Search

Organisms often swim through fluids that are spatially inhomogeneous. If the fluids are polymeric, gradients in polymer concentration may lead to gradients in both fluid viscosity and elasticity. In this letter, we present theoretical results for the dynamics of active particles, biological or otherwise, swimming through spatially inhomogeneous viscoelastic fluids. We model the active particles using the squirmer model, and show that spatial variations in fluid relaxation time lead to a novel mechanism for reorientation and taxis in viscoelastic fluids, which we refer to as a form of durotaxis in fluids., Comment: 5 pages, 1 figure

Text generation is the automated process of producing written or spoken language using computational methods. It involves generating coherent and contextually relevant text based on predefined rules or learned patterns. However, challenges in text generation arise from maintaining coherence, ensuring diversity and creativity, and avoiding biases or inappropriate content. This research paper developed a novel approach to improve text generation in the context of joint Natural Language Generation (NLG) and Natural Language Understanding (NLU) learning. The data is prepared by gathering and preprocessing annotated datasets, including cleaning, tokenization, stemming, and stop-word removal. Feature extraction techniques such as POS tagging, Bag of words, and Term Frequency-Inverse Document Frequency (TF-IDF) are applied. Transformer-based encoders and decoders, capturing long range dependencies and improving source-target sequence modelling. Pre-trained language models like Optimized BERT are incorporated, along with a Hybrid Redfox Artificial Hummingbird Algorithm (HRAHA). Reinforcement learning with policy gradient techniques, semi-supervised training, improved attention mechanisms, and differentiable approximations like straight-through Gumbel SoftMax estimator are employed to fine-tune the models and handle complex linguistic tasks effectively. The proposed model is implemented using Python.

Despite the significance of coronal mass ejections (CMEs) in space weather, a comprehensive understanding of their interior morphology remains a scientific challenge, particularly with the advent of many state-of-the-art solar missions such as Parker Solar Probe (Parker) and Solar Orbiter (SO). In this study, we present an analysis of a complex CME as observed by the Wide-Field Imager for Solar PRobe (WISPR) heliospheric imager during Parker's seventh solar encounter. The CME morphology does not fully conform with the general three-part density structure, exhibiting a front and core not significantly bright, with a highly structured overall configuration. In particular, its morphology reveals non-concentric nested rings, which we argue are a signature of the embedded helical magnetic flux rope (MFR) of the CME. For that, we analyze the morphological and kinematical properties of the nested density structures and demonstrate that they outline the projection of the three-dimensional structure of the flux rope as it crosses the lines of sight of the WISPR imager, thereby revealing the magnetic field geometry. Comparison of observations from various viewpoints suggests that the CME substructures can be discerned owing to the ideal viewing perspective, close proximity, and spatial resolution of the observing instrument., Comment: 21 pages, 11 figures

Globally, infertility rates are increasing, with 2.5\% of all births being assisted by in vitro fertilisation (IVF) in 2022. Male infertility is the cause for approximately half of these cases. The quality of sperm DNA has substantial impact on the success of IVF. The assessment of sperm DNA is traditionally done through chemical assays which render sperm cells ineligible for IVF. Many compounding factors lead to the population crisis, with fertility rates dropping globally in recent history. As such assisted reproductive technologies (ART) have been the focus of recent research efforts. Simultaneously, artificial intelligence has grown ubiquitous and is permeating more aspects of modern life. With the advent of state-of-the-art machine learning and its exceptional performance in many sectors, this work builds on these successes and proposes a novel framework for the prediction of sperm cell DNA fragmentation from images of unstained sperm. Rendering a predictive model which preserves sperm integrity and allows for optimal selection of sperm for IVF.

The ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions served as a rigorous platform to evaluate and benchmark state-of-the-art semantic segmentation models under challenging conditions for autonomous driving. Over several months, participants were provided with the IDD-AW dataset, consisting of 5000 high-quality RGB-NIR image pairs, each annotated at the pixel level and captured under adverse weather conditions such as rain, fog, low light, and snow. A key aspect of the competition was the use and improvement of the Safe mean Intersection over Union (Safe mIoU) metric, designed to penalize unsafe incorrect predictions that could be overlooked by traditional mIoU. This innovative metric emphasized the importance of safety in developing autonomous driving systems. The competition showed significant advancements in the field, with participants demonstrating models that excelled in semantic segmentation and prioritized safety and robustness in unstructured and adverse conditions. The results of the competition set new benchmarks in the domain, highlighting the critical role of safety in deploying autonomous vehicles in real-world scenarios. The contributions from this competition are expected to drive further innovation in autonomous driving technology, addressing the critical challenges of operating in diverse and unpredictable environments., Comment: 15 pages, 7 figures, ICPR Competition Paper

In recent times a number of platforms are using badge-based achievements or leaderboards to increase user involvement and participation. Due to recent advancements, there is a question of up to what extent virtual achievement systems have on users using particular platforms. Here in this paper, we discuss measuring the impact of the leaderboard-based achievement system by integrating it into an online learning android application UPSC Pre that has thousands of questions and answers categorized topic wise related to UPSC exams, one of the toughest exams to crack in the world. We are conducting the experiment on 10 randomly chosen students who are using the app in a controlled setting and the data measurement is done using the Firebase Analytics tool by Google. We observed that the students using the leaderboard have increased participation without any reductions in their quality and the time of using the platform has increased compared to previous engagements. Students who participated in the experiment felt the leaderboard was competitive and enjoyed gaining positions on the leaderboard and wanted it in the User interface for other platforms as well. The research has an impact in designing the learning applications to cater and improve the user experience in the future. The results are not limited to educational purposes but can be expanded to other fields such as self development applications, other research projects, Gaming industry and many more., Comment: 4 Pages, 4 Figures

Quantum computing (QC) provides a promising avenue toward enabling quantum chemistry calculations, which are classically impossible due to a computational complexity that increases exponentially with system size. As fully fault-tolerant algorithms and hardware, for which an exponential speedup is predicted, are currently out of reach, recent research efforts are dedicated to developing and scaling algorithms for Noisy Intermediate-Scale Quantum (NISQ) devices to showcase the practical utility of such machines. To demonstrate the utility of NISQ devices in the field of chemistry, we apply our recently developed FAST-VQE algorithm and a novel quantum gate reduction strategy based on propositional satisfiability together with standard optimization tools for the simulation of the rate-determining proton transfer step for CO2 hydration catalysed by carbonic anhydrase resulting in the first application of a quantum computing device for the simulation of an enzymatic reaction. To this end, we have combined classical force field simulations with quantum mechanical methods on classical and quantum computers in a hybrid calculation approach. The presented technique significantly enhances the accuracy and capabilities of QC-based molecular modeling and finally pushes it into compelling and realistic applications. The framework is general and can be applied beyond the case of computational enzymology.

CNOT optimization plays a significant role in noise reduction for Quantum Circuits. Several heuristic and exact approaches exist for CNOT optimization. In this paper, we investigate more complicated variations of optimal synthesis by allowing qubit permutations and handling layout restrictions. We encode such problems into Planning, SAT, and QBF. We provide optimization for both CNOT gate count and circuit depth. For experimental evaluation, we consider standard T-gate optimized benchmarks and optimize CNOT sub-circuits. We show that allowing qubit permutations can further reduce up to 56% in CNOT count and 46% in circuit depth. In the case of optimally mapped circuits under layout restrictions, we observe a reduction up to 17% CNOT count and 19% CNOT depth., Comment: 9 pages, 12 tables

Schizophrenia (SZ) is a severe brain disorder marked by diverse cognitive impairments, abnormalities in brain structure, function, and genetic factors. Its complex symptoms and overlap with other psychiatric conditions challenge traditional diagnostic methods, necessitating advanced systems to improve precision. Existing research studies have mostly focused on imaging data, such as structural and functional MRI, for SZ diagnosis. There has been less focus on the integration of genomic features despite their potential in identifying heritable SZ traits. In this study, we introduce a Multi-modal Imaging Genomics Transformer (MIGTrans), that attentively integrates genomics with structural and functional imaging data to capture SZ-related neuroanatomical and connectome abnormalities. MIGTrans demonstrated improved SZ classification performance with an accuracy of 86.05% (+/- 0.02), offering clear interpretations and identifying significant genomic locations and brain morphological/connectivity patterns associated with SZ., Comment: Accepted for presentation at the AI for Imaging Genomic Learning (AIIG) Workshop, MICCAI 2024

