Search

Segment Anything Model 2 (SAM 2) has emerged as a powerful tool for video object segmentation and tracking anything. Key components of SAM 2 that drive the impressive video object segmentation performance include a large multistage image encoder for frame feature extraction and a memory mechanism that stores memory contexts from past frames to help current frame segmentation. The high computation complexity of multistage image encoder and memory module has limited its applications in real-world tasks, e.g., video object segmentation on mobile devices. To address this limitation, we propose EfficientTAMs, lightweight track anything models that produce high-quality results with low latency and model size. Our idea is based on revisiting the plain, nonhierarchical Vision Transformer (ViT) as an image encoder for video object segmentation, and introducing an efficient memory module, which reduces the complexity for both frame feature extraction and memory computation for current frame segmentation. We take vanilla lightweight ViTs and efficient memory module to build EfficientTAMs, and train the models on SA-1B and SA-V datasets for video object segmentation and track anything tasks. We evaluate on multiple video segmentation benchmarks including semi-supervised VOS and promptable video segmentation, and find that our proposed EfficientTAM with vanilla ViT perform comparably to SAM 2 model (HieraB+SAM 2) with ~2x speedup on A100 and ~2.4x parameter reduction. On segment anything image tasks, our EfficientTAMs also perform favorably over original SAM with ~20x speedup on A100 and ~20x parameter reduction. On mobile devices such as iPhone 15 Pro Max, our EfficientTAMs can run at ~10 FPS for performing video object segmentation with reasonable quality, highlighting the capability of small models for on-device video object segmentation applications.

This study integrates Transit Signal Priority (TSP) into multi-agent reinforcement learning (MARL) based traffic signal control. The first part of the study develops adaptive signal control based on MARL for a pair of coordinated intersections in a microscopic simulation environment. The two agents, one for each intersection, are centrally trained using a value decomposition network (VDN) architecture. The trained agents show slightly better performance compared to coordinated actuated signal control based on overall intersection delay at v/c of 0.95. In the second part of the study the trained signal control agents are used as background signal controllers while developing event-based TSP agents. In one variation, independent TSP agents are formulated and trained under a decentralized training and decentralized execution (DTDE) framework to implement TSP at each intersection. In the second variation, the two TSP agents are centrally trained under a centralized training and decentralized execution (CTDE) framework and VDN architecture to select and implement coordinated TSP strategies across the two intersections. In both cases the agents converge to the same bus delay value, but independent agents show high instability throughout the training process. For the test runs, the two independent agents reduce bus delay across the two intersections by 22% compared to the no TSP case while the coordinated TSP agents achieve 27% delay reduction. In both cases, there is only a slight increase in delay for a majority of the side street movements.

Spin relaxation of electrons in materials involve both reversible dephasing and irreversible decoherence processes. Their interplay leads to a complex dependence of spin relaxation times on the direction and magnitude of magnetic fields, relevant for spintronics and quantum information applications. Here, we use real-time first-principles density matrix dynamics simulations to directly simulate Hahn echo measurements, disentangle dephasing from decoherence, and predict T1, T2 and T2* spin lifetimes. We show that g-factor fluctuations lead to non-trivial magnetic field dependence of each of these lifetimes in inversion-symmetric crystals of CsPbBr3 and silicon, even when only intrinsic spin-phonon scattering is present. Most importantly, fluctuations in the off-diagonal components of the g-tensor lead to a strong magnetic field dependence of even the T1 lifetime in silicon. Our calculations elucidate the detailed role of anisotropic g-factors in determining the spin dynamics even in simple, low spin-orbit coupling materials such as silicon.

Mitigating climate change requires transforming agriculture to minimize environ mental impact and build climate resilience. Regenerative agricultural practices enhance soil organic carbon (SOC) levels, thus improving soil health and sequestering carbon. A challenge to increasing regenerative agriculture practices is cheaply measuring SOC over time and understanding how SOC is affected by regenerative agricultural practices and other environmental factors and farm management practices. To address this challenge, we introduce an AI-driven Soil Organic Carbon Copilot that automates the ingestion of complex multi-resolution, multi-modal data to provide large-scale insights into soil health and regenerative practices. Our data includes extreme weather event data (e.g., drought and wildfire incidents), farm management data (e.g., cropland information and tillage predictions), and SOC predictions. We find that integrating public data and specialized models enables large-scale, localized analysis for sustainable agriculture. In comparisons of agricultural practices across California counties, we find evidence that diverse agricultural activity may mitigate the negative effects of tillage; and that while extreme weather conditions heavily affect SOC, composting may mitigate SOC loss. Finally, implementing role-specific personas empowers agronomists, farm consultants, policymakers, and other stakeholders to implement evidence-based strategies that promote sustainable agriculture and build climate resilience.

Addressing climate change calls for action to control CO$_2$ pollution. Direct air and ocean capture offer a solution to this challenge. Making carbon capture competitive with alternatives, such as forestation and mineralisation, requires fundamentally novel approaches and ideas. One such approach is electrosorption, which is currently limited by the availability of suitable electrosorbents. In this work, we introduce a metal-organic copper-2,3,6,7,10,11-hexahydroxytriphenylene (Cu$_3$(HHTP)$_2$) metal-organic framework (MOF) that can act as electrosorbent for CO$_2$ capture, thereby expanding the palette of materials that can be used for this process. Cu$_3$(HHTP)$_2$ is the first MOF to switch its ability to capture and release CO$_2$ in aqueous electrolytes. By using cyclic voltammetry (CV) and differential electrochemical mass spectrometry (DEMS), we demonstrate reversible CO$_2$ electrosorption. Based on density functional theory (DFT) calculations, we provide atomistic insights into the mechanism of electrosorption and conclude that efficient CO$_2$ capture is facilitated by a combination of redox-active copper and aromatic HHTP ligand within Cu3(HHTP)2. By showcasing the applicability of Cu$_3$(HHTP)$_2$ -- with a CO$_2$ capacity of 2 mmol g$^{-1}$ and an adsorption enthalpy of -20 kJ mol$^{-1}$ - this study encourages further exploration of conductive redox-active MOFs in the search for superior CO$_2$ electrosorbents., Comment: 17 pages, 4 figures, supporting information

Uncertainty quantification is crucial in time series prediction, and quantile regression offers a valuable mechanism for uncertainty quantification which is useful for extreme value forecasting. Although deep learning models have been prominent in multi-step ahead prediction, the development and evaluation of quantile deep learning models have been limited. We present a novel quantile regression deep learning framework for multi-step time series prediction. In this way, we elevate the capabilities of deep learning models by incorporating quantile regression, thus providing a more nuanced understanding of predictive values. We provide an implementation of prominent deep learning models for multi-step ahead time series prediction and evaluate their performance under high volatility and extreme conditions. We include multivariate and univariate modelling, strategies and provide a comparison with conventional deep learning models from the literature. Our models are tested on two cryptocurrencies: Bitcoin and Ethereum, using daily close-price data and selected benchmark time series datasets. The results show that integrating a quantile loss function with deep learning provides additional predictions for selected quantiles without a loss in the prediction accuracy when compared to the literature. Our quantile model has the ability to handle volatility more effectively and provides additional information for decision-making and uncertainty quantification through the use of quantiles when compared to conventional deep learning models.

