Search

In many low- and medium-income countries (LMICs), student-centered pedagogies are often implicitly or explicitly at the heart of innovative pedagogical reforms. In recent years, there has been a growing emphasis on student-centered pedagogies, which aim to shift power dynamics, increase interaction, and prioritize the needs of learners. Many international agencies, governments, and education experts view these pedagogies as "best practices" or a pedagogical "silver bullet" to improve classroom practice. This paper is the second in a series of three working papers meant to serve as references and conversation starters for policymakers and researchers as they navigate pedagogical reform for education system transformation in their local contexts. Together, the three working papers emphasize the need for more locally driven collaborative research on how the interaction of culture, local education ecosystems, and learning theories--collectively called Invisible Pedagogical Mindsets--influences teachers' pedagogical choices in the classroom. This paper details why the authors recommend policymakers examine Invisible Pedagogical Mindsets in their local context to inform pedagogical reforms. The authors discuss the reasons why generalized "best practices"--namely "student-centered pedagogies" as currently implemented--do not often successfully transfer to new cultures, countries, and contexts and argue that many pedagogical reforms do not adequately consider the Invisible Pedagogical Mindsets embedded in each local context.

Although global access to schooling has increased over the last several decades, Sustainable Development Goal 4 (SDG 4), which champions inclusive, equitable, quality education, is far from being achieved. Experts predict that if the global community continues to operate education systems in the same way, by 2030, only one in six countries will reach the universal secondary school completion targets, and approximately 300 million students in school will continue to lack basic numeracy and literacy skills. The 2022 United Nations Transforming Education Summit emphasized the urgent need for a complete overhaul of education systems to meet SDG 4 targets. One significant outcome of the summit was a call to improve student learning by transforming teacher classroom practice. This paper is the first in a series of three working papers meant to serve as references and conversation starters for policymakers and researchers as they navigate pedagogical reform for education system transformation in their local contexts. This paper explores various definitions of pedagogies, the lack of consensus on what pedagogy means in practice, and the effects of Invisible Pedagogical Mindsets on pedagogical approaches.

Since the 1990s, there has been a growing demand for evidence-based education policy and practice. This demand stems from concerns that education systems are not meeting the needs of a changing world and that education research lacks rigor. While this demand aims to improve the quality of education, silos between different actors often hinder how evidence informs policymaking. We encourage researchers to use a collaborative research approach by involving multiple education actors in the research process to close the gaps between research, policy, and practice. This paper is the third in a series of three working papers meant to serve as references and conversation starters for policymakers and researchers as they navigate pedagogical reform for education system transformation in their local contexts. Together, the three working papers emphasize the need for more locally driven collaborative research on how the interaction of culture, local education ecosystems, and learning theories--collectively called Invisible Pedagogical Mindsets--influences teachers' pedagogical choices in the classroom. Primarily intended for education researchers, Working Paper III advocates the use of collaborative research approaches to actively include multiple education actors in the research process, foster complementary relationships between actors with different expertise, and make research findings more relevant and responsive to the local education ecosystem. The paper has three parts that discuss the need for flexible research approaches to inform policy given the complexities of education decision-making, the importance of communication and dissemination, and how collaborative research can bridge the gaps between research, policy, and practice. The paper concludes by looking at the ongoing work of the SPARKS project at the Center for Universal Education and how collaborative research can contribute to education systems transformation.

We present a comprehensive survey on the use of annotations in information visualizations, highlighting their crucial role in improving audience understanding and engagement with visual data. Our investigation encompasses empirical studies on annotations, showcasing their impact on user engagement, interaction, comprehension, and memorability across various contexts. We also study the existing tools and techniques for creating annotations and their diverse applications, enhancing the understanding of both practical and theoretical aspects of annotations in data visualization. Additionally, we identify existing research gaps and propose potential future research directions, making our survey a valuable resource for researchers, visualization designers, and practitioners by providing a thorough understanding of the application of annotations in visualization.

