Search

Advancements in generative modeling are pushing the state-of-the-art in synthetic medical image generation. These synthetic images can serve as an effective data augmentation method to aid the development of more accurate machine learning models for medical image analysis. While the fidelity of these synthetic images has progressively increased, the diversity of these images is an understudied phenomenon. In this work, we propose the SDICE index, which is based on the characterization of similarity distributions induced by a contrastive encoder. Given a synthetic dataset and a reference dataset of real images, the SDICE index measures the distance between the similarity score distributions of original and synthetic images, where the similarity scores are estimated using a pre-trained contrastive encoder. This distance is then normalized using an exponential function to provide a consistent metric that can be easily compared across domains. Experiments conducted on the MIMIC-chest X-ray and ImageNet datasets demonstrate the effectiveness of SDICE index in assessing synthetic medical dataset diversity., Comment: Accepted at BMVC 2024 - PFATCV

The spectroscopic redshift measurement of BL Lac, a class of blazar, is challenging because its spectrum has no or weak emission lines ($\leqslant5\AA$). We estimate the redshift by the photometric dropout technique for a sample of 64 blazars (59 BL Lacs and five blazar candidates of uncertainty type). Two telescopes are utilized to observe the sample: the {\it Swift} space telescope observes sources in $uvw2,\ uvm2,\ uvw1,\ u,\ b,\ v$ filters, while the ground-based telescopes SARA-CT/RM observed sources in $g',\ r,' \ i',\ z'$ filters. The photometric data are obtained using the {\it photozpy} package. We fit the photometric data by the LePhare package and report four new high-$z$ ($z>1.3$) BL Lacs at $2.03^{+0.07}_{-0.05}$, $1.84^{+0.10}_{-0.03}$, $2.04^{+0.16}_{-0.14}$, $2.93^{+0.01}_{-0.04}$ as well as upper limits for 50 sources. The work increased the number of high-$z$ BL Lacs found by this method up to 23. The high-$z$ sources are discussed in the context of the cosmic gamma-ray horizon, blazar sequence, Fermi blazar divide, and masquerading BL Lacs., Comment: Updated the CGRH plot

Hot carrier effect, a phenomenon where charge carriers generated by photon absorption remain energetic by not losing much energy, has been one of the leading strategies in increasing solar cell efficiency. Nanostructuring offers an effective approach to enhance hot carrier effect via the spatial confinement, as occurring in a nanowire structure. The recent experimental study by Esmaielpour et al. [ACS Applied Nano Materials 7, 2817 (2024)] reveals a fascinating non-monotonic dependence of the hot carrier effect in nanowire array on the diameter of the nanowire, contrary to what might be expected from quantum confinement alone. We show that this non-monotonic behavior can be explained by a simple model for electron energy loss that involves two principal mechanisms. First, electron-phonon scattering, that increases with nanowire diameter, leading to hot carrier effect that decreases with increasing diameter. Second, electron capture by a defect level within band gap, that is, a midgap state, that decreases with nanowire diameter, leading to hot carrier effect that increases with increasing diameter. The two mechanisms balance at a certain diameter corresponding to optimal hot carrier effect. Our result offers a guideline to optimize hot carrier effect in nanowire solar cells and ultimately their efficiency by adjusting the dimensions and micro-structural properties of nanowires., Comment: Main text + Supplementary materials, accepted, to appear in Physical Review B Letter (2024)

Compared to ground state electronic structure optimizations, accurate simulations of molecular real-time electron dynamics are usually much more difficult to perform. To simulate electron dynamics, the time-dependent density matrix renormalization group (TDDMRG) has been shown to offer an attractive compromise between accuracy and cost. However, many simulation parameters significantly affect the quality and efficiency of a TDDMRG simulation. So far, it is unclear whether common wisdom from ground state DMRG carries over to the TDDMRG, and a guideline on how to choose these parameters is missing. Here, in order to establish such a guideline, we investigate the convergence behavior of the main TDDMRG simulation parameters, such as time integrator, the choice of orbitals, and the choice of MPS representation for complex-valued non-singlet states. In addition, we propose a method to select orbitals that are tailored to optimize the dynamics. Lastly, we showcase the TDDMRG by applying it to charge migration ionization dynamics in furfural, where we reveal a rapid conversion from an ionized state with a $\sigma$ character to one with a $\pi$ character within less than a femtosecond.