The Magellanic Stream has long been known to contain multiple HI strands and corresponding stellar populations are beginning to be discovered. Combining an H3-selected sample with stars drawn from the Gaia catalog, we trace stars along a sub-dominant strand of the Magellanic Stream, as defined by gas content, across 30$^\circ$ on the sky. We find that the dominant strand is devoid of stars with Galactocentric distance $\lesssim 55$ kpc while the subdominant strand shows a close correspondence to such stars. We conclude that (1) the two Stream strands have different origins, (2) they are likely only close in projection, (3) the subdominant strand is tidal in origin, and (4) the subdominant strand is composed of disk material, likely drawn from the disk of the Small Magellanic Cloud., Comment: 8 pages, 8 figures

This paper presents Llama Guard 3-1B-INT4, a compact and efficient Llama Guard model, which has been open-sourced to the community during Meta Connect 2024. We demonstrate that Llama Guard 3-1B-INT4 can be deployed on resource-constrained devices, achieving a throughput of at least 30 tokens per second and a time-to-first-token of 2.5 seconds or less on a commodity Android mobile CPU. Notably, our experiments show that Llama Guard 3-1B-INT4 attains comparable or superior safety moderation scores to its larger counterpart, Llama Guard 3-1B, despite being approximately 7 times smaller in size (440MB).

The detection and subsequent inference of binary black hole signals rely heavily on the accuracy of the waveform model employed. In the highly non-linear, dynamic, and strong-field regime near merger, these waveforms can only be accurately modeled through numerical relativity simulations. Considering the precision requirements of next-generation gravitational wave observatories, we present in this paper high-resolution simulations of four non-spinning quasi-circular binary black hole systems with mass ratios of 1, 2, 3, and 4, conducted using the GR-Athena++ code. We extract waveforms from these simulations using both finite radius and Cauchy characteristic extraction methods. Additionally, we provide a comprehensive error analysis to evaluate the accuracy and convergence of the waveforms. This dataset encompasses gravitational waves of the precision (self-mismatch) demanded by upcoming gravitational detectors such as LISA, Cosmic Explorer, and Einstein Telescope. The waveforms are publicly available on ScholarSphere, and represent the first set of waveforms of the new GR-Athena++ catalog., Comment: The gravitational wave catalog of this work is publicly available at https://scholarsphere.psu.edu/catalog?q=GRAthena

Transition metal telluride compositions are explored extensively for their unique magnetic behavior. Since chromium telluride (Cr2Te3) exhibits a near-room-temperature phase transition, the material can be effectively used in applications such as magnetic refrigeration. Compared to existing magnetocaloric materials, Heusler alloys, and rare-earth-based alloys, the large-scale synthesis of Cr2Te3 involves less complexity, resulting in a stable composition. Compared to existing tellurides, Cr2Te3 exhibited a large magnetic entropy change of 2.36 J/kg-K at a very small magnetic field of 0.1 T. The refrigeration capacity (RC) of 160 J/kg was determined from entropy change versus temperature curve. The results were comparable with the existing Cr compounds. The telluride system, Cr2Te3 compared to pure gadolinium, reveals an enhanced room temperature magnetocaloric effect (MCE) with a broad working temperature range. The heating cycle of MCE was successfully visualized using a thermal imaging setup. To confirm the observed magnetic properties of Cr2Te3, first-principles calculations were conducted. Through density functional theory (DFT) studies, we were able to determine both Curie temperature (TC) and Neel temperature (TN) which validated our experimental transitions at the same temperatures. Structural transition was also observed using first principles DFT calculation which is responsible for magnetic behavior.

In recent years, with the rapid development of augmented reality (AR) technology, there is an increasing demand for multi-user collaborative experiences. Unlike for single-user experiences, ensuring the spatial localization of every user and maintaining synchronization and consistency of positioning and orientation across multiple users is a significant challenge. In this paper, we propose a multi-user localization system based on ORB-SLAM2 using monocular RGB images as a development platform based on the Unity 3D game engine. This system not only performs user localization but also places a common virtual object on a planar surface (such as table) in the environment so that every user holds a proper perspective view of the object. These generated virtual objects serve as reference points for multi-user position synchronization. The positioning information is passed among every user's AR devices via a central server, based on which the relative position and movement of other users in the space of a specific user are presented via virtual avatars all with respect to these virtual objects. In addition, we use deep learning techniques to estimate the depth map of an image from a single RGB image to solve occlusion problems in AR applications, making virtual objects appear more natural in AR scenes.

Task-oriented dialogue systems rely on predefined conversation schemes (dialogue flows) often represented as directed acyclic graphs. These flows can be manually designed or automatically generated from previously recorded conversations. Due to variations in domain expertise or reliance on different sets of prior conversations, these dialogue flows can manifest in significantly different graph structures. Despite their importance, there is no standard method for evaluating the quality of dialogue flows. We introduce FuDGE (Fuzzy Dialogue-Graph Edit Distance), a novel metric that evaluates dialogue flows by assessing their structural complexity and representational coverage of the conversation data. FuDGE measures how well individual conversations align with a flow and, consequently, how well a set of conversations is represented by the flow overall. Through extensive experiments on manually configured flows and flows generated by automated techniques, we demonstrate the effectiveness of FuDGE and its evaluation framework. By standardizing and optimizing dialogue flows, FuDGE enables conversational designers and automated techniques to achieve higher levels of efficiency and automation.

