The Stanceosaurus corpus (Zheng et al., 2022) was designed to provide high-quality, annotated, 5-way stance data extracted from Twitter, suitable for analyzing cross-cultural and cross-lingual misinformation. In the Stanceosaurus 2.0 iteration, we extend this framework to encompass Russian and Spanish. The former is of current significance due to prevalent misinformation amid escalating tensions with the West and the violent incursion into Ukraine. The latter, meanwhile, represents an enormous community that has been largely overlooked on major social media platforms. By incorporating an additional 3,874 Spanish and Russian tweets over 41 misinformation claims, our objective is to support research focused on these issues. To demonstrate the value of this data, we employed zero-shot cross-lingual transfer on multilingual BERT, yielding results on par with the initial Stanceosaurus study with a macro F1 score of 43 for both languages. This underlines the viability of stance classification as an effective tool for identifying multicultural misinformation.

The underwater world remains largely unexplored, with Autonomous Underwater Vehicles (AUVs) playing a crucial role in sub-sea explorations. However, continuous monitoring of underwater environments using AUVs can generate a significant amount of data. In addition, sending live data feed from an underwater environment requires dedicated on-board data storage options for AUVs which can hinder requirements of other higher priority tasks. Informative sampling techniques offer a solution by condensing observations. In this paper, we present a semantically-aware online informative sampling (ON-IS) approach which samples an AUV's visual experience in real-time. Specifically, we obtain visual features from a fine-tuned object detection model to align the sampling outcomes with the desired semantic information. Our contributions are (a) a novel Semantic Online Informative Sampling (SON-IS) algorithm, (b) a user study to validate the proposed approach and (c) a novel evaluation metric to score our proposed algorithm with respect to the suggested samples by human subjects

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over free-form text. In the absence of ground-truth probabilities, we explore a setting where, in order to (approximately) disentangle a given LLM's uncertainty, a significantly larger model stands in as a proxy for the ground truth. We show that small linear probes trained on the embeddings of frozen, pretrained models accurately predict when larger models will be more confident at the token level and that probes trained on one text domain generalize to others. Going further, we propose a fully unsupervised method that achieves non-trivial accuracy on the same task. Taken together, we interpret these results as evidence that LLMs naturally contain internal representations of different types of uncertainty that could potentially be leveraged to devise more informative indicators of model confidence in diverse practical settings.

Punctuation restoration is a crucial step after Automatic Speech Recognition (ASR) systems to enhance transcript readability and facilitate subsequent NLP tasks. Nevertheless, conventional lexical-based approaches are inadequate for solving the punctuation restoration task in Spanish, where ambiguity can be often found between unpunctuated declaratives and questions. In this study, we propose a novel hybrid acoustic-lexical punctuation restoration system for Spanish transcription, which consolidates acoustic and lexical signals through a modular process. Our experiment results show that the proposed system can effectively improve F1 score of question marks and overall punctuation restoration on both public and internal Spanish conversational datasets. Additionally, benchmark comparison against LLMs (Large Language Model) indicates the superiority of our approach in accuracy, reliability and latency. Furthermore, we demonstrate that the Word Error Rate (WER) of the ASR module also benefits from our proposed system.

The extraordinary advancement in Generative Artificial Intelligence (GenAI) has caused a transformative shift in our approach to complex tasks incorporating various modalities such as text, audio, video, and image generation. GenAI, as a broad category, excels at creating synthetic data that can closely mimic real-world phenomena, showcasing its prowess in diverse creative applications. In text generation, models like OpenAI's GPT (Generative Pre-trained Transformer) [OpenAI, 2023] are revolutionizing how society writes. These models, trained on massive corpora of text data, exhibit an impressive ability to understand context, generate coherent paragraphs, and even complete sentences in a very consistent way [Roumeliotis and Tselikas, 2023]. The ability to produce fluent and relevant textual content has established applications in natural language processing, content creation, and even automated writing [Huang and Tan, 2023]. Audio generation models, exemplified by technologies such as Tacotron [Wang et al., 2017] and WaveNet [Oord et al., 2016], have significantly advanced our ability to synthesize realistic speech patterns. These models take advantage of deep neural networks to capture the intricacies of human speech, producing natural-sounding voices and musical compositions with nuanced variations in tone, pitch, and rhythm [Ning et al., 2019]. Image generation, a focal point of our discussion, has witnessed the evolution of models such as DALL-E [Betker et al., 2023, Ramesh et al., 2021], MidJourney [mid, 2022], and Stable Diffusion [Rombach et al., 2022], which can generate diverse and intricate images from textual prompts.