Random numbers are central to various applications such as secure communications, quantum key distribution theory (QKD), statistics, and other tasks. One of today's most popular generators is quantum random numbers (QRNGs). The inherent randomness and true unpredictability in quantum mechanics allowed us to construct QRNGs that are more accurate and useful than traditional random number generators. Based on different quantum mechanical principles, several QRNGs have already been designed. The primary focus of this paper is the generation and analysis of quantum random numbers based on radioactive decay. In the experimental set, two beta-active radioactive sources, cobalt-60 (Co60) and Strontium-90 (Sr 90), and an ST-360 counter with a Geiger-Muller (GM) tube are used to record the counts. The recorded data was then self-tested by entropy and frequency measurement. Moreover, popular testing technique, the National Institute of Science and Technology (NIST) randomness testing is used, to ensure that the guaranteed randomness meets security standards. The research provides the impact of the nature of the radioactive source, the distance between the counter and sources, and the recording time of the counts on generating quantum random numbers of radioactive QRNGs.

This paper addresses the challenges of embedding common droop control characteristics in ac-dc power system steady-state simulation and optimization problems. We propose a smooth approximation methodology to construct differentiable functions that encode the attributes of piecewise linear droop control with saturation. We transform the nonsmooth droop curves into smooth nonlinear equality constraints, solvable with Newton methods and interior point solvers. These constraints are then added to power flow, optimal power flow, and security-constrained optimal power flow problems in ac-dc power systems. The results demonstrate significant improvements in accuracy in terms of power sharing response, voltage regulation, and system efficiency, while outperforming existing mixed-integer formulations in computational efficiency., Comment: 6 pages, 8 figures, 2024 IEEE PES Australasian Universities Power Engineering Conference

Artificial Intelligence (AI) has demonstrated significant potential in automating various medical imaging tasks, which could soon become routine in clinical practice for disease diagnosis, prognosis, treatment planning, and post-treatment surveillance. However, the privacy concerns surrounding patient data present a major barrier to the widespread adoption of AI in medical imaging, as large, diverse training datasets are essential for developing accurate, generalizable, and robust Artificial intelligence models. Federated Learning (FL) offers a solution that enables organizations to train AI models collaboratively without sharing sensitive data. federated learning exchanges model training information, such as gradients, between the participating sites. Despite its promise, federated learning is still in its developmental stages and faces several challenges. Notably, sensitive information can still be inferred from the gradients shared during model training. Quantifying AI models' uncertainty is vital due to potential data distribution shifts post-deployment, which can affect model performance. Uncertainty quantification (UQ) in FL is particularly challenging due to data heterogeneity across participating sites. This review provides a comprehensive examination of FL, privacy-preserving FL (PPFL), and UQ in FL. We identify key gaps in current FL methodologies and propose future research directions to enhance data privacy and trustworthiness in medical imaging applications., Comment: 21 pages, 5 figures, 4 tables, Review paper, preprint to Radiology AI. arXiv admin note: text overlap with arXiv:2406.12815

A resolving set for a simple graph $G$ is a subset of vertex set of $G$ such that it distinguishes all vertices of $G$ using the shortest distance from this subset. This subset is a metric basis if it is the smallest set with this property. A resolving set is a fault tolerant resolving set if the removal of any vertex from the subset still leaves it a resolving set. The smallest set satisfying this property is the fault tolerant metric basis, and the cardinality of this set is termed as fault tolerant metric dimension of $G$, denoted by $\beta'(G)$. In this article, we determine the fault tolerant metric dimension of bicyclic graphs of type-I and II and show that it is always $4$ for both types of graphs. We then use these results to form our basis to consider leafless cacti graphs, and calculate their fault tolerant metric dimensions in terms of \textit{inner cycles} and \textit{outer cycles}. We then consider a detailed real world example of supply and distribution center management, and discuss the application of fault tolerant metric dimension in such a scenario. We also briefly discuss some other scenarios where leafless cacti graphs can be used to model real world problems.