Multi-messenger astronomy, driven by gravitational-wave observations, is a rapidly evolving field poised for significant advancements over the next decade. This paper examines the role of the upcoming LIGO-India detector in enhancing multi-messenger efforts by comparing ten networks using key metrics such as signal-to-noise ratio (SNR), sky localization area ($\Delta \Omega_{90}$), and the precision of astrophysical parameter measurements. Our results show that a network with two L-shaped Cosmic Explorer (CE) detectors and one triangular Einstein Telescope (ET) performs best, detecting nearly the entire annual binary neutron star merger population ($\sim$ 16000 events) up to redshift of 0.5 with SNR $\geq 10$, and localizing over 10000 events within 10 deg$^2$, including 146 events within 0.1 deg$^2$. It detects over 9000 events with relative luminosity distance errors $\Delta D_L / D_L < 0.1$, including 110 with sub-percent errors. Notably, replacing the 20 km CE detector with LIGO-India retains comparable performance, localizing over 9000 events within 10 deg$^2$ and 86 within 0.1 deg$^2$. This network detects over 5700 events with $\Delta D_L / D_L < 0.1$, including 55 events with sub-percent $D_L$ errors. Both networks localize $\mathcal{O}(100)$ mergers within 10 deg$^2$ up to 10 minutes pre-merger, significantly outperforming a network of two CE detectors and LIGO-Livingston. While I$^\sharp$ achieves localization and early warning performance comparable to the 20 km CE detector within the evaluated metrics, its shorter arms and narrower sensitivity band may limit its effectiveness for other science goals. These differences suggest that, although CE20's contributions may extend beyond this paper's scope, our findings underscore LIGO-India's strong potential for precise source localization and extended early warning times--critical advancements for multi-messenger astrophysics., Comment: 17 pages (10 pages main text, 5 pages appendices, 2 pages bibliography), 12 figures, 4 tables

We present the observations of a quiescent filament eruption and its deflection from the radial direction. The event occurred in the southern solar hemisphere on 2021 May 9 and was observed by the Atmospheric Imaging Assembly (AIA) on board the Solar Dynamics Observatory (SDO), by the STEREO A Observatory and GONG. Part of the filament erupted in the west direction, while major part of the filament deviated towards east direction. LASCO observed a very weak CME towards the west direction where it faded quickly. Moreover, the eruption was associated with CME observed by STEREO A COR1 and COR2. Our observations provide the evidence that the filament eruption was highly non-radial in nature., Comment: Accepted in the Proceedings of IAUS 388

Miniaturization of electronic components has led to overheating, increasing power consumption and causing early circuit failures. Conventional heat dissipation methods are becoming inadequate due to limited surface area and higher short-circuit risks. This study presents a fast, low-cost, and scalable technique using 2D hexagonal boron nitride (hBN) coatings to enhance heat dissipation in commercial electronics. Inexpensive hBN layers, applied by drop casting or spray coating, boost thermal conductivity at IC surfaces from below 0.3 W/m-K to 260 W/m-K, resulting in over double the heat flux and convective heat transfer. This significantly reduces operating temperatures and power consumption, as demonstrated by a 17.4% reduction in a coated audio amplifier circuit board. Density functional theory indicates enhanced interaction between 2D hBN and packaging materials as a key factor. This approach promises substantial energy and cost savings for large-scale electronics without altering existing manufacturing processes., Comment: 27 Pages, 5 Figures

Intent discovery is crucial for both building new conversational agents and improving existing ones. While several approaches have been proposed for intent discovery, most rely on clustering to group similar utterances together. Traditional evaluation of these utterance clusters requires intent labels for each utterance, limiting scalability. Although some clustering quality metrics exist that do not require labeled data, they focus solely on cluster geometry while ignoring the linguistic nuances present in conversational transcripts. In this paper, we introduce Keyword-based Utterance Level Clustering Quality (KULCQ), an unsupervised metric that leverages keyword analysis to evaluate clustering quality. We demonstrate KULCQ's effectiveness by comparing it with existing unsupervised clustering metrics and validate its performance through comprehensive ablation studies. Our results show that KULCQ better captures semantic relationships in conversational data while maintaining consistency with geometric clustering principles.

We study an architecture for fault-tolerant measurement-based quantum computation (FT-MBQC) over optically-networked trapped-ion modules. The architecture is implemented with a finite number of modules and ions per module, and leverages photonic interactions for generating remote entanglement between modules and local Coulomb interactions for intra-modular entangling gates. We focus on generating the topologically protected Raussendorf-Harrington-Goyal (RHG) lattice cluster state, which is known to be robust against lattice bond failures and qubit noise, with the modules acting as lattice sites. To ensure that the remote entanglement generation rates surpass the bond-failure tolerance threshold of the RHG lattice, we employ spatial and temporal multiplexing. For realistic system timing parameters, we estimate the code cycle time of the RHG lattice and the ion resources required in a bi-layered implementation, where the number of modules matches the number of sites in two lattice layers, and qubits are reinitialized after measurement. For large distances between modules, we incorporate quantum repeaters between sites and analyze the benefits in terms of cumulative resource requirements. Finally, we derive and analyze a qubit noise-tolerance threshold inequality for the RHG lattice generation in the proposed architecture that accounts for noise from various sources. This includes the depolarizing noise arising from the photonically-mediated remote entanglement generation between modules due to finite optical detection efficiency, limited visibility, and the presence of dark clicks, in addition to the noise from imperfect gates and measurements, and memory decoherence with time. Our work thus underscores the hardware and channel threshold requirements to realize distributed FT-MBQC in a leading qubit platform today -- trapped ions., Comment: 20 pages, 19 figures

Each year, the production of synthetic dye wastewater reaches a trillion tons, posing a significant challenge to addressing water scarcity on a global level. Hence, the treatment of wastewater to prevent water scarcity is of prime importance, and failing to do so will increase ecotoxicological risks and human health. Textile wastewater contains harmful dye. Photocatalytic degradation of such dye-contaminated wastewater is crucial to purifying the dye-contaminated water. However, this process takes time, uses high-power lamps, and is expensive. Here, we report the effect of the concentration of precursor on the size and surface morphology of TiO2 nanostructures prepared by facile hydrothermal synthesis and its ability to perform as a photocatalyst to degrade the most common industrial textile dye, methylene blue (MB), under natural sunlight. The impact of particle size on the photocatalytic activity and photocarrier migration rate was thoroughly examined. Also, the effect of pH on adsorption and photocatalytic degradation has been evaluated in detail. With several optimized conditions, almost complete dye degradation was achieved within 40 minutes under the direct illumination of natural sunlight. The enhanced photocatalytic performance can be correlated to the synergetic effect of a higher charge transfer mechanism, good catalytic active surface area availability (386 m2/g), and several optimized parameters that affect the reaction efficacy. Additionally, repeated use of NPs without sacrificing performance five times confirmed its stability and Sustainability as a promising candidate for large-scale industrial textile wastewater remedies.