Schizophrenia (SZ) is a complex mental disorder that necessitates accurate and timely diagnosis for effective treatment. Traditional methods for SZ classification often struggle to capture transient EEG features and face high computational complexity. This study proposes a convolutional autoencoder (CAE) to address these challenges by reducing dimensionality and computational complexity. Additionally, we introduce a novel approach utilizing spectral scalograms (SS) combined with EfficientNet (ENB) architectures. The SS, obtained through continuous wavelet transform, reveals temporal and spectral information of EEG signals, aiding in the identification of transient features. ENB models, through transfer learning (TL), extract discriminative features and improve SZ classification accuracy. Experimental evaluation on a comprehensive dataset demonstrates the efficacy of our approach, achieving a five-fold mean cross-validation accuracy of 98.5\% using CAE with a soft voting classifier and 99\% employing SS with the ENB7 model. These results suggest the potential of our methods to enhance SZ diagnosis, surpassing traditional deep learning (DL) and TL techniques. By leveraging CAE and ENBs, this research offers a robust framework for objective SZ classification, promoting early intervention and improved patient outcomes.

We present the identification and physical analysis of a possible magnetic island feature seen in white-light images observed by the Wide-field Imager for Solar Probe (WISPR) on board the Parker Solar Probe (Parker). The island is imaged by WISPR during Parker's second solar encounter on 2019 April 06, when Parker was ~38 solar radii from the Sun center. We report that the average velocity and acceleration of the feature are approximately 334 km s and -0.64 m s-2. The kinematics of the island feature, coupled with its direction of propagation, indicate that the island is likely entrained in the slow solar wind. The island is elliptical in shape with a density deficit in its center, suggesting the presence of a magnetic guide field. We argue that this feature is consistent with the formation of this island via reconnection in the current sheet of the streamer. The feature's aspect ratio (calculated as the ratio of its minor to major axis) evolves from an elliptical to a more circular shape that approximately doubles during its propagation through WISPR's field of view. The island is not distinct in other white-light observations from the Solar and Heliospheric Observatory (SOHO) and the Solar Terrestrial Relations Observatory (STEREO) coronagraphs, suggesting that this is a comparatively faint heliospheric feature and that viewing perspective and WISPR's enhanced sensitivity are key to observing the magnetic island.

We find the mixing induced by a small swimming organism in a density stratified fluid. We model the swimmer as a spherical squirmer and quantify mixing through a mixing efficiency that is the ratio of rate of change of potential energy of fluid to the total work done by the swimmer. Assessing mixing in the near field and far field of the swimmer separately, we find that the near-field mixing aligns with past work, but the overall mixing is much larger than that caused by a point-sized swimmer (like force-dipole), although still small in weak stratification. Equivalent results are also obtained for a homogeneous dilute suspension of non-interacting swimmers. Our study highlights the impact of swimmer size on mixing, revealing that small-sized swimmers cannot induce substantial mixing. However, we propose few (unexplored) pathways through which small swimmers could induce significant mixing, ultimately contributing towards oceanic mixing., Comment: 11 pages

Automated retinal image medical description generation is crucial for streamlining medical diagnosis and treatment planning. Existing challenges include the reliance on learned retinal image representations, difficulties in handling multiple imaging modalities, and the lack of clinical context in visual representations. Addressing these issues, we propose the Multi-Modal Medical Transformer (M3T), a novel deep learning architecture that integrates visual representations with diagnostic keywords. Unlike previous studies focusing on specific aspects, our approach efficiently learns contextual information and semantics from both modalities, enabling the generation of precise and coherent medical descriptions for retinal images. Experimental studies on the DeepEyeNet dataset validate the success of M3T in meeting ophthalmologists' standards, demonstrating a substantial 13.5% improvement in BLEU@4 over the best-performing baseline model., Comment: This paper has been accepted for presentation at the IEEE International Conference on Image Processing (ICIP 2024)