In medical image classification, supervised learning is challenging due to the lack of labeled medical images. Contrary to the traditional \textit{modus operandi} of pre-training followed by fine-tuning, this work leverages the visual-textual alignment within Vision-Language models (\texttt{VLMs}) to facilitate the unsupervised learning. Specifically, we propose \underline{Med}ical \underline{Un}supervised \underline{A}daptation (\texttt{MedUnA}), constituting two-stage training: Adapter Pre-training, and Unsupervised Learning. In the first stage, we use descriptions generated by a Large Language Model (\texttt{LLM}) corresponding to class labels, which are passed through the text encoder \texttt{BioBERT}. The resulting text embeddings are then aligned with the class labels by training a lightweight \texttt{adapter}. We choose \texttt{\texttt{LLMs}} because of their capability to generate detailed, contextually relevant descriptions to obtain enhanced text embeddings. In the second stage, the trained \texttt{adapter} is integrated with the visual encoder of \texttt{MedCLIP}. This stage employs a contrastive entropy-based loss and prompt tuning to align visual embeddings. We incorporate self-entropy minimization into the overall training objective to ensure more confident embeddings, which are crucial for effective unsupervised learning and alignment. We evaluate the performance of \texttt{MedUnA} on three different kinds of data modalities - chest X-rays, eye fundus and skin lesion images. The results demonstrate significant accuracy gain on average compared to the baselines across different datasets, highlighting the efficacy of our approach.

Tunnel ionization (TI) underlies many important ultrafast processes, such as high-harmonic generation and strong-field ionization. Among the existing theories for TI, many-electron weak-field asymptotic theory (ME-WFAT) is by design capable of accurately treating many-electron effects in TI. An earlier version of ME-WFAT relied on an accurate representation of the asymptotic tail of the orbitals, which hindered its implementation in Gaussian-basis-set-based quantum chemistry programs. In this work, we reformulate ME-WFAT in the integral representation, which makes the quality of the asymptotic tail much less critical, hence greatly facilitating its implementation in standard quantum chemistry packages. The integral reformulation introduced here is therefore much more robust when applied to molecules with arbitrary geometry. We present several case studies, among which is the CO molecule where some earlier theories disagree with experiments. Here, we find that ME-WFAT produces the largest ionization probability when the field points from C to O, as experiments suggest. An attractive feature of ME-WFAT is that it can be used with various types of multi-electron methods whether of density functional [Phys. Rev. A 106, 052211 (2022)] or multiconfiguration types, which facilitates tunnel ionization calculation in systems exhibiting a strong multireference character, such as transition-metal-containing molecules., Comment: 20 pages and 6 figures

The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time involves tuning learnable prompts, ie, test-time prompt tuning. This paper introduces Test-Time Low-rank adaptation (TTL) as an alternative to prompt tuning for zero-shot generalization of large-scale VLMs. Taking inspiration from recent advancements in efficiently fine-tuning large language models, TTL offers a test-time parameter-efficient adaptation approach that updates the attention weights of the transformer encoder by maximizing prediction confidence. The self-supervised confidence maximization objective is specified using a weighted entropy loss that enforces consistency among predictions of augmented samples. TTL introduces only a small amount of trainable parameters for low-rank adapters in the model space while keeping the prompts and backbone frozen. Extensive experiments on a variety of natural distribution and cross-domain tasks show that TTL can outperform other techniques for test-time optimization of VLMs in strict zero-shot settings. Specifically, TTL outperforms test-time prompt tuning baselines with a significant improvement on average. Our code is available at at https://github.com/Razaimam45/TTL-Test-Time-Low-Rank-Adaptation., Comment: Main paper: 11 pages, Supplementary material: 5 pages

We implemented symbolic regression techniques to identify suitable analytical functions that map various properties of neutron stars (NSs), obtained by solving the Tolman-Oppenheimer-Volkoff (TOV) equations, to a few key parameters of the equation of state (EoS). These symbolic regression models (SRMs) are then employed to perform Bayesian inference with a comprehensive dataset from nuclear physics experiments and astrophysical observations. The posterior distributions of EoS parameters obtained from Bayesian inference using SRMs closely match those obtained directly from the solutions of TOV equations. Our SRM-based approach is approximately 100 times faster, enabling efficient Bayesian analyses across different combinations of data to explore their sensitivity to various EoS parameters within a reasonably short time.