Metric dimensions and metric basis are graph invariants studied for their use in locating and indexing nodes in a graph. It was recently established that for bicyclic graph of type-III ($\Theta $-graphs), the metric dimension is $3$ only, when all paths have equal lengths, or when one of the outside path has a length $2$ more than the other two paths. In this article, we refute this claim and show that the case where the middle path is $2$ vertices more than the other two paths, also has metric dimension $3$. We also determine the metric dimension for other values of $p,q,r$ which were omitted in the recent research due to the constraint $p \leq q \leq r$. We also propose a graph-based technique to transform an agricultural supply chain logistics problem into a mathematical model, by using metric basis and metric dimensions. We provide a theoretical groundwork which can be used to model and solve these problems using machine learning algorithms.

In the rapidly evolving field of information visualization, rigorous evaluation is essential for validating new techniques, understanding user interactions, and demonstrating the effectiveness and usability of visualizations. Faithful evaluations provide valuable insights into how users interact with and perceive the system, enabling designers to identify potential weaknesses and make informed decisions about design choices and improvements. However, an emerging trend of multiple evaluations within a single research raises critical questions about the sustainability, feasibility, and methodological rigor of such an approach. New researchers and students, influenced by this trend, may believe -- multiple evaluations are necessary for a study, regardless of the contribution types. However, the number of evaluations in a study should depend on its contributions and merits, not on the trend of including multiple evaluations to strengthen a paper. So, how many evaluations are enough? This is a situational question and cannot be formulaically determined. Our objective is to summarize current trends and patterns to assess the distribution of evaluation methods over different paper contribution types. In this paper, we identify this trend through a non-exhaustive literature survey of evaluation patterns in 214 papers in the two most recent years' VIS issues in IEEE TVCG from 2023 and 2024. We then discuss various evaluation strategy patterns in the information visualization field to guide practical choices and how this paper will open avenues for further discussion.

Shape is commonly used to distinguish between categories in multi-class scatterplots. However, existing guidelines for choosing effective shape palettes rely largely on intuition and do not consider how these needs may change as the number of categories increases. Although shapes can be a finite number compared to colors, they can not be represented by a numerical space, making it difficult to propose a general guideline for shape choices or shed light on the design heuristics of designer-crafted shape palettes. This paper presents a series of four experiments evaluating the efficiency of 39 shapes across three tasks -- relative mean judgment tasks, expert choices, and data correlation estimation. Given how complex and tangled results are, rather than relying on conventional features for modeling, we built a model and introduced a corresponding design tool that offers recommendations for shape encodings. The perceptual effectiveness of shapes significantly varies across specific pairs, and certain shapes may enhance perceptual efficiency and accuracy. However, how performance varies does not map well to classical features of shape such as angles, fill, or convex hull. We developed a model based on pairwise relations between shapes measured in our experiments and the number of shapes required to intelligently recommend shape palettes for a given design. This tool provides designers with agency over shape selection while incorporating empirical elements of perceptual performance captured in our study. Our model advances the understanding of shape perception in visualization contexts and provides practical design guidelines for advanced shape usage in visualization design that optimize perceptual efficiency.

Individuals with Intellectual and Developmental Disabilities (IDD) have unique needs and challenges when working with data. While visualization aims to make data more accessible to a broad audience, our understanding of how to design cognitively accessible visualizations remains limited. In this study, we engaged 20 participants with IDD as co-designers to explore how they approach and visualize data. Our preliminary investigation paired four participants as data pen-pals in a six-week online asynchronous participatory design workshop. In response to the observed conceptual, technological, and emotional struggles with data, we subsequently organized a two-day in-person co-design workshop with 16 participants to further understand relevant visualization authoring and sensemaking strategies. Reflecting on how participants engaged with and represented data, we propose two strategies for cognitively accessible data visualizations: transforming numbers into narratives and blending data design with everyday aesthetics. Our findings emphasize the importance of involving individuals with IDD in the design process, demonstrating their capacity for data analysis and expression, and underscoring the need for a narrative and tangible approach to accessible data visualization.

