Graph Shift Operators (GSOs), such as the adjacency and graph Laplacian matrices, play a fundamental role in graph theory and graph representation learning. Traditional GSOs are typically constructed by normalizing the adjacency matrix by the degree matrix, a local centrality metric. In this work, we instead propose and study Centrality GSOs (CGSOs), which normalize adjacency matrices by global centrality metrics such as the PageRank, $k$-core or count of fixed length walks. We study spectral properties of the CGSOs, allowing us to get an understanding of their action on graph signals. We confirm this understanding by defining and running the spectral clustering algorithm based on different CGSOs on several synthetic and real-world datasets. We furthermore outline how our CGSO can act as the message passing operator in any Graph Neural Network and in particular demonstrate strong performance of a variant of the Graph Convolutional Network and Graph Attention Network using our CGSOs on several real-world benchmark datasets.

The first piece of AI-generated video I ever made moved me to tears – tears of laughter. Given the chance to fool around with Runway AI's Gen-3 Alpha, I dropped in an image of an eagle carrying off a wolf. Moments later, the picture sprang into life. Except the bird only had one leg – and its plummeting prey sprouted wings from its tail and morphed into a wolf-headed goose. It was weird and hilarious.

Deep Learning (DL) has shown promise for downscaling global climate change projections under different approaches, including Perfect Prognosis (PP) and Regional Climate Model (RCM) emulation. Unlike emulators, PP downscaling models are trained on observational data, so it remains an open question whether they can plausibly extrapolate unseen conditions and changes in future emissions scenarios. Here we focus on this problem as the main drawback for the operationalization of these methods and present the results of 1) a literature review to identify state-of-the-art DL models for PP downscaling and 2) an intercomparison experiment to evaluate the performance of these models and to assess their extrapolation capability using a common experimental framework, taking into account the sensitivity of results to different training replicas. We focus on minimum and maximum temperatures and precipitation over Spain, a region with a range of climatic conditions with different influential regional processes. We conclude with a discussion of the findings, limitations of existing methods, and prospects for future development.

The COVID-19 pandemic has affected millions of people globally, with respiratory organs being strongly affected in individuals with comorbidities. Medical imaging-based diagnosis and prognosis have become increasingly popular in clinical settings for detecting COVID-19 lung infections. Among various medical imaging modalities, ultrasound stands out as a low-cost, mobile, and radiation-safe imaging technology. In this comprehensive review, we focus on AI-driven studies utilizing lung ultrasound (LUS) for COVID-19 detection and analysis. We provide a detailed overview of both publicly available and private LUS datasets and categorize the AI studies according to the dataset they used. Additionally, we systematically analyzed and tabulated the studies across various dimensions, including data preprocessing methods, AI models, cross-validation techniques, and evaluation metrics. In total, we reviewed 60 articles, 41 of which utilized public datasets, while the remaining employed private data. Our findings suggest that ultrasound-based AI studies for COVID-19 detection have great potential for clinical use, especially for children and pregnant women. Our review also provides a useful summary for future researchers and clinicians who may be interested in the field.

However, although the cooperation between these two seems natural, the difference in their representation is obviously not negligible. Prof. Henry Kautz proposed a taxonomy of Neuro-Symbolic Systems in the AAAI 2020. In addition, many researchers have conducted relevant reviews of the recent neuro-symbolic AI from different perspectives. As Fig.1 shows, Acharya et al. [1] proposed a new classification method, which classified and discussed the application of existing neuro-symbolic AI by the role of neural and symbolic parts: learning for reasoning, reasoning for Learning, and learning-reasoning. Garcez et al. [73] proposed a taxonomy that includes sequential, nested, cooperative, and compiled neuro-symbolic AI based on the six types introduced by Henry Kautz. In addition, some reviews focus on cross-field integration and applications. For example, Berlot-Attwell [27] reviewed neuro-symbolic VQA (visual question answering) from the perspectives of AGI (artificial general intelligence) desiderata. Marra [128] conducted a comprehensive review on integrating neuro-symbolic and statistical relational artificial intelligence based on seven dimensions.

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the increasing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.

