on contrast-based and texture-based images, with minimal adaptation, encounter the existing preference for intensity-based input. Nevertheless, PopuSense demonstrates improved separability in contrast-based images, presenting an additional avenue for refining representations learned by a model.