Most ost Big Data datasets suffer from selection bias. For example, X (Twitter) training observations differ largely from the testing offline observations as individuals on Twitter are generally more educated, democratic or left-leaning. Therefore, one major obstacle to reliable estimation is the differences between training and testing data. How can researchers make use of such data even in the presence of non-ignorable selection mechanisms? A number of methods have been developed for this issue, such as distributionally robust optimization (DRO) or learning fairness. A possible avenue to reducing the effect of bias is meta-information. Researchers, being field exerts, might have prior information on the form and extent of selection bias affecting their dataset, and in which direction the selection might cause the estimate to change, e.g. over or under estimation. At the same time, there is no direct way to leverage these types of information in learning. I propose a loss function which takes into account two types of meta data information given by the researcher: quantity and direction (under or over sampling) of bias in the training set. Estimation with the proposed loss function is then implemented through a neural network, the directional Rockafellar-Uryasev (dRU) regression model. I test the dRU model on a biased training dataset, a Big Data online drawn electoral poll. I apply the proposed model using meta data information coherent with the political and sampling information obtained from previous studies. The results show that including meta information improves the electoral results predictions compared to a model that does not include them.

Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest that supervised models can learn interpretable factors of variation in a linear fashion. Recent advances in self-supervised learning, particularly nonlinear Independent Component Analysis, have shown that these methods can recover latent structures by inverting the data generating process. We extend these identifiability results to parametric instance discrimination, then show how insights transfer to the ubiquitous setting of supervised learning with cross-entropy minimization. We prove that even in standard classification tasks, models learn representations of ground-truth factors of variation up to a linear transformation. We corroborate our theoretical contribution with a series of empirical studies. First, using simulated data matching our theoretical assumptions, we demonstrate successful disentanglement of latent factors. Second, we show that on DisLib, a widely-used disentanglement benchmark, simple classification tasks recover latent structures up to linear transformations. Finally, we reveal that models trained on ImageNet encode representations that permit linear decoding of proxy factors of variation. Together, our theoretical findings and experiments offer a compelling explanation for recent observations of linear representations, such as superposition in neural networks. This work takes a significant step toward a cohesive theory that accounts for the unreasonable effectiveness of supervised deep learning.

Russian forces downed 19 Ukrainian drones overnight – 16 over the southern Rostov region and the remainder over the Belgorod and Bryansk regions – Russia's Ministry of Defence said on Sunday. Blasts were heard in Kyiv early on Sunday and smoke was seen rising from above residential buildings after a suspected Russian drone attack on Ukraine's capital. The attack comes after Kyiv's Mayor Vitali Klitschko said on the Telegram channel that Ukraine's air defence units were trying to repel a Russian air attack on the city, ordering people to stay in shelters. Ukrainian forces are restraining one of Russia's "most powerful offensives" since the start of Moscow's full-scale invasion in 2022, Ukraine's top military commander, General Oleksandr Syrskii, has said. Russia troops have taken two more settlements along the Donbas frontline – Kurakhivka and Pershotravneve – Russian news agencies reported on Saturday, citing the country's Defence Ministry.

Sotheby's will auctio the first-ever artwork created by a humanoid robot. Thieves in the Netherlands used explosives to blow open the doors of an art gallery on Friday, making off with two rare screen prints by American pop artist Andy Warhol. According to MPV Gallery owner Mark Peet Visser, the suspects also abandoned two more works which were badly damaged in the street as they fled. Visser shared with the Associated Press that the suspects attempted to steal all four works from Warhol's 1985 "Reigning Queens" series. The Warhol portraits include renderings of Queen Elizabeth II of the United Kingdom, Queen Margrethe II of Denmark, Queen Beatrix of the Netherlands, and Queen Ntombi Tfwala of Swaziland (now Eswatini).

In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, RuAG applies Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.

We introduce SinaTools, an open-source Python package for Arabic natural language processing and understanding. SinaTools is a unified package allowing people to integrate it into their system workflow, offering solutions for various tasks such as flat and nested Named Entity Recognition (NER), fully-flagged Word Sense Disambiguation (WSD), Semantic Relatedness, Synonymy Extractions and Evaluation, Lemmatization, Part-of-speech Tagging, Root Tagging, and additional helper utilities such as corpus processing, text stripping methods, and diacritic-aware word matching. This paper presents SinaTools and its benchmarking results, demonstrating that SinaTools outperforms all similar tools on the aforementioned tasks, such as Flat NER (87.33%), Nested NER (89.42%), WSD (82.63%), Semantic Relatedness (0.49 Spearman rank), Lemmatization (90.5%), POS tagging (97.5%), among others. SinaTools can be downloaded from (https://sina.birzeit.edu/sinatools).