Effectively representing medical images, especially retinal images, presents a considerable challenge due to variations in appearance, size, and contextual information of pathological signs called lesions. Precise discrimination of these lesions is crucial for diagnosing vision-threatening issues such as diabetic retinopathy. While visual attention-based neural networks have been introduced to learn spatial context and channel correlations from retinal images, they often fall short in capturing localized lesion context. Addressing this limitation, we propose a novel attention mechanism called Guided Context Gating, an unique approach that integrates Context Formulation, Channel Correlation, and Guided Gating to learn global context, spatial correlations, and localized lesion context. Our qualitative evaluation against existing attention mechanisms emphasize the superiority of Guided Context Gating in terms of explainability. Notably, experiments on the Zenodo-DR-7 dataset reveal a substantial 2.63% accuracy boost over advanced attention mechanisms & an impressive 6.53% improvement over the state-of-the-art Vision Transformer for assessing the severity grade of retinopathy, even with imbalanced and limited training samples for each class., Comment: This paper has been accepted for presentation at the IEEE International Conference on Image Processing (ICIP 2024)

Schizophrenia is a debilitating, chronic mental disorder that significantly impacts an individual's cognitive abilities, behavior, and social interactions. It is characterized by subtle morphological changes in the brain, particularly in the gray matter. These changes are often imperceptible through manual observation, demanding an automated approach to diagnosis. This study introduces a deep learning methodology for the classification of individuals with Schizophrenia. We achieve this by implementing a diversified attention mechanism known as Spatial Sequence Attention (SSA) which is designed to extract and emphasize significant feature representations from structural MRI (sMRI). Initially, we employ the transfer learning paradigm by leveraging pre-trained DenseNet to extract initial feature maps from the final convolutional block which contains morphological alterations associated with Schizophrenia. These features are further processed by the proposed SSA to capture and emphasize intricate spatial interactions and relationships across volumes within the brain. Our experimental studies conducted on a clinical dataset have revealed that the proposed attention mechanism outperforms the existing Squeeze & Excitation Network for Schizophrenia classification., Comment: This paper has been accepted for the 21st IEEE International Symposium on Biomedical Imaging (ISBI 2024)

Despite advancements in medical care, hip fractures impose a significant burden on individuals and healthcare systems. This paper focuses on the prediction of hip fracture risk in older and middle-aged adults, where falls and compromised bone quality are predominant factors. We propose a novel staged model that combines advanced imaging and clinical data to improve predictive performance. By using CNNs to extract features from hip DXA images, along with clinical variables, shape measurements, and texture features, our method provides a comprehensive framework for assessing fracture risk. A staged machine learning-based model was developed using two ensemble models: Ensemble 1 (clinical variables only) and Ensemble 2 (clinical variables and DXA imaging features). This staged approach used uncertainty quantification from Ensemble 1 to decide if DXA features are necessary for further prediction. Ensemble 2 exhibited the highest performance, achieving an AUC of 0.9541, an accuracy of 0.9195, a sensitivity of 0.8078, and a specificity of 0.9427. The staged model also performed well, with an AUC of 0.8486, an accuracy of 0.8611, a sensitivity of 0.5578, and a specificity of 0.9249, outperforming Ensemble 1, which had an AUC of 0.5549, an accuracy of 0.7239, a sensitivity of 0.1956, and a specificity of 0.8343. Furthermore, the staged model suggested that 54.49% of patients did not require DXA scanning. It effectively balanced accuracy and specificity, offering a robust solution when DXA data acquisition is not always feasible. Statistical tests confirmed significant differences between the models, highlighting the advantages of the advanced modeling strategies. Our staged approach could identify individuals at risk with a high accuracy but reduce the unnecessary DXA scanning. It has great promise to guide interventions to prevent hip fractures with reduced cost and radiation., Comment: 29 pages, 5 figures, 6 tables