In this study, we developed the geometrically deformed compact objects in the $f(Q, T)$ gravity theory under an electric field through gravitational decoupling via. minimal geometric deformation (MGD) technique for the first time. The decoupled field equations are solved via two different mimic approaches $\theta_0^0 = \rho$ and $\theta_1^1 = p_r$ through the Karmarkar condition. We conduct physical viability tests on our models and examine how decoupling parameters affect the physical qualities of objects. The obtained models are compared with the observational constraints for neutron stars PSR J1810+174, PSR J1959+2048, and PSR J2215+5135, including GW190814. Particularly, by modifying parameters $\alpha$ and $n$, we accomplish the occurrence of a "\textit{mass gap}" component. The resulting models exhibit stable, well-behaved mass profiles, regular behaviour, and no gravitational collapse, as verified by the Buchdahl--Andr\'{e}asson's limit. Furthermore, we provide a thorough physical analysis that is based on two parameters: $n$ ($f(Q,T)$--coupling parameter) and $\alpha$ (decoupling parameter). This work extends our current understanding of compact star configurations and sheds light on the behaviour of compact objects in the $f(Q,T)$ gravity., Comment: Fortschritte der Physik published version

In this work, we investigated a most general isotropic charged fluid solution for the Buchdahl model via a two-step method in $\mathscr{F}(Q)$-gravity framework for the first time. In this context, a linear function of the form $\mathscr{F}(Q)=\zeta_1 Q+\zeta_2$ and a particular transformation is used to solve the Einstein-Maxwell Equations (EMEs) employing the Buchdahl ansatz: $ e^{\Upsilon(r)}=\frac{\mu(1+\lambda r^2)}{\mu+\lambda r^2}$, where $\zeta_1$, $\zeta_2$, $\lambda$ and $\mu$ are constant parameters. The Schwarzschild de Sitter~(AdS) exterior solution is joined to the interior solution at the boundary to determine the constant parameters. It should be emphasized that, for a given transformation, the Buchdahl ansatz only offers a mathematically feasible solution in the context of electric charge, where pressure and density are maximum at the center and decrease monotonically towards the boundary when $0<\mu<1$. We taken into account the compact star EX01785-248 with $M=(1.3\pm 0.2)M_{\odot}$; Radius $=12.02^{+0.55}_{-0.55}$~km for graphical analysis. The physical acceptability of the model in the context of $\mathscr{F}(Q)$ has been evaluated by looking at the necessary physical properties, including energy conditions, causality, hydrostatic equilibrium, pressure-density ratio, etc. Additionally, we predicted the maximum mass limit of different compact objects for various parameter values along with the mass-radius relation. The maximum masses range (1.927 - 2.321)~$M_\odot$ are obtained for our solution. It can be observed that when the coupling parameter $\zeta_1$ for $\mathscr{F}(Q)$ gravity is smaller, then our solution yields massive stars. The present investigation provides novel insights and realistic implications regarding the formation of compact astrophysical objects., Comment: 11 figures and 5 Tables

Machine learning (ML) and Artificial Intelligence (AI) have fueled remarkable advancements, particularly in healthcare. Within medical imaging, ML models hold the promise of improving disease diagnoses, treatment planning, and post-treatment monitoring. Various computer vision tasks like image classification, object detection, and image segmentation are poised to become routine in clinical analysis. However, privacy concerns surrounding patient data hinder the assembly of large training datasets needed for developing and training accurate, robust, and generalizable models. Federated Learning (FL) emerges as a compelling solution, enabling organizations to collaborate on ML model training by sharing model training information (gradients) rather than data (e.g., medical images). FL's distributed learning framework facilitates inter-institutional collaboration while preserving patient privacy. However, FL, while robust in privacy preservation, faces several challenges. Sensitive information can still be gleaned from shared gradients that are passed on between organizations during model training. Additionally, in medical imaging, quantifying model confidence\uncertainty accurately is crucial due to the noise and artifacts present in the data. Uncertainty estimation in FL encounters unique hurdles due to data heterogeneity across organizations. This paper offers a comprehensive review of FL, privacy preservation, and uncertainty estimation, with a focus on medical imaging. Alongside a survey of current research, we identify gaps in the field and suggest future directions for FL research to enhance privacy and address noisy medical imaging data challenges., Comment: 31 pages, 5 figures, 3 tables, Journal preprint