The prevalence of AI-generated imagery has raised concerns about the authenticity of astronomical images, especially with advanced text-to-image models like Stable Diffusion producing highly realistic synthetic samples. Existing detection methods, primarily based on convolutional neural networks (CNNs) or spectral analysis, have limitations when used independently. We present AstroSpy, a hybrid model that integrates both spectral and image features to distinguish real from synthetic astronomical images. Trained on a unique dataset of real NASA images and AI-generated fakes (approximately 18k samples), AstroSpy utilizes a dual-pathway architecture to fuse spatial and spectral information. This approach enables AstroSpy to achieve superior performance in identifying authentic astronomical images. Extensive evaluations demonstrate AstroSpy's effectiveness and robustness, significantly outperforming baseline models in both in-domain and cross-domain tasks, highlighting its potential to combat misinformation in astronomy.

Existing vision-text contrastive learning models enhance representation transferability and support zero-shot prediction by matching paired image and caption embeddings while pushing unrelated pairs apart. However, astronomical image-label datasets are significantly smaller compared to general image and label datasets available from the internet. We introduce CosmoCLIP, an astronomical image-text contrastive learning framework precisely fine-tuned on the pre-trained CLIP model using SpaceNet and BLIP-based captions. SpaceNet, attained via FLARE, constitutes ~13k optimally distributed images, while BLIP acts as a rich knowledge extractor. The rich semantics derived from this SpaceNet and BLIP descriptions, when learned contrastively, enable CosmoCLIP to achieve superior generalization across various in-domain and out-of-domain tasks. Our results demonstrate that CosmoCLIP is a straightforward yet powerful framework, significantly outperforming CLIP in zero-shot classification and image-text retrieval tasks., Comment: Accepted at SPAICE Conference, ECSAT, UK, 2024

This work presents a soft continuum robot (SCR) that can be used as a soft continuum manipulator (SCM) and a soft snake robot (SSR). This is achieved using expanded polyethylene foam (EPE) modules as the soft material. In situations like post-earthquake search operations, these dual-purpose robots could play a vital role. The soft continuum manipulator with a camera attached to the tip can manually search for survivors in the debris. On the other hand, the soft snake robot can be made by attaching an active wheel to the soft continuum manipulator. This mobile robot can reach places humans cannot and gather information about survivors. This work presents the design, fabrication, and experimental validation of the dual soft continuum robot., Comment: 41 pages, 21 figures

The widespread adoption of ML systems across critical domains like hiring, finance, and healthcare raises growing concerns about their potential for discriminatory decision-making based on protected attributes. While efforts to ensure fairness during development are crucial, they leave deployed ML systems vulnerable to potentially exhibiting discrimination during their operations. To address this gap, we propose a novel framework for on-the-fly tracking and correction of discrimination in deployed ML systems. Leveraging counterfactual explanations, the framework continuously monitors the predictions made by an ML system and flags discriminatory outcomes. When flagged, post-hoc explanations related to the original prediction and the counterfactual alternatives are presented to a human reviewer for real-time intervention. This human-in-the-loop approach empowers reviewers to accept or override the ML system decision, enabling fair and responsible ML operation under dynamic settings. While further work is needed for validation and refinement, this framework offers a promising avenue for mitigating discrimination and building trust in ML systems deployed in a wide range of domains., Comment: 13 pages

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs.To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area., Comment: 44 pages, 14 figures, 7 tables, built with love by the BigCode community :)

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 28 countries on four continents, covering 26 languages with 11 scripts, providing a total of 9k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.

The intersection of Astronomy and AI encounters significant challenges related to issues such as noisy backgrounds, lower resolution (LR), and the intricate process of filtering and archiving images from advanced telescopes like the James Webb. Given the dispersion of raw images in feature space, we have proposed a \textit{two-stage augmentation framework} entitled as \textbf{FLARE} based on \underline{f}eature \underline{l}earning and \underline{a}ugmented \underline{r}esolution \underline{e}nhancement. We first apply lower (LR) to higher resolution (HR) conversion followed by standard augmentations. Secondly, we integrate a diffusion approach to synthetically generate samples using class-concatenated prompts. By merging these two stages using weighted percentiles, we realign the feature space distribution, enabling a classification model to establish a distinct decision boundary and achieve superior generalization on various in-domain and out-of-domain tasks. We conducted experiments on several downstream cosmos datasets and on our optimally distributed \textbf{SpaceNet} dataset across 8-class fine-grained and 4-class macro classification tasks. FLARE attains the highest performance gain of 20.78\% for fine-grained tasks compared to similar baselines, while across different classification models, FLARE shows a consistent increment of an average of +15\%. This outcome underscores the effectiveness of the FLARE method in enhancing the precision of image classification, ultimately bolstering the reliability of astronomical research outcomes. % Our code and SpaceNet dataset will be released to the public soon. Our code and SpaceNet dataset is available at \href{https://github.com/Razaimam45/PlanetX_Dxb}{\textit{https://github.com/Razaimam45/PlanetX\_Dxb}}., Comment: 15 pages main paper (including references), 3 pages supplementary material. Our code and SpaceNet dataset is available at https://github.com/Razaimam45/PlanetX_Dxb