Relativistic discrete ejecta launched by black hole X-ray binaries (BH XRBs) can be observed to propagate up to parsec-scales from the central object. Observing the final deceleration phase of these jets is crucial to estimate their physical parameters and to reconstruct their full trajectory, with implications for the jet powering mechanism, composition and formation. In this paper we present the results of the modelling of the motion of the ejecta from three BH XRBs: MAXI J1820+070, MAXI J1535$-$571 and XTE J1752$-$223, for which high-resolution radio and X-ray observations of jets propagating up to $\sim$15 arcsec ($\sim$0.6 pc at 3 kpc) from the core have been published in the recent years. For each jet, we modeled its entire motion with a dynamical blast-wave model, inferring robust values for the jet Lorentz factor, inclination angle and ejection time. Under several assumptions associated to the ejection duration, the jet opening angle and the available accretion power, we are able to derive stringent constraints on the maximum jet kinetic energy for each source (between $10^{43}$ and $10^{44}$ erg, including also H1743$-$322), as well as placing interesting upper limits on the density of the ISM through which the jets are propagating (from $n_{\rm ISM} \lesssim 0.4$ cm$^{-3}$ down to $n_{\rm ISM} \lesssim 10^{-4}$ cm$^{-3}$). Overall, our results highlight the potential of applying models derived from gamma-ray bursts to the physics of jets from BH XRBs and support the emerging picture of these sources as preferentially embedded in low-density environments., Comment: 22 pages, 9 figures. Accepted for publication in MNRAS

In this paper, we explore the potential application of Large Language Models (LLMs) that will automatically model constraints and generate code for dynamic scheduling problems given an existing static model. Static scheduling problems are modelled and coded by optimization experts. These models may be easily obsoleted as the underlying constraints may need to be fine-tuned in order to reflect changes in the scheduling rules. Furthermore, it may be necessary to turn a static model into a dynamic one in order to cope with disturbances in the environment. In this paper, we propose a Retrieval-Augmented Generation (RAG) based LLM model to automate the process of implementing constraints for Dynamic Scheduling (RAGDyS), without seeking help from an optimization modeling expert. Our framework aims to minimize technical complexities related to mathematical modelling and computational workload for end-users, thereby allowing end-users to quickly obtain a new schedule close to the original schedule with changes reflected by natural language constraint descriptions., Comment: 7 pages (excluding appendix), 10 figures, 3 tables

Out-of-system (OoS) interference is a potential limitation for distributed networks that operate in unlicensed spectrum or in a spectrum sharing scenario. The OoS interference differs from the in-system interference in that OoS signals and their associated channels (or even their statistics) are completely unknown. In this paper, we propose a novel distributed algorithm that can mitigate OoS interference in the uplink and suppress the signal transmission in the OoS direction in the downlink. To estimate the OoS interference, each access point (AP), upon receiving an estimate of OoS interference from a previous AP, computes a better estimate of OoS interference by rotate-and-average using Procrustes method and forwards the estimates to the next AP. This process continues until the central processing unit (CPU) receives the final estimate. Our method has comparable performance to that of a fully centralized interference rejection combining algorithm and has much lower fronthaul load requirements., Comment: 5 pages, 2 figures, to be published in IEEE Wireless Communications Letters

In this note, we study the effect of viscosity gradients on the energy dissipated by the motion of microswimmers and the associated efficiency of that motion. Using spheroidal squirmer model swimmers in weak linearly varying viscosity fields, we find that efficiency depends on whether they generate propulsion from the back (pushers) or the front (pullers). Pushers are faster and more efficient when moving down gradients but slower and less efficient moving up viscosity gradients, and the opposite is true for pullers. However, both pushers and pullers display negative viscotaxis, therefore pushers dynamically tend to the most efficient orientation while pullers the least. We also evaluate the effect of shape on power expenditure and efficiency when swimming in viscosity gradients and find that in general the change in both due to gradients monotonically decreases with increasing slenderness. This work shows how shape and gait play an important role in determining dynamics and efficiency in inhomogeneous environments, and demonstrating that both efficiency minimizing and maximizing stable dynamical states are possible., Comment: 12 pages, 1 figure

