Practically, satellite remote sensing is the only approach to measuring these variables at the spatial As the use of artificial intelligence (AI) expands to more and and temporal resolution needed for most applications (Liang more traditional domains, the bias in predictions made by 2001). Due to the large volume of satellite data, machine AI has also raised broad concerns in recent years. To facilitate learning methods have become increasingly popular choices the responsible use of AI, fairness-aware learning has in predicting temperature-related variables (Deo and Şahin emerged as an essential component in AI's deployment in 2017; Wang et al. 2021). However, fairness has yet to be societal applications. In this study, we focus on learningbased considered. Due to the social impact, it is important to ensure mapping applications, where it is important to evaluate fairness among different places in the prediction map.

Pandemics, notably the recent COVID-19 outbreak, have impacted both public health and the global economy. A profound understanding of disease progression and efficient response strategies is thus needed to prepare for potential future outbreaks. In this paper, we emphasize the potential of Agent-Based Models (ABM) in capturing complex infection dynamics and understanding the impact of interventions. We simulate realistic pharmaceutical, behavioral, and digital interventions that mirror challenges in real-world policy adoption and suggest a holistic combination of these interventions for pandemic response. Using these simulations, we study the trends of emergent behavior on a large-scale population based on real-world socio-demographic and geo-census data from Kings County in Washington. Our analysis reveals the pivotal role of the initial 100 days in dictating a pandemic's course, emphasizing the importance of quick decision-making and efficient policy development. Further, we highlight that investing in behavioral and digital interventions can reduce the burden on pharmaceutical interventions by reducing the total number of infections and hospitalizations, and by delaying the pandemic's peak. We also infer that allocating the same amount of dollars towards extensive testing with contact tracing and self-quarantine offers greater cost efficiency compared to spending the entire budget on vaccinations.

Recent works have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities. However, creating such datasets is difficult and most works rely on manual curation or proprietary language models. Automatic data curation is difficult as it is still not clear how we can define diversity for instruction tuning, how diversity and quality depend on one other, and how we can optimize dataset quality and diversity. To resolve these issue, we propose a new algorithm, Quality-Diversity Instruction Tuning (QDIT). QDIT provides a simple method to simultaneously control dataset diversity and quality, allowing us to conduct an in-depth study on the effect of diversity and quality on instruction tuning performance. From this study we draw two key insights (1) there is a natural tradeoff between data diversity and quality and (2) increasing data diversity significantly improves the worst case instruction following performance, therefore improving robustness. We validate the performance of QDIT on several large scale instruction tuning datasets, where we find it can substantially improve worst and average case performance compared to quality-driven data selection.

Large Language Models (LLMs) have demonstrated remarkable performance on coding related tasks, particularly on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities of LLMs suffer from severe limitations. First, most benchmarks are deficient as they focus on a narrow range of popular programming languages and specific tasks, whereas the real-world software development scenarios show dire need to implement systems with multilingual programming environments to satisfy diverse requirements. Practical programming practices also strongly expect multi-task settings for testing coding capabilities of LLMs comprehensively and robustly. Second, most benchmarks also fail to consider the actual executability and the consistency of execution results of the generated code. To bridge these gaps between existing benchmarks and expectations from practical applications, we introduce CodeScope, an execution-based, multilingual, multi-task, multi-dimensional evaluation benchmark for comprehensively gauging LLM capabilities on coding tasks. CodeScope covers 43 programming languages and 8 coding tasks. It evaluates the coding performance of LLMs from three dimensions (perspectives): difficulty, efficiency, and length. To facilitate execution-based evaluations of code generation, we develop MultiCodeEngine, an automated code execution engine that supports 14 programming languages. Finally, we systematically evaluate and analyze 8 mainstream LLMs on CodeScope tasks and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks. The CodeScope benchmark and datasets are publicly available at https://github.com/WeixiangYAN/CodeScope.

Otago Exercise Program (OEP) is a rehabilitation program for older adults to improve frailty, sarcopenia, and balance. Accurate monitoring of patient involvement in OEP is challenging, as self-reports (diaries) are often unreliable. With the development of wearable sensors, Human Activity Recognition (HAR) systems using wearable sensors have revolutionized healthcare. However, their usage for OEP still shows limited performance. The objective of this study is to build an unobtrusive and accurate system to monitor OEP for older adults. Data was collected from older adults wearing a single waist-mounted Inertial Measurement Unit (IMU). Two datasets were collected, one in a laboratory setting, and one at the homes of the patients. A hierarchical system is proposed with two stages: 1) using a deep learning model to recognize whether the patients are performing OEP or activities of daily life (ADLs) using a 10-minute sliding window; 2) based on stage 1, using a 6-second sliding window to recognize the OEP sub-classes performed. The results showed that in stage 1, OEP could be recognized with window-wise f1-scores over 0.95 and Intersection-over-Union (IoU) f1-scores over 0.85 for both datasets. In stage 2, for the home scenario, four activities could be recognized with f1-scores over 0.8: ankle plantarflexors, abdominal muscles, knee bends, and sit-to-stand. The results showed the potential of monitoring the compliance of OEP using a single IMU in daily life. Also, some OEP sub-classes are possible to be recognized for further analysis.