Blockchain technology, heralded as a transformative innovation, has far-reaching implications beyond its initial application in cryptocurrencies. This study explores the potential of blockchain in enhancing data integrity and traceability within Industry Cyber-Physical Systems (ICPS), a crucial aspect in the era of Industry 4.0. ICPS, integrating computational and physical components, is pivotal in managing critical infrastructure like manufacturing, power grids, and transportation networks. However, they face challenges in security, privacy, and reliability. With its inherent immutability, transparency, and distributed consensus, blockchain presents a groundbreaking approach to address these challenges. It ensures robust data reliability and traceability across ICPS, enhancing transaction transparency and facilitating secure data sharing. This research unearths various blockchain applications in ICPS, including supply chain management, quality control, contract management, and data sharing. Each application demonstrates blockchain's capacity to streamline processes, reduce fraud, and enhance system efficiency. In supply chain management, blockchain provides real-time auditing and compliance. For quality control, it establishes tamper-proof records, boosting consumer confidence. In contract management, smart contracts automate execution, enhancing efficiency. Blockchain also fosters secure collaboration in ICPS, which is crucial for system stability and safety. This study emphasizes the need for further research on blockchain's practical implementation in ICPS, focusing on challenges like scalability, system integration, and security vulnerabilities. It also suggests examining blockchain's economic and organizational impacts in ICPS to understand its feasibility and long-term advantages.

The automatic recognition of tabular data in document images presents a significant challenge due to the diverse range of table styles and complex structures. Tables offer valuable content representation, enhancing the predictive capabilities of various systems such as search engines and Knowledge Graphs. Addressing the two main problems, namely table detection (TD) and table structure recognition (TSR), has traditionally been approached independently. In this research, we propose an end-to-end pipeline that integrates deep learning models, including DETR, CascadeTabNet, and PP OCR v2, to achieve comprehensive image-based table recognition. This integrated approach effectively handles diverse table styles, complex structures, and image distortions, resulting in improved accuracy and efficiency compared to existing methods like Table Transformers. Our system achieves simultaneous table detection (TD), table structure recognition (TSR), and table content recognition (TCR), preserving table structures and accurately extracting tabular data from document images. The integration of multiple models addresses the intricacies of table recognition, making our approach a promising solution for image-based table understanding, data extraction, and information retrieval applications. Our proposed approach achieves an IOU of 0.96 and an OCR Accuracy of 78%, showcasing a remarkable improvement of approximately 25% in the OCR Accuracy compared to the previous Table Transformer approach., Comment: 8 pages, 2 figures, Workshop of 1st MMIR Deep Multimodal Learning for Information Retrieval

With recent elevated adaptation of cloud services in almost every major public sector, the health sector emerges as a vulnerable segment, particularly in data exchange of sensitive Health records, as determining the retention, exchange, and efficient use of patient records without jeopardizing patient privacy, particularly on mobile-applications remains an area to expand. In the existing scenarios of cloud-mobile services, several vulnerabilities can be found including trapping of data within a single cloud-service-provider and loss of resource control being the significant ones. In this study, we have suggested a CPABE and OAuth2.0 based framework for efficient access-control and authorization respectively to improve the practicality of EHR sharing across a single client-application. In addition to solving issues like practicality, data entrapment, and resource control loss, the suggested framework also aims to provide two significant functionalities simultaneously, the specific operation of client application itself, and straightforward access of data to institutions, governments, and organizations seeking delicate EHRs. Our implementation of the suggested framework along with its analytical comparison signifies its potential in terms of efficient performance and minimal latency as this study would have a considerable impact on the recent literature as it intends to bridge the pragmatic deficit in CPABE-based EHR services.

