Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of these dialogues by treating them as regular text. In this paper, we propose a speaker-enhanced pre-training method for long dialogue summarization, which leverages the inherent structure of multiple-turn dialogues. To support our study, we curate a diverse dataset that includes transcripts from real-world scenarios, movie or TV show transcripts, and dialogues generated by a Large Language Model. We then perform a pre-training, which encompasses the detection of speaker changes, and masked utterance generation. Experimental results of fine-tuned models demonstrate that our model achieves state-of-the-art performance on downstream benchmarks with long context, surpassing baseline models and highlighting the effectiveness of our approach. Our findings highlight the importance of curating pre-training datasets that exhibit diversity and variations in length distribution to ensure effective alignment with downstream datasets.

This study presents a new approach for estimating confidence in machine learning model predictions, specifically in regression tasks utilizing Earth Observation (EO) data, with a particular focus on mosquito abundance (MA) estimation. We take advantage of a Variational AutoEncoder architecture, to derive a confidence metric by the latent space representations of EO datasets. This methodology is pivotal in establishing a correlation between the Euclidean distance in latent representations and the Absolute Error (AE) in individual MA predictions. Our research focuses on EO datasets from the Veneto region in Italy and the Upper Rhine Valley in Germany, targeting areas significantly affected by mosquito populations. A key finding is a notable correlation of 0.46 between the AE of MA predictions and the proposed confidence metric. This correlation signifies a robust, new metric for quantifying the reliability and enhancing the trustworthiness of the AI model's predictions in the context of both EO data analysis and mosquito abundance studies.

Brain tumors are the most common solid tumors and the leading cause of cancer-related death among children. Tumor segmentation is essential in surgical and treatment planning, and response assessment and monitoring. However, manual segmentation is time-consuming and has high inter-operator variability, underscoring the need for more efficient methods. We compared two deep learning-based 3D segmentation models, DeepMedic and nnU-Net, after training with pediatric-specific multi-institutional brain tumor data using based on multi-parametric MRI scans.Multi-parametric preoperative MRI scans of 339 pediatric patients (n=293 internal and n=46 external cohorts) with a variety of tumor subtypes, were preprocessed and manually segmented into four tumor subregions, i.e., enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). After training, performance of the two models on internal and external test sets was evaluated using Dice scores, sensitivity, and Hausdorff distance with reference to ground truth manual segmentations. Dice score for nnU-Net internal test sets was (mean +/- SD (median)) 0.9+/-0.07 (0.94) for WT, 0.77+/-0.29 for ET, 0.66+/-0.32 for NET, 0.71+/-0.33 for CC, and 0.71+/-0.40 for ED, respectively. For DeepMedic the Dice scores were 0.82+/-0.16 for WT, 0.66+/-0.32 for ET, 0.48+/-0.27, for NET, 0.48+/-0.36 for CC, and 0.19+/-0.33 for ED, respectively. Dice scores were significantly higher for nnU-Net (p<=0.01). External validation of the trained nnU-Net model on the multi-institutional BraTS-PEDs 2023 dataset revealed high generalization capability in segmentation of whole tumor and tumor core with Dice scores of 0.87+/-0.13 (0.91) and 0.83+/-0.18 (0.89), respectively. Pediatric-specific data trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.

The use of Mixed-Integer Linear Programming (MILP) models to represent neural networks with Rectified Linear Unit (ReLU) activations has become increasingly widespread in the last decade. This has enabled the use of MILP technology to test--or stress--their behavior, to adversarially improve their training, and to embed them in optimization models leveraging their predictive power. Many of these MILP models rely on activation bounds. That is, bounds on the input values of each neuron. In this work, we explore the tradeoff between the tightness of these bounds and the computational effort of solving the resulting MILP models. We provide guidelines for implementing these models based on the impact of network structure, regularization, and rounding.