Despite the progress we have recorded in the last few years in multilingual natural language processing, evaluation is typically limited to a small set of languages with available datasets which excludes a large number of low-resource languages. In this paper, we created SIB-200 -- a large-scale open-sourced benchmark dataset for topic classification in 200 languages and dialects to address the lack of evaluation dataset for Natural Language Understanding (NLU). For many of the languages covered in SIB-200, this is the first publicly available evaluation dataset for NLU. The dataset is based on Flores-200 machine translation corpus. We annotated the English portion of the dataset and extended the sentence-level annotation to the remaining 203 languages covered in the corpus. Despite the simplicity of this task, our evaluation in full-supervised setting, cross-lingual transfer setting and prompting of large language model setting show that there is still a large gap between the performance of high-resource and low-resource languages when multilingual evaluation is scaled to numerous world languages. We found that languages unseen during the pre-training of multilingual language models, under-represented language families (like Nilotic and Altantic-Congo), and languages from the regions of Africa, Americas, Oceania and South East Asia, often have the lowest performance on our topic classification dataset. We hope our dataset will encourage a more inclusive evaluation of multilingual language models on a more diverse set of languages. https://github.com/dadelani/sib-200

Recent advancements have significantly augmented the reasoning capabilities of Large Language Models (LLMs) through various methodologies, especially chain-of-thought (CoT) reasoning. However, previous methods fail to address reasoning errors in intermediate steps, leading to accumulative errors. In this paper, we propose Deductive Beam Search (DBS), which seamlessly integrates CoT and deductive reasoning with step-wise beam search for LLMs. Our approach deploys a verifier, verifying the deducibility of a reasoning step and its premises, thus alleviating the error accumulation. Furthermore, we introduce a scalable and labor-free data construction method to amplify our model's verification capabilities. Extensive experiments demonstrate that our approach significantly enhances the base performance of LLMs of various scales (7B, 13B, 70B, and ChatGPT) across 8 reasoning datasets from 3 diverse reasoning genres, including arithmetic, commonsense, and symbolic. Moreover, our analysis proves DBS's capability of detecting diverse and subtle reasoning errors and robustness on different model scales.

Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods. To address this challenge, we propose an efficient model-free feature selection framework via elastic expansion and compression of the features, namely EasyFS, to achieve better performance than state-of-the-art model-aware methods while sharing the characters of efficiency and flexibility with the existing model-free methods. In particular, EasyFS expands the feature space by using the random non-linear projection network to achieve the non-linear combinations of the original features, so as to model the interrelationships among the features and discover most correlated features. Meanwhile, a novel redundancy measurement based on the change of coding rate is proposed for efficient filtering of redundant features. Comprehensive experiments on 21 different datasets show that EasyFS outperforms state-of-the art methods up to 10.9\% in the regression tasks and 5.7\% in the classification tasks while saving more than 94\% of the time.

Aim: To study the existence of subgroups by exploring the similarities between the attributes of the nodes of the groups, in relation to diet and gender and, to analyse the connectivity between groups based on aspects of similarities between them through SNA and artificial intelligence techniques. Methods: 235 students from 5 different educational centres participate in this study between March and December 2015. Data analysis carried out is divided into two blocks: social network analysis and unsupervised machine learning techniques. As for the social network analysis, the Girvan-Newman technique was applied to find the best number of cohesive groups within each of the friendship networks of the different classes analysed. Results: After applying Girvan-Newman in the three classes, the best division into clusters was respectively 2 for classroom A, 7 for classroom B and 6 for classroom C. There are significant differences between the groups and the gender and diet variables. After applying K-means using population diet as an input variable, a K-means clustering of 2 clusters for class A, 3 clusters for class B and 3 clusters for class C is obtained. Conclusion: Adolescents form subgroups within their classrooms. Subgroup cohesion is defined by the fact that nodes share similarities in aspects that influence obesity, they share attributes related to food quality and gender. The concept of homophily, related to SNA, justifies our results. Artificial intelligence techniques together with the application of the Girvan-Newman provide robustness to the structural analysis of similarities and cohesion between subgroups.

Artificially generated induced pluripotent stem cells (iPSCs) from somatic cells play an important role for disease modeling and drug screening of neurodegenerative diseases. Astrocytes differentiated from iPSCs are important targets to investigate neuronal metabolism. The astrocyte differentiation progress can be monitored through the variations of morphology observed from microscopy images at different differentiation stages, then determined by molecular biology techniques upon maturation. However, the astrocytes usually ``perfectly'' blend into the background and some of them are covered by interference information (i.e., dead cells, media sediments, and cell debris), which makes astrocytes difficult to observe. Due to the lack of annotated datasets, the existing state-of-the-art deep learning approaches cannot be used to address this issue. In this paper, we introduce a new task named astrocyte segmentation with a novel dataset, called IAI704, which contains 704 images and their corresponding pixel-level annotation masks. Moreover, a novel frequency domain denoising network, named FDNet, is proposed for astrocyte segmentation. In detail, our FDNet consists of a contextual information fusion module (CIF), an attention block (AB), and a Fourier transform block (FTB). CIF and AB fuse multi-scale feature embeddings to localize the astrocytes. FTB transforms feature embeddings into the frequency domain and conducts a high-pass filter to eliminate interference information. Experimental results demonstrate the superiority of our proposed FDNet over the state-of-the-art substitutes in astrocyte segmentation, shedding insights for iPSC differentiation progress prediction.