Time series anomaly detection presents various challenges due to the sequential and dynamic nature of time-dependent data. Traditional unsupervised methods frequently encounter difficulties in generalization, often overfitting to known normal patterns observed during training and struggling to adapt to unseen normality. In response to this limitation, self-supervised techniques for time series have garnered attention as a potential solution to undertake this obstacle and enhance the performance of anomaly detectors. This paper presents a comprehensive review of the recent methods that make use of self-supervised learning for time series anomaly detection. A taxonomy is proposed to categorize these methods based on their primary characteristics, facilitating a clear understanding of their diversity within this field. The information contained in this survey, along with additional details that will be periodically updated, is available on the following GitHub repository: https://github.com/Aitorzan3/Awesome-Self-Supervised-Time-Series-Anomaly-Detection.

Due to the scarcity of data in low-resourced languages, the development of language models for these languages has been very slow. Currently, pre-trained language models have gained popularity in natural language processing, especially, in developing domain-specific models for low-resourced languages. In this study, we experiment with the impact of using occlusion-based techniques when training a language model for a text generation task. We curate 2 new datasets, the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the radio news domain. We use the SepMono dataset to pre-train transformer-based models using the occlusion and non-occlusion pre-training techniques and compare performance. The SepNews dataset is specifically used for fine-tuning. Our results show that the non-occlusion models perform better compared to the occlusion-based models when measuring validation loss and perplexity. However, analysis of the generated text using the BLEU score metric, which measures the quality of the generated text, shows a slightly higher BLEU score for the occlusion-based models compared to the non-occlusion models.

In recent years, the prediction of multidimensional time series data has become increasingly important due to its wide-ranging applications. Tensor-based prediction methods have gained attention for their ability to preserve the inherent structure of such data. However, existing approaches, such as tensor autoregression and tensor decomposition, often have consistently failed to provide clear assertions regarding the number of samples that can be exactly predicted. While matrix-based methods using nuclear norms address this limitation, their reliance on matrices limits accuracy and increases computational costs when handling multidimensional data. To overcome these challenges, we reformulate multidimensional time series prediction as a deterministic tensor completion problem and propose a novel theoretical framework. Specifically, we develop a deterministic tensor completion theory and introduce the Temporal Convolutional Tensor Nuclear Norm (TCTNN) model. By convolving the multidimensional time series along the temporal dimension and applying the tensor nuclear norm, our approach identifies the maximum forecast horizon for exact predictions. Additionally, TCTNN achieves superior performance in prediction accuracy and computational efficiency compared to existing methods across diverse real-world datasets, including climate temperature, network flow, and traffic ride data. Our implementation is publicly available at https://github.com/HaoShu2000/TCTNN.

Principal component analysis is commonly used for dimensionality reduction, feature extraction, denoising, and visualization. The most commonly used principal component analysis method is based upon optimization of the L2-norm, however, the L2-norm is known to exaggerate the contribution of errors and outliers. When optimizing over the L1-norm, the components generated are known to exhibit robustness or resistance to outliers in the data. The L1-norm components can be solved for with a binary optimization problem. Previously, L1-BF has been used to solve the binary optimization for multiple components simultaneously. In this paper we propose QAPCA, a new method for finding principal components using quantum annealing hardware which will optimize over the robust L1-norm. The conditions required for convergence of the annealing problem are discussed. The potential speedup when using quantum annealing is demonstrated through complexity analysis and experimental results. To showcase performance against classical principal component analysis techniques experiments upon synthetic Gaussian data, a fault detection scenario and breast cancer diagnostic data are studied. We find that the reconstruction error when using QAPCA is comparable to that when using L1-BF.

The global adoption of Large Language Models (LLMs) in healthcare shows promise to enhance clinical workflows and improve patient outcomes. However, Automatic Speech Recognition (ASR) errors in critical medical terms remain a significant challenge. These errors can compromise patient care and safety if not detected. This study investigates the prevalence and impact of ASR errors in medical transcription in Nigeria, the United Kingdom, and the United States. By evaluating raw and LLM-corrected transcriptions of accented English in these regions, we assess the potential and limitations of LLMs to address challenges related to accents and medical terminology in ASR. Our findings highlight significant disparities in ASR accuracy across regions and identify specific conditions under which LLM corrections are most effective.