In recent years, predicting mobile app usage has become increasingly important for areas like app recommendation, user behaviour analysis, and mobile resource management. Existing models, however, struggle with the heterogeneous nature of contextual data and the user cold start problem. This study introduces a novel prediction model, Mobile App Prediction Leveraging Large Language Model Embeddings (MAPLE), which employs Large Language Models (LLMs) and installed app similarity to overcome these challenges. MAPLE utilises the power of LLMs to process contextual data and discern intricate relationships within it effectively. Additionally, we explore the use of installed app similarity to address the cold start problem, facilitating the modelling of user preferences and habits, even for new users with limited historical data. In essence, our research presents MAPLE as a novel, potent, and practical approach to app usage prediction, making significant strides in resolving issues faced by existing models. MAPLE stands out as a comprehensive and effective solution, setting a new benchmark for more precise and personalised app usage predictions. In tests on two real-world datasets, MAPLE surpasses contemporary models in both standard and cold start scenarios. These outcomes validate MAPLE's capacity for precise app usage predictions and its resilience against the cold start problem. This enhanced performance stems from the model's proficiency in capturing complex temporal patterns and leveraging contextual information. As a result, MAPLE can potentially improve personalised mobile app usage predictions and user experiences markedly.

While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at \url{https://github.com/yangbang18/CLFM}.

The reasoning abilities of large language models (LLMs) are the topic of a growing body of research in artificial intelligence and cognitive science. In this paper, we probe the extent to which a dozen LLMs are able to distinguish logically correct inferences from logically fallacious ones. We focus on inference patterns involving conditionals (e.g., 'If Ann has a queen, then Bob has a jack') and epistemic modals (e.g., 'Ann might have an ace', 'Bob must have a king'). These inference patterns have been of special interest to logicians, philosophers, and linguists, since they plausibly play a central role in human reasoning. Assessing LLMs on these inference patterns is thus highly relevant to the question of how much the reasoning abilities of LLMs match those of humans. Among the LLMs we tested, all but GPT-4 often make basic mistakes with conditionals. Moreover, even GPT-4 displays logically inconsistent judgments across inference patterns involving epistemic modals.

Quantum computing shows great potential, but errors pose a significant challenge. This study explores new strategies for mitigating quantum errors using artificial neural networks (ANN) and the Yang-Baxter equation (YBE). Unlike traditional error correction methods, which are computationally intensive, we investigate artificial error mitigation. The manuscript introduces the basics of quantum error sources and explores the potential of using classical computation for error mitigation. The Yang-Baxter equation plays a crucial role, allowing us to compress time dynamics simulations into constant-depth circuits. By introducing controlled noise through the YBE, we enhance the dataset for error mitigation. We train an ANN model on partial data from quantum simulations, demonstrating its effectiveness in correcting errors in time-evolving quantum states.

Investors and regulators are concerned about financial market volatility and crashes. For this reason, the Volatility index (VIX) was introduced in 1993 by the Chicago Board Options Exchange (CBOE) with the aim of assessing the expected financial market volatility in the short-run, i.e. for the next 30 days, since it is calculated as an implied volatility from the options on the S&P 500 index on this time-to-maturity [1]. The VIX has been proven to be a good predictor of expected stock index shifts, and therefore as an early warning for investor sentiment and financial market turbulences (see e.g., [1], and more recently, [2]). Due to its importance for asset managers and regulators, it would be useful to foresee the values of the index; however, the VIX is very difficult to forecast [3]. There exist several proposals to predict time series found in the literature classified as conventional and modern methods (see e.g., [4] and the references therein).

Yield curves are used for a wide variety of tasks in actuarial science and finance for deriving the present value of future cashflows within valuations that apply a market consistent approach. A market consistent approach is required by modern solvency regulations, such as Solvency II, while recently updated accounting standards, such as the recently introduced IFRS 17, require the use of credit and liquidity adjusted yield curves for discounting liabilities, including both life and non-life insurance liabilities. Insurers, and other entities, that report on their liabilities on a discounted basis are exposed to the risk of changes in the interest rates in their markets, which translate directly into changes in the solvency of these entities. Therefore, managing this risk of adverse changes in yield curves - which we refer to as interest rate risk in what follows - is an important task within actuarial work, which is usually considered in the context of corresponding changes in the asset portfolio backing these liabilities, changes in the value of which may act as an offset. This process is, therefore, usually referred to as Asset-Liability Management (ALM).