Cancer clinics capture disease data at various scales, from genetic to organ level. Current bioinformatic methods struggle to handle the heterogeneous nature of this data, especially with missing modalities. We propose PARADIGM, a Graph Neural Network (GNN) framework that learns from multimodal, heterogeneous datasets to improve clinical outcome prediction. PARADIGM generates embeddings from multi-resolution data using foundation models, aggregates them into patient-level representations, fuses them into a unified graph, and enhances performance for tasks like survival analysis. We train GNNs on pan-Squamous Cell Carcinomas and validate our approach on Moffitt Cancer Center lung SCC data. Multimodal GNN outperforms other models in patient survival prediction. Converging individual data modalities across varying scales provides a more insightful disease view. Our solution aims to understand the patient's circumstances comprehensively, offering insights on heterogeneous data integration and the benefits of converging maximum data views.

Drawing inspiration from the recent breakthroughs in the \ce{Na_{2}BaCo(PO_{4})_{2}} quantum magnet, renowned for its spin supersolidity phase and its potential for revolutionary cooling applications, our study delves into the intricate interplay among lattice, spin, and orbital degrees of freedom within this intriguing compound. Using meticulous temperature, field, and pressure-dependent Raman scattering techniques, we present compelling experimental evidence revealing pronounced crystal-electric field (CEF) excitations, alongside the interplay of CEF-phonon interactions. Notably, our experiments elucidate all electronic transitions from $j_{1 / 2}$ to $j_{3 / 2}$ and from $j_{1 / 2}$ to $j_{5 / 2}$, with energy level patterns closely aligned with theoretical predictions based on point-charge models. Furthermore, the application of a magnetic field and pressure reveals Zeeman splittings characterized by Land\'e-g factors as well as the CEF-phonon resonances. The anomalous shift in coupled peak at low temperatures originates from the hybridization of CEF and phonon excitations due to their close energy proximity. These findings constitute a significant step towards unraveling the fundamental properties of this exotic quantum material for future research in fundamental physics or engineering application.

Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. However, these approaches suffer from a problem called "rehearsal memory overfitting, " where the model becomes too specialized on limited memory samples and loses its ability to generalize effectively. As a result, the effectiveness of the rehearsal memory progressively decays, ultimately resulting in catastrophic forgetting of the learned tasks. We introduce the Adversarially Diversified Rehearsal Memory (ADRM) to address the memory overfitting challenge. This novel method is designed to enrich memory sample diversity and bolster resistance against natural and adversarial noise disruptions. ADRM employs the FGSM attacks to introduce adversarially modified memory samples, achieving two primary objectives: enhancing memory diversity and fostering a robust response to continual feature drifts in memory samples. Our contributions are as follows: Firstly, ADRM addresses overfitting in rehearsal memory by employing FGSM to diversify and increase the complexity of the memory buffer. Secondly, we demonstrate that ADRM mitigates memory overfitting and significantly improves the robustness of CL models, which is crucial for safety-critical applications. Finally, our detailed analysis of features and visualization demonstrates that ADRM mitigates feature drifts in CL memory samples, significantly reducing catastrophic forgetting and resulting in a more resilient CL model. Additionally, our in-depth t-SNE visualizations of feature distribution and the quantification of the feature similarity further enrich our understanding of feature representation in existing CL approaches. Our code is publically available at https://github.com/hikmatkhan/ADRM.