Retrieval-Augmented Generation (RAG) models have drawn considerable attention in modern open-domain question answering. The effectiveness of RAG depends on the quality of the top retrieved documents. However, conventional retrieval methods sometimes fail to rank the most relevant documents at the top. In this paper, we introduce ASRank, a new re-ranking method based on scoring retrieved documents using zero-shot answer scent which relies on a pre-trained large language model to compute the likelihood of the document-derived answers aligning with the answer scent. Our approach demonstrates marked improvements across several datasets, including NQ, TriviaQA, WebQA, ArchivalQA, HotpotQA, and Entity Questions. Notably, ASRank increases Top-1 retrieval accuracy on NQ from $19.2\%$ to $46.5\%$ for MSS and $22.1\%$ to $47.3\%$ for BM25. It also shows strong retrieval performance on several datasets compared to state-of-the-art methods (47.3 Top-1 by ASRank vs 35.4 by UPR by BM25).

While he charmed, almost seduced the audience with a credible picture of a booming US economy about to scale new technological heights, he simultaneously menaced with threats of tariffs to those who did not choose to shift their factories into the US. "Your prerogative" he said, with a smile not out of place in a Godfather movie. He awkwardly mumbled about sponsoring the World Cup. In this first week of his second term, most people at Davos were nodding along, as they cannot think what else to do, just yet. Two worlds colliding, as the'America First' President was beamed in like a 30-foot interplanetary emperor, into the beating heart of the rules-based international economic order. It is one thing suggesting that trade deficits are a problem with your domestic electorate.

In an increasingly digital world, connectivity is a necessity. Yet, nearly a third of the global population remains offline, unable to access the services vital to participating in our global digital economy and society. The Edison Alliance at the World Economic Forum has worked to change that by delivering digital connectivity and access to financial, healthcare, and education services to those who need them most. Our partnerships with governments, industries, and non-governmental organizations drive lasting systemic change. The World Economic Forum played a pivotal role in launching and guiding the Alliance's work, providing a platform for stakeholders to come together and commit to a vision with actionable ideas and plans.

Knowledge Tracing (KT) is a fundamental component of Intelligent Tutoring Systems (ITS), enabling the modeling of students' knowledge states to predict future performance. The introduction of Deep Knowledge Tracing (DKT), the first deep learning-based KT (DLKT) model, has brought significant advantages in terms of applicability and comprehensiveness. However, recent DLKT models, such as Attentive Knowledge Tracing (AKT), have often prioritized predictive performance at the expense of these benefits. While deep sequential models like DKT have shown potential, they face challenges related to parallel computing, storage decision modification, and limited storage capacity. To address these limitations, we propose DKT2, a novel KT model that leverages the recently developed xLSTM architecture. DKT2 enhances input representation using the Rasch model and incorporates Item Response Theory (IRT) for interpretability, allowing for the decomposition of learned knowledge into familiar and unfamiliar knowledge. By integrating this knowledge with predicted questions, DKT2 generates comprehensive knowledge states. Extensive experiments conducted across three large-scale datasets demonstrate that DKT2 consistently outperforms 17 baseline models in various prediction tasks, underscoring its potential for real-world educational applications. This work bridges the gap between theoretical advancements and practical implementation in KT.Our code and datasets will be available at https://github.com/codebase-2025/DKT2.

Performance models are essential for automatic code optimization, enabling compilers to predict the effects of code transformations on performance and guide search for optimal transformations. Building state-of-the-art performance models with deep learning, however, requires vast labeled datasets of random programs -- an expensive and time-consuming process, stretching over months. This paper introduces a self-supervised pre-training scheme with autoencoders to reduce the need for labeled data. By pre-training on a large dataset of random programs, the autoencoder learns representations of code and transformations, which are then used to embed programs for the performance model. Implemented in the Tiramisu autoscheduler, our approach improves model accuracy with less data. For example, to achieve a MAPE of 20.72%, the original model requires 18 million data points, whereas our method achieves a similar MAPE of 22.44% with only 3.6 million data points, reducing data requirements by 5x.