Supramolecular gels are formed by the self-assembly of low molecular weight organic gelators with their solvent molecules. These are emerging novel materials with good semiconducting and light emitting properties with application potential as hole and electron transport layers in organic solar cells, LEDs, stimulus-responsive smart semiconducting materials, thin film transistors (TFT) etc. In this context charge transport and mobility of charge carriers in these materials assume extreme significance. In the study, Electrochemical impedance spectroscopy, which is a non-destructive technique, is used to analyze frequency dependent electrochemical impedance values, of a novel meallogel, ZnA_CA (Zinc Acetate_Citric Acid), and used to evaluate the charge properties and mobility. A comparative study of mobility values obtained from diode I-V characteristics of the gel and Impedance measurements has also been made., Comment: 8 pages, 3 figures

Owing to their rapid cooling rate and hence loss-limited propagation distance, cosmic-ray electrons and positrons (CRe) at very high energies probe local cosmic-ray accelerators and provide constraints on exotic production mechanisms such as annihilation of dark matter particles. We present a high-statistics measurement of the spectrum of CRe candidate events from 0.3 to 40 TeV with the High Energy Stereoscopic System (H.E.S.S.), covering two orders of magnitude in energy and reaching a proton rejection power of better than $10^{4}$. The measured spectrum is well described by a broken power law, with a break around 1 TeV, where the spectral index increases from $\Gamma_1 = 3.25$ $\pm$ 0.02 (stat) $\pm$ 0.2 (sys) to $\Gamma_2 = 4.49$ $\pm$ 0.04 (stat) $\pm$ 0.2 (sys). Apart from the break, the spectrum is featureless. The absence of distinct signatures at multi-TeV energies imposes constraints on the presence of nearby CRe accelerators and the local CRe propagation mechanisms., Comment: main paper: 8 pages, 4 figures, supplemental material: 12 pages, 14 figures, accepted for publication in Physical Review Letters https://journals.aps.org/prl/

The ability to generate bipartite entanglement in quantum computing technologies is widely regarded as pivotal. However, the role of genuinely multipartite entanglement is much less understood than bipartite entanglement, particularly in the context of solving complicated optimization problems using quantum devices. It is thus crucial from both the algorithmic and hardware standpoints to understand whether multipartite entanglement contributes to achieving a good solution. Here, we tackle this challenge by analyzing genuine multipartite entanglement -- quantified by the generalized geometric measure -- generated in Trotterized quantum annealing and the quantum approximate optimization algorithm. Using numerical benchmarks, we analyze its occurrence in the annealing schedule in detail. We observe a multipartite-entanglement barrier, and we explore how it correlates to the algorithm's success. We also prove how multipartite entanglement provides an upper bound to the overlap of the instantaneous state with an exact solution. Vice versa, the overlaps to the initial and final product states, which can be easily measured experimentally, offer upper bounds for the multipartite entanglement during the entire schedule. Our results help to shed light on how complex quantum correlations come to bear as a resource in quantum optimization., Comment: 8+5 pages, 7+7 figures

In the past few years, the improved sensitivity and cadence of wide-field optical surveys have enabled the discovery of several afterglows without associated detected gamma-ray bursts (GRBs). We present the identification, observations, and multiwavelength modeling of a recent such afterglow (AT2023lcr), and model three literature events (AT2020blt, AT2021any, and AT2021lfa) in a consistent fashion. For each event, we consider the following possibilities as to why a GRB was not observed: 1) the jet was off-axis; 2) the jet had a low initial Lorentz factor; and 3) the afterglow was the result of an on-axis classical GRB (on-axis jet with physical parameters typical of the GRB population), but the emission was undetected by gamma-ray satellites. We estimate all physical parameters using afterglowpy and Markov Chain Monte Carlo methods from emcee. We find that AT2023lcr, AT2020blt, and AT2021any are consistent with on-axis classical GRBs, and AT2021lfa is consistent with both on-axis low Lorentz factor ($\Gamma_0 \approx 5 - 13$) and off-axis ($\theta_\text{obs}=2\theta_\text{jet}$) high Lorentz factor ($\Gamma_0 \approx 100$) jets., Comment: 40 pages, 18 figures, 20 tables

We show how the flow approach of Duch, with elementary differentials as coordinates, can be used to prove local well-posedness for rough stochastic differential equations driven by fractional Brownian motion with Hurst index $H > \frac{1}{4}$. A novelty appearing here is that we use coordinates for the flow that are indexed by trees rather than multi-indices.

By leveraging the principles of quantum mechanics, QML opens doors to novel approaches in machine learning and offers potential speedup. However, machine learning models are well-documented to be vulnerable to malicious manipulations, and this susceptibility extends to the models of QML. This situation necessitates a thorough understanding of QML's resilience against adversarial attacks, particularly in an era where quantum computing capabilities are expanding. In this regard, this paper examines model-independent bounds on adversarial performance for QML. To the best of our knowledge, we introduce the first computation of an approximate lower bound for adversarial error when evaluating model resilience against sophisticated quantum-based adversarial attacks. Experimental results are compared to the computed bound, demonstrating the potential of QML models to achieve high robustness. In the best case, the experimental error is only 10% above the estimated bound, offering evidence of the inherent robustness of quantum models. This work not only advances our theoretical understanding of quantum model resilience but also provides a precise reference bound for the future development of robust QML algorithms., Comment: 21 pages, 9 figures

The impact of uniform lattice strain (with lattice parameter (LP), $a = 5.62$-$5.83$ \r{A}) and tetragonal lattice distortion (with $0.8 \leq c/a \leq1.2$ and $V_0$ volume; resulting LP: $a = 5.38$-$5.92$ \r{A}, $c = 5.33$-$6.45$ \r{A}) on the structural, electronic, and magnetic properties of CoFeCrGa SGS alloy (optimized LP: $a = 5.72$ \r{A}) has been investigated. The SGS nature of CoFeCrGa remains robust under uniform strain; however, the tetragonal lattice distortion has a detrimental impact on the SGS nature, and even a small distortions lead to metallic nature for CoFeCrGa. Despite this, the tetragonally distorted structures maintain high spin polarization (SP $\geq 60\% $); except for the structure with $c/a = 0.8$, for which SP significantly decreases to $\sim 25\%$. The lattice deformation-induced magnetic anisotropy (MA) is also explored by considering the magnetocrystalline anisotropy (MCA) and the magnetic shape anisotropy (MSA). Both MCA and MSA eliminate for the Y-I ordered and uniformly strained structures, resulting in a magnetic isotropic nature for them. Conversely, the tetragonally distorted structures with $c/a < 1.0$ and $c/a > 1.0$ exhibit very high in-plane magnetic anisotropy and perpendicular magnetic anisotropy, respectively; with magnitudes of $\sim 10^5$-$10^6$ J/m$^3$. For tetragonally deformed structures, MSA contribution to MA is negligible, and thus, MCA dictates the total MA. In summary, the isotropically strained structures show SGS nature, while the tetragonally distorted structures exhibit the high MA along with high SP.