Developing accurate machine learning models for oncology requires large-scale, high-quality multimodal datasets. However, creating such datasets remains challenging due to the complexity and heterogeneity of medical data. To address this challenge, we introduce HoneyBee, a scalable modular framework for building multimodal oncology datasets that leverages foundation models to generate representative embeddings. HoneyBee integrates various data modalities, including clinical diagnostic and pathology imaging data, medical notes, reports, records, and molecular data. It employs data preprocessing techniques and foundation models to generate embeddings that capture the essential features and relationships within the raw medical data. The generated embeddings are stored in a structured format using Hugging Face datasets and PyTorch dataloaders for accessibility. Vector databases enable efficient querying and retrieval for machine learning applications. We demonstrate the effectiveness of HoneyBee through experiments assessing the quality and representativeness of these embeddings. The framework is designed to be extensible to other medical domains and aims to accelerate oncology research by providing high-quality, machine learning-ready datasets. HoneyBee is an ongoing open-source effort, and the code, datasets, and models are available at the project repository.

Multi-omics research has enhanced our understanding of cancer heterogeneity and progression. Investigating molecular data through multi-omics approaches is crucial for unraveling the complex biological mechanisms underlying cancer, thereby enabling effective diagnosis, treatment, and prevention strategies. However, predicting patient outcomes through integration of all available multi-omics data is an under-study research direction. Here, we present SeNMo (Self-normalizing Network for Multi-omics), a deep neural network trained on multi-omics data across 33 cancer types. SeNMo is efficient in handling multi-omics data characterized by high-width (many features) and low-length (fewer samples) attributes. We trained SeNMo for the task of overall survival using pan-cancer data involving 33 cancer sites from Genomics Data Commons (GDC). The training data includes gene expression, DNA methylation, miRNA expression, DNA mutations, protein expression modalities, and clinical data. We evaluated the model's performance in predicting overall survival using concordance index (C-Index). SeNMo performed consistently well in training regime, with the validation C-Index of 0.76 on GDC's public data. In the testing regime, SeNMo performed with a C-Index of 0.758 on a held-out test set. The model showed an average accuracy of 99.8% on the task of classifying the primary cancer type on the pan-cancer test cohort. SeNMo proved to be a mini-foundation model for multi-omics oncology data because it demonstrated robust performance, and adaptability not only across molecular data types but also on the classification task of predicting the primary cancer type of patients. SeNMo can be further scaled to any cancer site and molecular data type. We believe SeNMo and similar models are poised to transform the oncology landscape, offering hope for more effective, efficient, and patient-centric cancer care.

A gravastar comprises three distinct sections: the interior zone, the middle shell, and its outer region. By considering a specific extended teleparallel gravity model that incorporates conformal Killing vectors and provides the field equations. We observe that the interior part exhibits a repellent force acting on the shell. This is based on the assumption that pressure is analogous to negative energy density. The middle shell consists of ultrarelativistic plasma and pressure, which is directly proportional to the matter density and counteracts the repellent force exerted by the inner zone. In the outer zone, we compute the precise solution in a vacuum and then connect these spacetimes using junction conditions to investigate stability limits. We aim to investigate the influence of dark energy models on the stable characteristics of gravastar configurations. It is worth noting that the phantom field exhibits the highest stable configurations for all physically viable selections of physical parameters. We additionally investigate the influence of physical parameters on the correct length, entropy, and energy of the gravastar.

Artificial intelligence (AI) and neuroscience share a rich history, with advancements in neuroscience shaping the development of AI systems capable of human-like knowledge retention. Leveraging insights from neuroscience and existing research in adversarial and continual learning, we introduce a novel framework comprising two core concepts: feature distillation and re-consolidation. Our framework, named Robust Rehearsal, addresses the challenge of catastrophic forgetting inherent in continual learning (CL) systems by distilling and rehearsing robust features. Inspired by the mammalian brain's memory consolidation process, Robust Rehearsal aims to emulate the rehearsal of distilled experiences during learning tasks. Additionally, it mimics memory re-consolidation, where new experiences influence the integration of past experiences to mitigate forgetting. Extensive experiments conducted on CIFAR10, CIFAR100, and real-world helicopter attitude datasets showcase the superior performance of CL models trained with Robust Rehearsal compared to baseline methods. Furthermore, examining different optimization training objectives-joint, continual, and adversarial learning-we highlight the crucial role of feature learning in model performance. This underscores the significance of rehearsing CL-robust samples in mitigating catastrophic forgetting. In conclusion, aligning CL approaches with neuroscience insights offers promising solutions to the challenge of catastrophic forgetting, paving the way for more robust and human-like AI systems.