The growing prominence of large language models (LLMs) necessitates the exploration of their capabilities beyond English. This research investigates the Telugu language proficiency of ChatGPT and Gemini, two leading LLMs. Through a designed set of 20 questions encompassing greetings, grammar, vocabulary, common phrases, task completion, and situational reasoning, the study delves into their strengths and weaknesses in handling Telugu. The analysis aims to identify the LLM that demonstrates a deeper understanding of Telugu grammatical structures, possesses a broader vocabulary, and exhibits superior performance in tasks like writing and reasoning. By comparing their ability to comprehend and use everyday Telugu expressions, the research sheds light on their suitability for real-world language interaction. Furthermore, the evaluation of adaptability and reasoning capabilities provides insights into how each LLM leverages Telugu to respond to dynamic situations. This comparative analysis contributes to the ongoing discussion on multilingual capabilities in AI and paves the way for future research in developing LLMs that can seamlessly integrate with Telugu-speaking communities.

Accurate assessment of fuel conditions is a prerequisite for fire ignition and behavior prediction, and risk management. The method proposed herein leverages diverse data sources including Landsat-8 optical imagery, Sentinel-1 (C-band) Synthetic Aperture Radar (SAR) imagery, PALSAR (L-band) SAR imagery, and terrain features to capture comprehensive information about fuel types and distributions. An ensemble model was trained to predict landscape-scale fuels such as the 'Scott and Burgan 40' using the as-received Forest Inventory and Analysis (FIA) field survey plot data obtained from the USDA Forest Service. However, this basic approach yielded relatively poor results due to the inadequate amount of training data. Pseudo-labeled and fully synthetic datasets were developed using generative AI approaches to address the limitations of ground truth data availability. These synthetic datasets were used for augmenting the FIA data from California to enhance the robustness and coverage of model training. The use of an ensemble of methods including deep learning neural networks, decision trees, and gradient boosting offered a fuel mapping accuracy of nearly 80\%. Through extensive experimentation and evaluation, the effectiveness of the proposed approach was validated for regions of the 2021 Dixie and Caldor fires. Comparative analyses against high-resolution data from the National Agriculture Imagery Program (NAIP) and timber harvest maps affirmed the robustness and reliability of the proposed approach, which is capable of near-real-time fuel mapping., Comment: 40 pages

Layout synthesis is mapping a quantum circuit to a quantum processor. SWAP gate insertions are needed for scheduling 2-qubit gates only on connected physical qubits. With the ever-increasing number of qubits in NISQ processors, scalable layout synthesis is of utmost importance. With large optimality gaps observed in heuristic approaches, scalable exact methods are needed. While recent exact and near-optimal approaches scale to moderate circuits, large deep circuits are still out of scope. In this work, we propose a SAT encoding based on parallel plans that apply 1 SWAP and a group of CNOTs at each time step. Using domain-specific information, we maintain optimality in parallel plans while scaling to large and deep circuits. From our results, we show the scalability of our approach which significantly outperforms leading exact and near-optimal approaches (up to 100x). For the first time, we can optimally map several 8, 14, and 16 qubit circuits onto 54, 80, and 127 qubit platforms with up to 17 SWAPs. While adding optimal SWAPs, we also report near-optimal depth in our mapped circuits., Comment: 7 Figures, 4 Tables, 1 Listing

The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emergence of generative AI, specifically large language models (LLMs), provides novel pathways for understanding such complex scientific codes. This paper presents S3LLM, an LLM-based framework designed to enable the examination of source code, code metadata, and summarized information in conjunction with textual technical reports in an interactive, conversational manner through a user-friendly interface. S3LLM leverages open-source LLaMA-2 models to enhance code analysis through the automatic transformation of natural language queries into domain-specific language (DSL) queries. Specifically, it translates these queries into Feature Query Language (FQL), enabling efficient scanning and parsing of entire code repositories. In addition, S3LLM is equipped to handle diverse metadata types, including DOT, SQL, and customized formats. Furthermore, S3LLM incorporates retrieval augmented generation (RAG) and LangChain technologies to directly query extensive documents. S3LLM demonstrates the potential of using locally deployed open-source LLMs for the rapid understanding of large-scale scientific computing software, eliminating the need for extensive coding expertise, and thereby making the process more efficient and effective. S3LLM is available at https://github.com/ResponsibleAILab/s3llm.