Traditional drug discovery is a long, expensive, and complex process. Advances in Artificial Intelligence (AI) and Machine Learning (ML) are beginning to change this narrative. Here, we provide a comprehensive overview of different AI and ML tools that can be used to streamline and accelerate the drug discovery process. By using data sets to train ML algorithms, it is possible to discover drugs or drug-like compounds relatively quickly, and efficiently. Additionally, we address limitations in AI-based drug discovery and development, including the scarcity of high-quality data to train AI models and ethical considerations. The growing impact of AI on the pharmaceutical industry is also highlighted. Finally, we discuss how AI and ML can expedite the discovery of new antibiotics to combat the problem of worldwide antimicrobial resistance (AMR)., Comment: 65 pages

The Legacy Survey of Space and Time (LSST) at Vera C. Rubin Observatory is planned to begin in the Fall of 2025. The LSST survey cadence has been designed via a community-driven process regulated by the Survey Cadence Optimization Committee (SCOC), which recommended up to 3% of the observing time to carry out Target of Opportunity (ToO) observations. Experts from the scientific community, Rubin Observatory personnel, and members of the SCOC were brought together to deliver a recommendation for the implementation of the ToO program during a workshop held in March 2024. Four main science cases were identified: gravitational wave multi-messenger astronomy, high energy neutrinos, Galactic supernovae, and small potentially hazardous asteroids possible impactors. Additional science cases were identified and briefly addressed in the documents, including lensed or poorly localized gamma-ray bursts and twilight discoveries. Trigger prioritization, automated response, and detailed strategies were discussed for each science case. This document represents the outcome of the Rubin ToO 2024 workshop, with additional contributions from members of the Rubin Science Collaborations. The implementation of the selection criteria and strategies presented in this document has been endorsed in the SCOC Phase 3 Recommendations document (PSTN-056). Although the ToO program is still to be finalized, this document serves as a baseline plan for ToO observations with the Rubin Observatory.

In mission-critical domains such as law enforcement and medical diagnosis, the ability to explain and interpret the outputs of deep learning models is crucial for ensuring user trust and supporting informed decision-making. Despite advancements in explainability, existing methods often fall short in providing explanations that mirror the depth and clarity of those given by human experts. Such expert-level explanations are essential for the dependable application of deep learning models in law enforcement and medical contexts. Additionally, we recognize that most explanations in real-world scenarios are communicated primarily through natural language. Addressing these needs, we propose a novel approach that utilizes characteristic descriptors to explain model decisions by identifying their presence in images, thereby generating expert-like explanations. Our method incorporates a concept bottleneck layer within the model architecture, which calculates the similarity between image and descriptor encodings to deliver inherent and faithful explanations. Through experiments in face recognition and chest X-ray diagnosis, we demonstrate that our approach offers a significant contrast over existing techniques, which are often limited to the use of saliency maps. We believe our approach represents a significant step toward making deep learning systems more accountable, transparent, and trustworthy in the critical domains of face recognition and medical diagnosis.

The radio galaxy NGC 1275, located at the central region of Perseus cluster, is a well-known very high-energy (VHE) gamma-ray emitter. The Major Atmospheric Cherenkov Experiment Telescope has detected two distinct episodes of VHE (E > 80 GeV) gamma-ray emission from NGC 1275 during 2022 December and 2023 January. The second outburst, observed on 2023 January 10, was the more intense of the two, with flux reaching 58$\%$ of the Crab Nebula flux above 80 GeV. The differential energy spectrum measured between 80 GeV and 1.5 TeV can be described by a power law with a spectral index of $\Gamma = - 2.90 \pm 0.16_{stat}$ for both flaring events. The broadband spectral energy distribution derived from these flares, along with quasisimultaneous low-energy counterparts, suggests that the observed gamma-ray emission can be explained using a homogeneous single-zone synchrotron self-Compton model. The physical parameters derived from this model for both flaring states are similar. The intermediate state observed between two flaring episodes is explained by a lower Doppler factor or magnetic field, which subsequently returned to its previous value during the high-activity state observed on 2023 January 10., Comment: 7 Pages, 5 Figures, and 1 Table

We present the results from our extensive hard-to-soft X-ray (NuSTAR, Swift-XRT, XMM-Newton, Chandra) and meter-to-mm wave radio (GMRT, VLA, NOEMA) monitoring campaign of the very nearby (d $=6.9$ Mpc) Type II SN2023ixf spanning $\approx$ 4--165 d post-explosion. This unprecedented dataset enables inferences on the explosion's circumstellar medium (CSM) density and geometry. Specifically, we find that the luminous X-ray emission is well modeled by thermal free-free radiation from the forward shock with rapidly decreasing photo-electric absorption with time. The radio spectrum is dominated by synchrotron radiation from the same shock, and the NOEMA detection of high-frequency radio emission may indicate a new component consistent with the secondary origin. Similar to the X-rays, the level of free-free absorption affecting the radio spectrum rapidly decreases with time as a consequence of the shock propagation into the dense CSM. While the X-ray and the radio modeling independently support the presence of a dense medium corresponding to an \emph{effective} mass-loss rate $\dot{M} \approx 10^{-4}\, \rm M_{\odot}\,yr^{-1}$ at $R = (0.4-14) \times 10^{15}$ (for $v_{\rm w}=\rm 25 \,km\,s^{-1}$), our study points at a complex CSM density structure with asymmetries and clumps. The inferred densities are $\approx$10--100 times those of typical red supergiants, indicating an extreme mass-loss phase of the progenitor in the $\approx$200 years preceding core collapse, which leads to the most X-ray luminous Type II SN and the one with the most delayed emergence of radio emission. These results add to the picture of the complex mass-loss history of massive stars on the verge of collapse and demonstrate the need for panchromatic campaigns to fully map their intricate environments., Comment: 32 pages, 16 figures, 9 Tables

This paper presents novel methods for tuning inverter controller gains using deep reinforcement learning (DRL). A Simulink-developed inverter model is converted into a dynamic link library (DLL) and integrated with a Python-based RL environment, leveraging the multi-core deployment and accelerated computing to significantly reduce RL training time. A neural network-based mechanism is developed to transform the cascaded PI controller into an actor network, allowing optimized gain tuning by an RL agent to mitigate scenarios such as subsynchronous oscillations (SSO) and initial transients. Two distinct tuning approaches are demonstrated: a fixed gain strategy, where controller gains are represented as RL policy (actor network) weights, and an adaptive gain strategy, where gains are dynamically generated as RL policy (actor network) outputs. A comparative analysis of these methods is provided, showcasing their effectiveness in stabilizing the transient performance of grid-forming and grid-following converters and deployment challenges in hardware. Experimental results are presented, demonstrating the enhanced robustness and practical applicability of the RL-tuned controller gains in real-world systems.