Existing guidelines for categorical color selection are heuristic, often grounded in intuition rather than empirical studies of readers' abilities. While design conventions recommend palettes maximize hue differences, more recent exploratory findings indicate other factors, such as lightness, may play a role in effective categorical palette design. We conducted a crowdsourced experiment on mean value judgments in multi-class scatterplots using five color palette families--single-hue sequential, multi-hue sequential, perceptually-uniform multi-hue sequential, diverging, and multi-hue categorical--that differ in how they manipulate hue and lightness. Participants estimated relative mean positions in scatterplots containing 2 to 10 categories using 20 colormaps. Our results confirm heuristic guidance that hue-based categorical palettes are most effective. However, they also provide additional evidence that scalable categorical encoding relies on more than hue variance., Comment: Accepted for publication in EuroVis 2024 Short Paper

InGaN quantum wells (QWs) grown on c-plane sapphire substrate experience strain due to the lattice mismatch. The strain generates a strong piezoelectric field in QWs that contributes to THz emission under ultrafast excitation. Physical parameters such as QW width, period number, and Indium concentration can affect the strength of the piezoelectric field and result in THz emission. Experimental parameters such as pump fluence, laser energy, excitation power, pump polarization angle, and incident angle can be tuned to further optimize the THz emission. This review summarizes the effects of physical and experimental parameters of THz emission on InGaN QWs. Comparison and relationship between photoluminescence properties and THz emission in QWs are given, which further explains the origin of THz emission in InGaN QWs.

Medical vision-language models (VLMs) combine computer vision (CV) and natural language processing (NLP) to analyze visual and textual medical data. Our paper reviews recent advancements in developing VLMs specialized for healthcare, focusing on models designed for medical report generation and visual question answering (VQA). We provide background on NLP and CV, explaining how techniques from both fields are integrated into VLMs to enable learning from multimodal data. Key areas we address include the exploration of medical vision-language datasets, in-depth analyses of architectures and pre-training strategies employed in recent noteworthy medical VLMs, and comprehensive discussion on evaluation metrics for assessing VLMs' performance in medical report generation and VQA. We also highlight current challenges and propose future directions, including enhancing clinical validity and addressing patient privacy concerns. Overall, our review summarizes recent progress in developing VLMs to harness multimodal medical data for improved healthcare applications., Comment: 43 pages; paper edited and restructured

In 2018 the Center for Universal Education (CUE) at Brookings launched a series of Real-time Scaling Labs (RTSL) to generate more evidence and provide practical recommendations on how to expand, deepen, and sustain the impact of education initiatives leading to transformative change in education systems, especially for the most disadvantaged children and youth. The purpose of this report is to look across all six of the RTSL cases to analyze common themes, insights, and lessons learned about the process of scaling as well as interesting divergences, and to offer considerations for others looking to learn from or build on this work. This report is intended for governments, education implementers, donors, and researchers who are interested in collaborative approaches to scaling impact in education. Section 1 examines key scaling lessons that emerged across all of the RTSL cases and analyzes scaling drivers (key levers, forces, or factors critical to making progress toward the scaling goal) at three different units of analysis to explore the way scaling happens at the system, institution, and individual levels. The second section analyzes how the RTSL model worked in practice, its strengths and challenges, and how it contributed to scaling. The report concludes with a set of core recommendations for governments, implementing organizations, donors, and researchers developed in consultation with the RTSL learning community. [This report was written with assistance from Brad Olsen and Katie Portnoy.]