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

This study aims to investigate the comprehensive characterization of information content in multimedia (videos), particularly on YouTube. The research presents a multi-method framework for characterizing multimedia content by clustering signals from various modalities, such as audio, video, and text. With a focus on South China Sea videos as a case study, this approach aims to enhance our understanding of online content, especially on YouTube. The dataset includes 160 videos, and our findings offer insights into content themes and patterns within different modalities of a video based on clusters. Text modality analysis revealed topical themes related to geopolitical countries, strategies, and global security, while video and audio modality analysis identified distinct patterns of signals related to diverse sets of videos, including news analysis/reporting, educational content, and interviews. Furthermore, our findings uncover instances of content repurposing within video clusters, which were identified using the barcode technique and audio similarity assessments. These findings indicate potential content amplification techniques. In conclusion, this study uniquely enhances our current understanding of multimedia content information based on modality clustering techniques., Comment: 14 pages, In the 4th International Conference on SMART MULTIMEDIA, 2024

The launches of Parker Solar Probe (Parker) and Solar Orbiter (SolO) are enabling a new era of solar wind studies that track the solar wind from its origin at the photosphere, through the corona, to multiple vantage points in the inner heliosphere. A key ingredient for these models is the input photospheric magnetic field map that provides the boundary condition for the coronal portion of many heliospheric models. In this paper, we perform steady-state, data-driven magnetohydrodynamic (MHD) simulations of the solar wind during Carrington rotation 2258 with the GAMERA model. We use the ADAPT and AFT flux transport models and quantitatively assess how well each model matches in-situ measurements from Parker, SolO, and Earth. We find that both models reproduce the magnetic field components at Parker quantitatively well. At SolO and Earth, the magnetic field is reproduced relatively well, though not as well as at Parker, and the density is reproduced extremely poorly. The velocity is overpredicted at Parker, but not at SolO or Earth, hinting that the Wang-Sheeley-Arge (WSA) relation, fine-tuned for Earth, misses the deceleration of the solar wind near the Sun. We conclude that AFT performs quantitatively similarly to ADAPT in all cases and that both models are comparable to a purely WSA heliospheric treatment with no MHD component. Finally, we trace field lines from SolO back to an active region outflow that was observed by Hinode/EIS, and which shows evidence of elevated charge state ratios.

Plane-wave electrons undergo momentum transfer as they scatter off a target in overlapping spherical waves. The transferred momentum leads to target structural information to be encoded in angle and energy differential scattering. For symmetric, periodic or structured targets this can engender diffraction in the electron intensity both in real (angular) and in momentum space. With the example of elastic scattering from C60 we show this simultaneous manifestation of diffraction signatures. The simulated angle-momentum diffractograms can be imaged in experiments with a two-dimensional detector and an energy-tunable electron gun. The result may inspire invention of technology to extend scopes of electron diffraction from molecules and nanostructures, open a direction of electron crystallography using the momentum-differential diffraction, and motivate an approach to control the time delay between the pump laser-pulse and the probe electron-pulse by tuning the electron impact-speed in ultrafast electron diffraction experiments., Comment: 6 pages, 5 figures