Various decision support systems are available that implement Data Mining and Data Warehousing techniques for diving into the sea of data for getting useful patterns of knowledge (pearls). Classification, regression, clustering, and many other algorithms are used to enhance the precision and accuracy of the decision process. So, there is scope for increasing the response time of the decision process, especially in mission-critical operations. If data are ordered with suitable and efficient sorting operation, the response time of the decision process can be minimized. Insertion sort is much more suitable for such applications due to its simple and straight logic along with its dynamic nature suitable for list implementation. But it is slower than merge sort and quick sort. The main reasons this is slow: firstly, a sequential search is used to find the actual position of the next key element into the sorted left subarray and secondly, shifting of elements is required by one position towards the right for accommodating the newly inserted element. Therefore, I propose a new algorithm by using a novel technique of binary search mechanism for finding the sorted location of the next key item into the previously sorted left subarray much quicker than the conventional insertion sort algorithm. Performance measurement in terms of the actual running time of the new algorithm has been compared with those of other conventional sorting algorithms apart from the insertion sort. The results obtained on various sample data show that the new algorithm is better in performance than the conventional insertion sort and merge sort algorithms., Comment: None

In this study, we propose an automated framework for camel farm monitoring, introducing two key contributions: the Unified Auto-Annotation framework and the Fine-Tune Distillation framework. The Unified Auto-Annotation approach combines two models, GroundingDINO (GD), and Segment-Anything-Model (SAM), to automatically annotate raw datasets extracted from surveillance videos. Building upon this foundation, the Fine-Tune Distillation framework conducts fine-tuning of student models using the auto-annotated dataset. This process involves transferring knowledge from a large teacher model to a student model, resembling a variant of Knowledge Distillation. The Fine-Tune Distillation framework aims to be adaptable to specific use cases, enabling the transfer of knowledge from the large models to the small models, making it suitable for domain-specific applications. By leveraging our raw dataset collected from Al-Marmoom Camel Farm in Dubai, UAE, and a pre-trained teacher model, GroundingDINO, the Fine-Tune Distillation framework produces a lightweight deployable model, YOLOv8. This framework demonstrates high performance and computational efficiency, facilitating efficient real-time object detection. Our code is available at \href{https://github.com/Razaimam45/Fine-Tune-Distillation}{https://github.com/Razaimam45/Fine-Tune-Distillation}

Inspired by the discovery of metal-organic frameworks, the possibility of quantum anomalous Hall effect (QAHE) in two-dimensional kagome systems with $d$-orbital electrons is studied within a multi-orbital tight-binding model. In the absence of exchange-type spin-orbit coupling, isotropic Slater-Koster integrals give a band structure with relativistic (Dirac) and quadratic band crossing points at high symmetry spots in the Brillouin zone. A quantized topological invariant requires a flux-creating spin-orbit coupling, giving Chern number (per spin sector) $C=1$ not only from the familiar Dirac points at the six corners of the Brillouin zone, but also from the quadratic band crossing point at the center $\Gamma$. Surprisingly, this QAHE comes from the nontrivial effective flux induced by the transverse part of the spin-orbit coupling, exhibited by electrons in the $d$-orbital state with $m_l=0$ ($d_{z^2}$ orbital), in stark contrast to the more familiar form of QAHE due to the $d$-orbitals with $m_l \neq 0$, driven by the Ising part of spin-orbit coupling. The $C=1$ Chern plateau (per spin sector) due to Dirac point extends over a smaller region of Fermi energy than that due to quadratic band crossing. Our result hints at the promising potential of kagome metal-organic frameworks as a platform for dissipationless electronics by virtue of its unique QAHE., Comment: 5 pages main text + 11 pages supplementary materials. Comments are welcome

Numerous successes have been achieved in combating the COVID-19 pandemic, initially using various precautionary measures like lockdowns, social distancing, and the use of face masks. More recently, various vaccinations have been developed to aid in the prevention or reduction of the severity of the COVID-19 infection. Despite the effectiveness of the precautionary measures and the vaccines, there are several controversies that are massively shared on social media platforms like Twitter. In this paper, we explore the use of state-of-the-art transformer-based language models to study people's acceptance of vaccines in Nigeria. We developed a novel dataset by crawling multi-lingual tweets using relevant hashtags and keywords. Our analysis and visualizations revealed that most tweets expressed neutral sentiments about COVID-19 vaccines, with some individuals expressing positive views, and there was no strong preference for specific vaccine types, although Moderna received slightly more positive sentiment. We also found out that fine-tuning a pre-trained LLM with an appropriate dataset can yield competitive results, even if the LLM was not initially pre-trained on the specific language of that dataset.