NATO leaders are holding their annual summit as Ukraine looks to the security alliance for support in its attempt to push back invading Russian forces. The Vilnius communique, however, while emphasising NATO's support for Ukraine, gave no clear timetable on when the country might be able to join the alliance, in a major disappointment for Ukrainian President Volodymyr Zelenskyy, who had travelled to the Lithuanian capital. "Ukraine's future is in NATO," the leaders said in the joint statement on Tuesday. "We will be in a position to extend an invitation to Ukraine to join the alliance when allies agree and conditions are met," the declaration said, without specifying the conditions. The communique also touched on the Asia Pacific, with the leaders of Australia, Japan, New Zealand and South Korea all attending as NATO allies. It said China was a challenge to NATO's interests, security and values with its "ambitions and coercive policies" triggering a furious response from Beijing. And it accused Beijing and Moscow of "mutually reinforcing attempts to undercut the rules-based international order". China has said it wants peace in Ukraine, but has not condemned Russia's full scale invasion since it began in February 2022. NATO is a defensive Alliance. It is the unique, essential and indispensable transatlantic forum to consult, coordinate and act on all matters related to our individual and collective security. We reaffirm our iron-clad commitment to defend each other and every inch of Allied territory at all times, protect our one billion citizens, and safeguard our freedom and democracy, in accordance with Article 5 of the Washington Treaty. We will continue to ensure our collective defence from all threats, no matter where they stem from, based on a 360-degree approach, to fulfil NATO's three core tasks of deterrence and defence, crisis prevention and management, and cooperative security. We adhere to international law and to the purposes and principles of the Charter of the United Nations and are committed to upholding the rules-based international order. This Summit marks a milestone in strengthening our Alliance. We look forward to our valuable exchanges with the Heads of State and Government of Australia, Japan, New Zealand, and the Republic of Korea, as well as the President of the European Council and the President of the European Commission at this Summit. We also welcome the engagements with the Foreign Ministers of Georgia and the Republic of Moldova, and with the Deputy Foreign Minister of Bosnia and Herzegovina, as we continue to consult closely on the implementation of NATO's tailored support measures. This is an historic step for Finland and for NATO. For many years, we worked closely as partners; we now stand together as Allies. NATO membership makes Finland safer, and NATO stronger. Every nation has the right to choose its own security arrangements.

Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world knowledge, implying the limitations of relying solely on their parameters to encode a wealth of world knowledge. This paper aims to understand LMs' strengths and limitations in memorizing factual knowledge, by conducting large-scale knowledge probing experiments of 10 models and 4 augmentation methods on PopQA, our new open-domain QA dataset with 14k questions. We find that LMs struggle with less popular factual knowledge, and that scaling fails to appreciably improve memorization of factual knowledge in the long tail. We then show that retrieval-augmented LMs largely outperform orders of magnitude larger LMs, while unassisted LMs remain competitive in questions about high-popularity entities. Based on those findings, we devise a simple, yet effective, method for powerful and efficient retrieval-augmented LMs, which retrieves non-parametric memories only when necessary. Experimental results show that this significantly improves models' performance while reducing the inference costs.

Automatic discourse processing is bottlenecked by data: current discourse formalisms pose highly demanding annotation tasks involving large taxonomies of discourse relations, making them inaccessible to lay annotators. This work instead adopts the linguistic framework of Questions Under Discussion (QUD) for discourse analysis and seeks to derive QUD structures automatically. QUD views each sentence as an answer to a question triggered in prior context; thus, we characterize relationships between sentences as free-form questions, in contrast to exhaustive fine-grained taxonomies. We develop the first-of-its-kind QUD parser that derives a dependency structure of questions over full documents, trained using a large, crowdsourced question-answering dataset DCQA (Ko et al., 2022). Human evaluation results show that QUD dependency parsing is possible for language models trained with this crowdsourced, generalizable annotation scheme. We illustrate how our QUD structure is distinct from RST trees, and demonstrate the utility of QUD analysis in the context of document simplification. Our findings show that QUD parsing is an appealing alternative for automatic discourse processing.

As phasor measurement units (PMUs) become more widely used in transmission power systems, a fast state estimation (SE) algorithm that can take advantage of their high sample rates is needed. To accomplish this, we present a method that uses graph neural networks (GNNs) to learn complex bus voltage estimates from PMU voltage and current measurements. We propose an original implementation of GNNs over the power system's factor graph to simplify the integration of various types and quantities of measurements on power system buses and branches. Furthermore, we augment the factor graph to improve the robustness of GNN predictions. This model is highly efficient and scalable, as its computational complexity is linear with respect to the number of nodes in the power system. Training and test examples were generated by randomly sampling sets of power system measurements and annotated with the exact solutions of linear SE with PMUs. The numerical results demonstrate that the GNN model provides an accurate approximation of the SE solutions. Furthermore, errors caused by PMU malfunctions or communication failures that would normally make the SE problem unobservable have a local effect and do not deteriorate the results in the rest of the power system.