The origin of X-ray emission from the resolved kiloparsec-scale jets and hotspots of many active galactic nuclei (AGN) remains uncertain, particularly where the X-ray emission is separate from the radio-optical synchrotron component. Possible explanations include synchrotron emission from a second electron population and external Compton or synchrotron self-Compton processes -- alternatives which imply very different physical conditions within the jet. Until recently, X-ray studies of resolved jets and hotspots have been restricted to below ~10 keV, often showing a hard spectral index indicating a spectral peak beyond this energy range. Here we present NuSTAR observations of the nearby powerful radio galaxy Pictor A, in which we clearly detect the western hotspot at approximately 4' from the host galaxy, the most significant detection of hotspot emission above 10 keV to date. The NuSTAR spectrum is best fit by a single powerlaw of index $\Gamma$ = 2.03 $\pm$ 0.04; an exponential cut-off gives a 1$\sigma$ lower limit on the cutoff energy of 40.7 keV. We confirm previous findings of variations in the soft X-ray flux detected by Chandra over the 2000 to 2015 period, at a significance of 6.5$\sigma$. This rises to >8$\sigma$ in the common 3-8 keV band using the combined 22-year span of Chandra and NuSTAR observations. The variability of the western Pictor A hotspot strongly confirms the previously argued synchrotron nature of the X-ray emission for the hotspot, while the lower bound to the spectral cutoff energy implies electron energies in the hotspot reach up to at least a few TeV., Comment: Accepted for publication in ApJ, 21 May 2024

The rise of micro/nanooptics and lab-on-chip devices demands the fabrication of three-dimensional structures with decent resolution. Here, we demonstrate the combination of grayscale electron beam lithography and direct forming methodology to fabricate antimony sulfide structures with free form for the first time. The refractive index of the electron beam patterned structure was calculated based on an optimization algorithm that is combined with genetic algorithm and transfer matrix method. By adopting electron irradiation with variable doses, 4-level Fresnel Zone Plates and metalens were produced and characterized. This method can be used for the fabrication of three-dimensional diffractive optical elements and metasurfaces in a single step manner., Comment: 17 pages, 4 figures, 1 table, 1 scheme. The Supplement Information will be given in a second Arxiv submission or the published journal

Time delay in a projectile-target scattering is a fundamental tool in understanding their interactions by probing the temporal domain. The present study focuses on computing and analyzing the Eisenbud-Wigner-Smith (EWS) time delay in low energy elastic e C60 scattering. The investigation is carried out in the framework of a non-relativistic partial wave analysis (PWA) technique. The projectile-target interaction is described in (1) Density Functional Theory (DFT) and (2) Annular Square Well (ASW) static model, and their final results are compared in details. The impact of polarization on resonant and non-resonant time delay is also investigated.

With a motive of ubiquitous connectivity over the globe with enhanced spectral efficiency, intelligent reflecting surfaces (IRS) integrated satellite-terrestrial communications is a topic of research interest in an infrastructure-deficient remote terrains. In line with this vision, this paper entails the performance analysis of satellite-terrestrial networks leveraging both aerial and terrestrial IRS nodes, with the support of high altitude platforms over diverse fading channels including shadowed Rician, Rician, and Nakagami-$m$ fading channels. The merits of IRS in enhancing spectral efficiency is analyzed through closed-form expressions of outage probability and ergodic rate. Further, the average symbol error rate analysis for the higher-order quadrature amplitude modulation (QAM) schemes such as hexagonal QAM, rectangular QAM, cross QAM, and square QAM is performed. Practical constraints like antenna gains, path loss, and link fading are considered to characterize the satellite terrestrial links. Finally, a comparison between the high-altitude platforms based IRS node and terrestrial IRS nodes is performed and various insights are drawn under various fading scenarios and path loss conditions. This paper contribute towards understanding and potential implementation of IRS-integrated satellite-terrestrial networks for efficient and reliable communication.

Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch remains a challenge in this area, where the domain of the pre-training data might differ from that of the downstream labeled data used for fine-tuning. In multilingual tasks such as SLID, the pre-trained speech model may not support all the languages in the downstream task. To address this challenge, we propose self-supervised adaptive pre-training (SAPT) to adapt the pre-trained model to the target domain and languages of the downstream task. We apply SAPT to the XLSR-128 model and investigate the effectiveness of this approach for the SLID task. First, we demonstrate that SAPT improves XLSR performance on the FLEURS benchmark with substantial gains up to 40.1% for under-represented languages. Second, we apply SAPT on four different datasets in a few-shot learning setting, showing that our approach improves the sample efficiency of XLSR during fine-tuning. Our experiments provide strong empirical evidence that continual adaptation via self-supervision improves downstream performance for multilingual speech models., Comment: Submitted to ICASSP 2024