The Rayleigh Taylor instability (RTI) occurs at the interface between two fluids of different densities, notably when a heavier fluid sits above a lighter one in an effective gravitational field. This instability is relevant to many astrophysical systems where relativistic effects are significant. We examine the linear theory of relativistic Rayleigh Taylor instability (RRTI) in a magnetized medium, allowing for relativistic fluid motion parallel to the interface. To simplify our derivations, we use an "intermediate frame" where fluids on both sides have the same Lorentz factor. Our analysis yields the dispersion relation for RRTI. We find that the instability occurs when the Atwood number $\mathcal{A}$ = $(\rho_1 h_1 - \rho_2 h_2) / (\rho_1 h_1 + \rho_2 h_2) >0$, without requiring relativistic correction. Relativistic motion increases the effective inertia ($\rho \rightarrow \gamma_*^2 \rho$), weakening the magnetic field's suppression of the instability. In the laboratory frame, the instability growth rate is reduced due to time dilation. These analytical results may inform studies of instabilities in systems such as microquasars, active galactic nuclei, gamma-ray bursts, and radio pulsars.

Anomaly-based cyber threat detection using deep learning is on a constant growth in popularity for novel cyber-attack detection and forensics. A robust, efficient, and real-time threat detector in a large-scale operational enterprise network requires high accuracy, high fidelity, and a high throughput model to detect malicious activities. Traditional anomaly-based detection models, however, suffer from high computational overhead and low detection accuracy, making them unsuitable for real-time threat detection. In this work, we propose LogSHIELD, a highly effective graph-based anomaly detection model in host data. We present a real-time threat detection approach using frequency-domain analysis of provenance graphs. To demonstrate the significance of graph-based frequency analysis we proposed two approaches. Approach-I uses a Graph Neural Network (GNN) LogGNN and approach-II performs frequency domain analysis on graph node samples for graph embedding. Both approaches use a statistical clustering algorithm for anomaly detection. The proposed models are evaluated using a large host log dataset consisting of 774M benign logs and 375K malware logs. LogSHIELD explores the provenance graph to extract contextual and causal relationships among logs, exposing abnormal activities. It can detect stealthy and sophisticated attacks with over 98% average AUC and F1 scores. It significantly improves throughput, achieves an average detection latency of 0.13 seconds, and outperforms state-of-the-art models in detection time.

OT 081 is a well-known, luminous blazar that is remarkably variable in many energy bands. We present the first broadband study of the source which includes very-high-energy (VHE, $E>$100\,GeV) $\gamma$-ray data taken by the MAGIC and H.E.S.S. imaging Cherenkov telescopes. The discovery of VHE $\gamma$-ray emission happened during a high state of $\gamma$-ray activity in July 2016, observed by many instruments from radio to VHE $\gamma$-rays. We identify four states of activity of the source, one of which includes VHE $\gamma$-ray emission. Variability in the VHE domain is found on daily timescales. The intrinsic VHE spectrum can be described by a power-law with index $3.27\pm0.44_{\rm stat}\pm0.15_{\rm sys}$ (MAGIC) and $3.39\pm0.58_{\rm stat}\pm0.64_{\rm sys}$ (H.E.S.S.) in the energy range of 55--300\,GeV and 120--500\,GeV, respectively. The broadband emission cannot be sucessfully reproduced by a simple one-zone synchrotron self-Compton model. Instead, an additional external Compton component is required. We test a lepto-hadronic model that reproduces the dataset well and a proton-synchrotron dominated model that requires an extreme proton luminosity. Emission models that are able to successfully represent the data place the emitting region well outside of the Broad Line Region (BLR) to a location at which the radiative environment is dominated by the infrared thermal radiation field of the dusty torus. In the scenario described by this flaring activity, the source appears to be an FSRQ, in contrast with past categorizations. This suggests that the source can be considered to be a transitional blazar, intermediate between BL~Lac and FSRQ objects., Comment: Accepted on MNRAS Corresponding authors: M. Manganaro, J. Becerra Gonz\'alez, M. Seglar-Arroyo, D. A. Sanchez

Next-generation gravitational-wave observatories are expected to detect over a thousand compact binary coalescence signals daily, with some lasting from minutes to hours. Consequently, multiple signals will overlap in the time-frequency plane, generating a "foreground noise" that predominantly affects the low-frequency range, where binary neutron star inspiral evolution is gradual. This study investigates the impact of such foreground noise on parameter estimation for short-duration binary black hole signals, particularly those with high detector-frame masses and/or located at large redshifts. Our results show a reduction in detection sensitivity by approximately 25\% when the noise power spectrum deviates by up to 50\% from Gaussian noise due to foreground contamination. Despite this, using standard parameter estimation techniques without subtracting overlapping signals, we find that foreground noise has minimal impact, primarily affecting precision. These findings suggest that even in the presence of substantial foreground noise, global-fit techniques, and/or signal subtraction will not be necessary, as accurate recovery of system parameters is achievable with minimal loss in precision., Comment: 12 pages, 11 figures

The Milky Way hosts at least two modes in its present day distribution of Fe and alpha-elements. The exact cause of this bimodality is disputed, but one class of explanations involves the merger between the Milky Way and a relatively massive satellite (Gaia-Sausage-Enceladus) at z~2. However, reproducing this bimodality in simulations is not straightforward, with conflicting results on the prevalance, morphology, and mechanism behind multimodality. We present a case study of a galaxy in the Illustris TNG50 simulation which undergoes sequential phases of starburst, brief quiescence, and then rejuvenation. This scenario results in a pronounced abundance bimodality after a post-processing adjustment of the [alpha/Fe] of old stars designed to mimic a higher star formation efficiency in dense gas. The high- and low-alpha sequences are separated in time by the brief quiescent period, which is not associated with a merger but by the formation of a bar followed by AGN activity. This galaxy indicates a novel scenario in which the alpha-bimodality in the Milky Way is caused by the formation of the bar via AGN-induced quenching. In addition to a stellar age gap in the Milky Way, we predict that abundance bimodalities should be more common in barred as opposed to unbarred galaxies., Comment: 13+10 pages, 5+18 figures, to be submitted to ApJ; comments welcome