On the other hand, it is quite conceivable that a simple diagnoses are made on the basis of a multitude of ECG binary classification of healthy vs. a specific pathology could features which consist mainly of time intervals between certain be successfully achieved by using only a reduced subset of the fiducial points on the ECG, amplitudes of prominent features complete list of diagnostic conditions. However, we consider or morphology of ECG segments. For each pathology, the it appropriate to study the simplest case first. A study of relevant criteria for specific features are well documented [1], multiclass feature importance algorithms with all four of the [2], although there may be minor differences between one above classes has been undertaken as a separate study [4].

Transformer networks have revolutionized NLP representation learning since they were introduced. Though a great effort has been made to explain the representation in transformers, it is widely recognized that our understanding is not sufficient. One important reason is that there lack enough visualization tools for detailed analysis. In this paper, we propose to use dictionary learning to open up these "black boxes" as linear superpositions of transformer factors. Through visualization, we demonstrate the hierarchical semantic structures captured by the transformer factors, e.g., word-level polysemy disambiguation, sentence-level pattern formation, and long-range dependency. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights. We hope this visualization tool can bring further knowledge and a better understanding of how transformer networks work. The code is available at https://github.com/zeyuyun1/TransformerVis

Data-driven state estimation (SE) is becoming increasingly important in modern power systems, as it allows for more efficient analysis of system behaviour using real-time measurement data. This paper thoroughly evaluates a phasor measurement unit-only state estimator based on graph neural networks (GNNs) applied over factor graphs. To assess the sample efficiency of the GNN model, we perform multiple training experiments on various training set sizes. Additionally, to evaluate the scalability of the GNN model, we conduct experiments on power systems of various sizes. Our results show that the GNN-based state estimator exhibits high accuracy and efficient use of data. Additionally, it demonstrated scalability in terms of both memory usage and inference time, making it a promising solution for data-driven SE in modern power systems.

When a customer overdraws their account and their balance is negative they are assessed an overdraft fee. Americans pay approximately \$15 billion in unnecessary overdraft fees a year, often in \$35 increments; users of the Mint personal finance app pay approximately \$250 million in fees a year in particular. These overdraft fees are an excessive financial burden and lead to cascading overdraft fees trapping customers in financial hardship. To address this problem, we have created an ML-driven overdraft early warning system (ODEWS) that assesses a customer's risk of overdrafting within the next week using their banking and transaction data in the Mint app. At-risk customers are sent an alert so they can take steps to avoid the fee, ultimately changing their behavior and financial habits. The system deployed resulted in a \$3 million savings in overdraft fees for Mint customers compared to a control group. Moreover, the methodology outlined here can be generalized to provide ML-driven personalized financial advice for many different personal finance goals--increase credit score, build emergency savings fund, pay down debut, allocate capital for investment.

To achieve optimal robot behavior in dynamic scenarios we need to consider complex dynamics in a predictive manner. In the vehicle dynamics community, it is well know that to achieve time-optimal driving on low surface, the vehicle should utilize drifting. Hence many authors have devised rules to split circuits and employ drifting on some segments. These rules are suboptimal and do not generalize to arbitrary circuit shapes (e.g., S-like curves). So, the question "When to go into which mode and how to drive in it?" remains unanswered. To choose the suitable mode (discrete decision), the algorithm needs information about the feasibility of the continuous motion in that mode. This makes it a class of Task and Motion Planning (TAMP) problems, which are known to be hard to solve optimally in real-time. In the AI planning community, search methods are commonly used. However, they cannot be directly applied to TAMP problems due to the continuous component. Here, we present a search-based method that effectively solves this problem and efficiently searches in a highly dimensional state space with nonlinear and unstable dynamics. The space of the possible trajectories is explored by sampling different combinations of motion primitives guided by the search. Our approach allows to use multiple locally approximated models to generate motion primitives (e.g., learned models of drifting) and effectively simplify the problem without losing accuracy. The algorithm performance is evaluated in simulated driving on a mixed-track with segments of different curvatures (right and left). Our code is available at https://git.io/JenvB

Geographic features are commonly used to improve the performance of pretrained language models (PLMs) on NLP tasks where they are intuitively beneficial (e.g., geolocation prediction, dialect feature prediction). Existing methods, however, leverage geographic information in task-specific fine-tuning and fail to integrate it into the geo-linguistic knowledge encoded by PLMs, which would make it transferable across different tasks. In this paper, we introduce an approach to task-agnostic geoadaptation of PLMs that forces them to learn associations between linguistic phenomena and geographic locations. Geoadaptation is an intermediate training step that couples language modeling and geolocation prediction in a multi-task learning setup. In our main set of experiments, we geoadapt BERTi\'{c}, a PLM for Bosnian-Croatian-Montenegrin-Serbian (BCMS), using a corpus of geotagged BCMS tweets. Evaluation on three tasks, namely fine-tuned as well as zero-shot geolocation prediction and zero-shot prediction of dialect features, shows that geoadaptation is very effective: e.g., we obtain state-of-the-art performance in supervised geolocation prediction and report massive gains over geographically uninformed PLMs on zero-shot geolocation prediction. Moreover, in follow-up experiments we successfully geoadapt two other PLMs, specifically ScandiBERT on Norwegian, Swedish, and Danish tweets and GermanBERT on Jodel posts in German from Austria, Germany, and Switzerland, proving that the benefits of geoadaptation are not limited to a particular language area and PLM.