Explainability is an essential reason limiting the application of neural networks in many vital fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging the transparency of symbolic learning, the results are less evident than imagined. This article proposes a classification for explainability by considering both model design and behavior of 191 studies from 2013, focusing on neuro-symbolic AI, hoping to inspire scholars who want to understand the explainability of neuro-symbolic AI. Precisely, we classify them into five categories by considering whether the form of bridging the representation differences is readable as their design factor, if there are representation differences between neural networks and symbolic logic learning, and whether a model decision or prediction process is understandable as their behavior factor: implicit intermediate representations and implicit prediction, partially explicit intermediate representations and partially explicit prediction, explicit intermediate representations or explicit prediction, explicit intermediate representation and explicit prediction, unified representation and explicit prediction. We also analyzed the research trends and three significant challenges: unified representations, explainability and transparency, and sufficient cooperation from neural networks and symbolic learning. Finally, we put forward suggestions for future research in three aspects: unified representations, enhancing model explainability, ethical considerations, and social impact.

An open problem in artificial intelligence is how to train language models that produce responses that are factually correct. Current frontier models sometimes produce false outputs or answers that are not substantiated by evidence, a problem known as "hallucinations." Such hallucinations are one of the major barriers for broader adoption of general forms artificial intelligence like large language models. Factuality is a complicated topic because it is hard to measure--evaluating the factuality of any given arbitrary claim can be challenging, and language models often generate long completions that contain dozens of factual claims. In this work we will sidestep the open-endedness of language models by considering only short, fact-seeking questions with a single answer. This reduction of scope is important because it makes measuring factuality much more tractable, albeit at the cost of leaving open research questions such as whether improved behavior on short-form factuality generalizes to long-form factuality. We present a benchmark called SimpleQA, which contains 4,326 short, fact-seeking questions. SimpleQA was designed with a few important properties in mind: High correctness. Reference answers to questions are determined by two independent AI trainers, and questions were written in such a way that the predicted answers are easily gradable.

Large language models (LLMs) offer promise in generating educational content, providing instructor feedback, and reducing teacher workload on assessments. While prior studies have focused on studying LLM-powered learning analytics, limited research has examined how effective LLMs are in a bilingual context. In this paper, we study the effectiveness of multilingual large language models (MLLMs) across monolingual (English-only, Spanish-only) and bilingual (Spanglish) student writing. We present a learning analytics use case that details LLM performance in assessing acceptable and unacceptable explanations of Science and Social Science concepts. Our findings reveal a significant bias in the grading performance of pre-trained models for bilingual writing compared to English-only and Spanish-only writing. Following this, we fine-tune open-source MLLMs including Llama 3.1 and Mistral NeMo using synthetic datasets generated in English, Spanish, and Spanglish. Our experiments indicate that the models perform significantly better for all three languages after fine-tuning with bilingual data. This study highlights the potential of enhancing MLLM effectiveness to support authentic language practices amongst bilingual learners. It also aims to illustrate the value of incorporating non-English languages into the design and implementation of language models in education.

Extreme multilabel classification (XMLC) problems occur in settings such as related product recommendation, large-scale document tagging, or ad prediction, and are characterized by a label space that can span millions of possible labels. There are two implicit tasks that the classifier performs: \emph{Evaluating} each potential label for its expected worth, and then \emph{selecting} the best candidates. For the latter task, only the relative order of scores matters, and this is what is captured by the standard evaluation procedure in the XMLC literature. However, in many practical applications, it is important to have a good estimate of the actual probability of a label being relevant, e.g., to decide whether to pay the fee to be allowed to display the corresponding ad. To judge whether an extreme classifier is indeed suited to this task, one can look, for example, to whether it returns \emph{calibrated} probabilities, which has hitherto not been done in this field. Therefore, this paper aims to establish the current status quo of calibration in XMLC by providing a systematic evaluation, comprising nine models from four different model families across seven benchmark datasets. As naive application of Expected Calibration Error (ECE) leads to meaningless results in long-tailed XMC datasets, we instead introduce the notion of \emph{calibration@k} (e.g., ECE@k), which focusses on the top-$k$ probability mass, offering a more appropriate measure for evaluating probability calibration in XMLC scenarios. While we find that different models can exhibit widely varying reliability plots, we also show that post-training calibration via a computationally efficient isotonic regression method enhances model calibration without sacrificing prediction accuracy. Thus, the practitioner can choose the model family based on accuracy considerations, and leave calibration to isotonic regression.