Complex Word Identification (CWI) is an essential step in the lexical simplification task and has recently become a task on its own. Some variations of this binary classification task have emerged, such as lexical complexity prediction (LCP) and complexity evaluation of multi-word expressions (MWE). Large language models (LLMs) recently became popular in the Natural Language Processing community because of their versatility and capability to solve unseen tasks in zero/few-shot settings. Our work investigates LLM usage, specifically open-source models such as Llama 2, Llama 3, and Vicuna v1.5, and closed-source, such as ChatGPT-3.5-turbo and GPT-4o, in the CWI, LCP, and MWE settings. We evaluate zero-shot, few-shot, and fine-tuning settings and show that LLMs struggle in certain conditions or achieve comparable results against existing methods. In addition, we provide some views on meta-learning combined with prompt learning. In the end, we conclude that the current state of LLMs cannot or barely outperform existing methods, which are usually much smaller.

This work has been submitted to the IEEE for possible publication. Abstract -- In this paper we reexamine the process through which a Neural Radiance Field (NeRF) can be trained to produce novel LiDAR views of a scene. Unlike image applications where camera pixels integrate light over time, LiDAR pulses arrive at specific times. As such, multiple LiDAR returns are possible for any given detector and the classification of these returns is inherently probabilistic. Applying a traditional NeRF training routine can result in the network learning "phantom surfaces" in free space between conflicting range measurements, similar to how "floater" aberrations may be produced by an image model. Code is available at https://github.com/mcdermatt/PLINK Neural Radience Fields (NeRFs) provide continuous representations of scenes by storing information about the surrounding world inside the weights of a neural network [1]. Recent works have extended NeRFs from camera images to LiDAR point clouds for use in localization [2], odometry [3], path planning [4], and data augmentation [5, 6]. To date, LiDAR applications of NeRFs have assumed a deterministic model of the scene.

People with learning disabilities have a higher mortality rate and premature deaths compared to the general public, as reported in published research in the UK and other countries. This study analyses hospitalisations of 9,618 patients identified with learning disabilities and long-term conditions for the population of Wales using electronic health record (EHR) data sources from the SAIL Databank. We describe the demographic characteristics, prevalence of long-term conditions, medication history, hospital visits, and lifestyle history for our study cohort, and apply machine learning models to predict the length of hospital stays for this cohort. The random forest (RF) model achieved an Area Under the Curve (AUC) of 0.759 (males) and 0.756 (females), a false negative rate of 0.224 (males) and 0.229 (females), and a balanced accuracy of 0.690 (males) and 0.689 (females). After examining model performance across ethnic groups, two bias mitigation algorithms (threshold optimization and the reductions algorithm using an exponentiated gradient) were applied to minimise performance discrepancies. The threshold optimizer algorithm outperformed the reductions algorithm, achieving lower ranges in false positive rate and balanced accuracy for the male cohort across the ethnic groups. This study demonstrates the potential of applying machine learning models with effective bias mitigation approaches on EHR data sources to enable equitable prediction of hospital stays by addressing data imbalances across groups.

Traditional natural disaster response involves significant coordinated teamwork where speed and efficiency are key. Nonetheless, human limitations can delay critical actions and inadvertently increase human and economic losses. Agentic Large Vision Language Models (LVLMs) offer a new avenue to address this challenge, with the potential for substantial socio-economic impact, particularly by improving resilience and resource access in underdeveloped regions. We introduce DisasTeller, the first multi-LVLM-powered framework designed to automate tasks in post-disaster management, including on-site assessment, emergency alerts, resource allocation, and recovery planning. By coordinating four specialised LVLM agents with GPT-4 as the core model, DisasTeller autonomously implements disaster response activities, reducing human execution time and optimising resource distribution. Our evaluations through both LVLMs and humans demonstrate DisasTeller's effectiveness in streamlining disaster response. This framework not only supports expert teams but also simplifies access to disaster management processes for non-experts, bridging the gap between traditional response methods and LVLM-driven efficiency.