Dynamic 2-[18F] fluoro-2-deoxy-D-glucose positron emission tomography (dFDG-PET) for human brain imaging has considerable clinical potential, yet its utilization remains limited. A key challenge in the quantitative analysis of dFDG-PET is characterizing a patient-specific blood input function, traditionally reliant on invasive arterial blood sampling. This research introduces a novel approach employing non-invasive deep learning model-based computations from the internal carotid arteries (ICA) with partial volume (PV) corrections, thereby eliminating the need for invasive arterial sampling. We present an end-to-end pipeline incorporating a 3D U-Net based ICA-net for ICA segmentation, alongside a Recurrent Neural Network (RNN) based MCIF-net for the derivation of a model-corrected blood input function (MCIF) with PV corrections. The developed 3D U-Net and RNN was trained and validated using a 5-fold cross-validation approach on 50 human brain FDG PET datasets. The ICA-net achieved an average Dice score of 82.18% and an Intersection over Union of 68.54% across all tested scans. Furthermore, the MCIF-net exhibited a minimal root mean squared error of 0.0052. The application of this pipeline to ground truth data for dFDG-PET brain scans resulted in the precise localization of seizure onset regions, which contributed to a successful clinical outcome, with the patient achieving a seizure-free state after treatment. These results underscore the efficacy of the ICA-net and MCIF-net deep learning pipeline in learning the ICA structure's distribution and automating MCIF computation with PV corrections. This advancement marks a significant leap in non-invasive neuroimaging.

There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created. To develop AI agents that can sense, think, and act as flexibly as humans in real-world settings, it is imperative to bridge the realism gap between the digital and physical worlds. How can we embody agents in an environment as rich and diverse as the one we inhabit, without the constraints imposed by real hardware and control? Towards this end, we introduce V-IRL: a platform that enables agents to scalably interact with the real world in a virtual yet realistic environment. Our platform serves as a playground for developing agents that can accomplish various practical tasks and as a vast testbed for measuring progress in capabilities spanning perception, decision-making, and interaction with real-world data across the entire globe.

The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech. In this work, we explore meta-earning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection. We propose a joint embedding architecture that incorporates the input's label and definition for classification via Prototypical Network. Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets. Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.

One of the challenges of natural language understanding is to deal with the subjectivity of sentences, which may express opinions and emotions that add layers of complexity and nuance. Sentiment analysis is a field that aims to extract and analyze these subjective elements from text, and it can be applied at different levels of granularity, such as document, paragraph, sentence, or aspect. Aspect-based sentiment analysis is a well-studied topic with many available data sets and models. However, there is no clear definition of what makes a sentence difficult for aspect-based sentiment analysis. In this paper, we explore this question by conducting an experiment with three data sets: "Laptops", "Restaurants", and "MTSC" (Multi-Target-dependent Sentiment Classification), and a merged version of these three datasets. We study the impact of domain diversity and syntactic diversity on difficulty. We use a combination of classifiers to identify the most difficult sentences and analyze their characteristics. We employ two ways of defining sentence difficulty. The first one is binary and labels a sentence as difficult if the classifiers fail to correctly predict the sentiment polarity. The second one is a six-level scale based on how many of the top five best-performing classifiers can correctly predict the sentiment polarity. We also define 9 linguistic features that, combined, aim at estimating the difficulty at sentence level.

Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications. The existing methodologies in the field primarily concentrate on constructing models that capture the relationship between utility function values and subsets within their respective supersets. However, these approaches tend to overlook the valuable information contained within the superset when utilizing neural networks to model set functions. In this work, we address this oversight by adopting a probabilistic perspective. Our theoretical findings demonstrate that when the target value is conditioned on both the input set and subset, it is essential to incorporate an \textit{invariant sufficient statistic} of the superset into the subset of interest for effective learning. This ensures that the output value remains invariant to permutations of the subset and its corresponding superset, enabling identification of the specific superset from which the subset originated. Motivated by these insights, we propose a simple yet effective information aggregation module designed to merge the representations of subsets and supersets from a permutation invariance perspective. Comprehensive empirical evaluations across diverse tasks and datasets validate the enhanced efficacy of our approach over conventional methods, underscoring the practicality and potency of our proposed strategies in real-world contexts.