We consider algorithms and spectral bounds for sparsest cut and conductance in directed polymatrodal networks. This is motivated by recent work on submodular hypergraphs \cite{Yoshida19,LiM18,ChenOT23,Veldt23} and previous work on multicommodity flows and cuts in polymatrodial networks \cite{ChekuriKRV15}. We obtain three results. First, we obtain an $O(\sqrt{\log n})$-approximation for sparsest cut and point out how this generalizes the result in \cite{ChenOT23}. Second, we consider the symmetric version of conductance and obtain an $O(\sqrt{OPT \log r})$ approximation where $r$ is the maximum degree and we point out how this generalizes previous work on vertex expansion in graphs. Third, we prove a non-constructive Cheeger like inequality that generalizes previous work on hypergraphs. We provide a unified treatment via line-embeddings which were shown to be effective for submodular cuts in \cite{ChekuriKRV15}.

We consider the task of classifying trajectories of boat activities as a proxy for assessing maritime threats. Previous approaches have considered entropy-based metrics for clustering boat activity into three broad categories: random walk, following, and chasing. Here, we comprehensively assess the accuracy of neural network-based approaches as alternatives to entropy-based clustering. We train four neural network models and compare them to shallow learning using synthetic data. We also investigate the accuracy of models as time steps increase and with and without rotated data. To improve test-time robustness, we normalize trajectories and perform rotation-based data augmentation. Our results show that deep networks can achieve a test-set accuracy of up to 100% on a full trajectory, with graceful degradation as the number of time steps decreases, outperforming entropy-based clustering.

Adverse Drug Reactions (ADRs) from psychiatric medications are the leading cause of hospitalizations among mental health patients. With healthcare systems and online communities facing limitations in resolving ADR-related issues, Large Language Models (LLMs) have the potential to fill this gap. Despite the increasing capabilities of LLMs, past research has not explored their capabilities in detecting ADRs related to psychiatric medications or in providing effective harm reduction strategies. To address this, we introduce the Psych-ADR benchmark and the Adverse Drug Reaction Response Assessment (ADRA) framework to systematically evaluate LLM performance in detecting ADR expressions and delivering expert-aligned mitigation strategies. Our analyses show that LLMs struggle with understanding the nuances of ADRs and differentiating between types of ADRs. While LLMs align with experts in terms of expressed emotions and tone of the text, their responses are more complex, harder to read, and only 70.86% aligned with expert strategies. Furthermore, they provide less actionable advice by a margin of 12.32% on average. Our work provides a comprehensive benchmark and evaluation framework for assessing LLMs in strategy-driven tasks within high-risk domains., Comment: 27 pages, 8 figures, 15 tables

Fluorescence imaging allows for non-invasively visualizing and measuring key physiological parameters like pH and dissolved oxygen. In our work, we created two ratiometric fluorescent microsensors designed for accurately tracking dissolved oxygen levels in 3D cell cultures. We developed a simple and cost-effective method to produce hybrid core-shell silica microparticles that are biocompatible and versatile. These sensors incorporate oxygen-sensitive probes (Ru(dpp) or PtOEP) and reference dyes (RBITC or A647 NHS-Ester). SEM analysis confirmed efficient loading and distribution of the sensing dye on the outer shell. Fluorimetric and CLSM tests demonstrated the sensors' reversibility and high sensitivity to oxygen, even when integrated into 3D scaffolds. Aging and bleaching experiments validated the stability of our hybrid core-shell silica microsensors for 3D monitoring. The Ru(dpp)-RBITC microparticles showed the most promising performance, especially in a pancreatic cancer model using alginate microgels. By employing computational segmentation, we generated 3D oxygen maps during live cell imaging, revealing oxygen gradients in the extracellular matrix and indicating a significant decrease in oxygen levels characteristic of solid tumors. Notably, after 12 hours, the oxygen concentration dropped to a hypoxic level of PO2 2.7 +/- 0.1%.

The intersection of LLMs (Large Language Models) and UAV (Unoccupied Aerial Vehicles) technology represents a promising field of research with the potential to enhance UAV capabilities significantly. This study explores the application of LLMs in UAV control, focusing on the opportunities for integrating advanced natural language processing into autonomous aerial systems. By enabling UAVs to interpret and respond to natural language commands, LLMs simplify the UAV control and usage, making them accessible to a broader user base and facilitating more intuitive human-machine interactions. The paper discusses several key areas where LLMs can impact UAV technology, including autonomous decision-making, dynamic mission planning, enhanced situational awareness, and improved safety protocols. Through a comprehensive review of current developments and potential future directions, this study aims to highlight how LLMs can transform UAV operations, making them more adaptable, responsive, and efficient in complex environments. A template development framework for integrating LLMs in UAV control is also described. Proof of Concept results that integrate existing LLM models and popular robotic simulation platforms are demonstrated. The findings suggest that while there are substantial technical and ethical challenges to address, integrating LLMs into UAV control holds promising implications for advancing autonomous aerial systems.

Extending Large Language Models (LLMs) to advanced applications requires reliable structured output generation. Existing methods which often rely on rigid JSON schemas, can lead to unreliable outputs, diminished reasoning capabilities, and increased computational overhead, limiting LLMs' adaptability for complex tasks. We introduce Meaning Typed Prompting (MTP), a technique for efficient structured output generation that integrates types, meanings, and abstractions, such as variables and classes, into the prompting process. By utilizing expressive type definitions, MTP enhances output clarity and reduces dependence on complex abstractions, simplifying development, and improving implementation efficiency. This enables LLMs to understand relationships and generate structured data more effectively. Empirical evaluations on multiple benchmarks demonstrate that MTP outperforms existing frameworks in accuracy, reliability, consistency, and token efficiency. We present Semantix, a framework that implements MTP, providing practical insights into its application.

Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM's context size. To address this limitation, we propose LongVU, a spatiotemporal adaptive compression mechanism thats reduces the number of video tokens while preserving visual details of long videos. Our idea is based on leveraging cross-modal query and inter-frame dependencies to adaptively reduce temporal and spatial redundancy in videos. Specifically, we leverage DINOv2 features to remove redundant frames that exhibit high similarity. Then we utilize text-guided cross-modal query for selective frame feature reduction. Further, we perform spatial token reduction across frames based on their temporal dependencies. Our adaptive compression strategy effectively processes a large number of frames with little visual information loss within given context length. Our LongVU consistently surpass existing methods across a variety of video understanding benchmarks, especially on hour-long video understanding tasks such as VideoMME and MLVU. Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance., Comment: Project page: https://vision-cair.github.io/LongVU

We consider Directed Steiner Forest (DSF), a fundamental problem in network design. The input to DSF is a directed edge-weighted graph $G = (V, E)$ and a collection of vertex pairs $\{(s_i, t_i)\}_{i \in [k]}$. The goal is to find a minimum cost subgraph $H$ of $G$ such that $H$ contains an $s_i$-$t_i$ path for each $i \in [k]$. DSF is NP-Hard and is known to be hard to approximate to a factor of $\Omega(2^{\log^{1 - \epsilon}(n)})$ for any fixed $\epsilon > 0$ [DK'99]. DSF admits approximation ratios of $O(k^{1/2 + \epsilon})$ [CEGS'11] and $O(n^{2/3 + \epsilon})$ [BBMRY'13]. In this work we show that in planar digraphs, an important and useful class of graphs in both theory and practice, DSF is much more tractable. We obtain an $O(\log^6 k)$-approximation algorithm via the junction tree technique. Our main technical contribution is to prove the existence of a low density junction tree in planar digraphs. To find an approximate junction tree we rely on recent results on rooted directed network design problems [FM'23, CJKZZ'24], in particular, on an LP-based algorithm for the Directed Steiner Tree problem [CJKZZ'24]. Our work and several other recent ones on algorithms for planar digraphs [FM'23, KS'21, CJKZZ'24] are built upon structural insights on planar graph reachability and shortest path separators [Thorup'04].

We present the results of a search for gravitational-wave transients associated with core-collapse supernova SN 2023ixf, which was observed in the galaxy Messier 101 via optical emission on 2023 May 19th, during the LIGO-Virgo-KAGRA 15th Engineering Run. We define a five-day on-source window during which an accompanying gravitational-wave signal may have occurred. No gravitational waves have been identified in data when at least two gravitational-wave observatories were operating, which covered $\sim 14\%$ of this five-day window. We report the search detection efficiency for various possible gravitational-wave emission models. Considering the distance to M101 (6.7 Mpc), we derive constraints on the gravitational-wave emission mechanism of core-collapse supernovae across a broad frequency spectrum, ranging from 50 Hz to 2 kHz where we assume the GW emission occurred when coincident data are available in the on-source window. Considering an ellipsoid model for a rotating proto-neutron star, our search is sensitive to gravitational-wave energy $1 \times 10^{-5} M_{\odot} c^2$ and luminosity $4 \times 10^{-5} M_{\odot} c^2/\text{s}$ for a source emitting at 50 Hz. These constraints are around an order of magnitude more stringent than those obtained so far with gravitational-wave data. The constraint on the ellipticity of the proto-neutron star that is formed is as low as $1.04$, at frequencies above $1200$ Hz, surpassing results from SN 2019ejj., Comment: Main paper: 6 pages, 4 figures and 1 table. Total with appendices: 20 pages, 4 figures, and 1 table

Social media is a great source of data for users reporting information and regarding their health and how various things have had an effect on them. This paper presents various approaches using Transformers and Large Language Models and their ensembles, their performance along with advantages and drawbacks for various tasks of SMM4H'24 - Classifying texts on impact of nature and outdoor spaces on the author's mental health (Task 3), Binary classification of tweets reporting their children's health disorders like Asthma, Autism, ADHD and Speech disorder (task 5), Binary classification of users self-reporting their age (task 6)., Comment: short paper , acl 2024

This paper significantly advances the application of Quantum Key Distribution (QKD) in Free- Space Optics (FSO) satellite-based quantum communication. We propose an innovative satellite quantum channel model and derive the secret quantum key distribution rate achievable through this channel. Unlike existing models that approximate the noise in quantum channels as merely Gaussian distributed, our model incorporates a hybrid noise analysis, accounting for both quantum Poissonian noise and classical Additive-White-Gaussian Noise (AWGN). This hybrid approach acknowledges the dual vulnerability of continuous variables (CV) Gaussian quantum channels to both quantum and classical noise, thereby offering a more realistic assessment of the quantum Secret Key Rate (SKR). This paper delves into the variation of SKR with the Signal-to-Noise Ratio (SNR) under various influencing parameters. We identify and analyze critical factors such as reconciliation efficiency, transmission coefficient, transmission efficiency, the quantum Poissonian noise parameter, and the satellite altitude. These parameters are pivotal in determining the SKR in FSO satellite quantum channels, highlighting the challenges of satellitebased quantum communication. Our work provides a comprehensive framework for understanding and optimizing SKR in satellite-based QKD systems, paving the way for more efficient and secure quantum communication networks.

Gallbladder cancer (GBC) is the most frequent cause of disease among biliary tract neoplasms. Identifying the molecular mechanisms and biomarkers linked to GBC progression has been a significant challenge in scientific research. Few recent studies have explored the roles of biomarkers in GBC. Our study aimed to identify biomarkers in GBC using machine learning (ML) and bioinformatics techniques. We compared GBC tumor samples with normal samples to identify differentially expressed genes (DEGs) from two microarray datasets (GSE100363, GSE139682) obtained from the NCBI GEO database. A total of 146 DEGs were found, with 39 up-regulated and 107 down-regulated genes. Functional enrichment analysis of these DEGs was performed using Gene Ontology (GO) terms and REACTOME pathways through DAVID. The protein-protein interaction network was constructed using the STRING database. To identify hub genes, we applied three ranking algorithms: Degree, MNC, and Closeness Centrality. The intersection of hub genes from these algorithms yielded 11 hub genes. Simultaneously, two feature selection methods (Pearson correlation and recursive feature elimination) were used to identify significant gene subsets. We then developed ML models using SVM and RF on the GSE100363 dataset, with validation on GSE139682, to determine the gene subset that best distinguishes GBC samples. The hub genes outperformed the other gene subsets. Finally, NTRK2, COL14A1, SCN4B, ATP1A2, SLC17A7, SLIT3, COL7A1, CLDN4, CLEC3B, ADCYAP1R1, and MFAP4 were identified as crucial genes, with SLIT3, COL7A1, and CLDN4 being strongly linked to GBC development and prediction.