Subtle periodic signals, such as blood volume pulse and respiration, can be extracted from RGB video, enabling noncontact health monitoring at low cost. Advancements in remote pulse estimation -- or remote photoplethysmography (rPPG) -- are currently driven by deep learning solutions. However, modern approaches are trained and evaluated on benchmark datasets with ground truth from contact-PPG sensors. We present the first non-contrastive unsupervised learning framework for signal regression to mitigate the need for labelled video data. With minimal assumptions of periodicity and finite bandwidth, our approach discovers the blood volume pulse directly from unlabelled videos. We find that encouraging sparse power spectra within normal physiological bandlimits and variance over batches of power spectra is sufficient for learning visual features of periodic signals. We perform the first experiments utilizing unlabelled video data not specifically created for rPPG to train robust pulse rate estimators. Given the limited inductive biases, we successfully applied the same approach to camera-based respiration by changing the bandlimits of the target signal. This shows that the approach is general enough for unsupervised learning of bandlimited quasi-periodic signals from different domains. Furthermore, we show that the framework is effective for finetuning models on unlabelled video from a single subject, allowing for personalized and adaptive signal regressors.

The vast majority of the popular English named entity recognition (NER) datasets contain American or British English data, despite the existence of many global varieties of English. As such, it is unclear whether they generalize for analyzing use of English globally. To test this, we build a newswire dataset, the Worldwide English NER Dataset, to analyze NER model performance on low-resource English variants from around the world. We test widely used NER toolkits and transformer models, including models using the pre-trained contextual models RoBERTa and ELECTRA, on three datasets: a commonly used British English newswire dataset, CoNLL 2003, a more American focused dataset OntoNotes, and our global dataset. All models trained on the CoNLL or OntoNotes datasets experienced significant performance drops-over 10 F1 in some cases-when tested on the Worldwide English dataset. Upon examination of region-specific errors, we observe the greatest performance drops for Oceania and Africa, while Asia and the Middle East had comparatively strong performance. Lastly, we find that a combined model trained on the Worldwide dataset and either CoNLL or OntoNotes lost only 1-2 F1 on both test sets.

The imminent need to interpret the output of a Machine Learning model with counterfactual (CF) explanations - via small perturbations to the input - has been notable in the research community. Although the variety of CF examples is important, the aspect of them being feasible at the same time, does not necessarily apply in their entirety. This work uses different benchmark datasets to examine through the preservation of the logical causal relations of their attributes, whether CF examples can be generated after a small amount of changes to the original input, be feasible and actually useful to the end-user in a real-world case. To achieve this, we used a black box model as a classifier, to distinguish the desired from the input class and a Variational Autoencoder (VAE) to generate feasible CF examples. As an extension, we also extracted two-dimensional manifolds (one for each dataset) that located the majority of the feasible examples, a representation that adequately distinguished them from infeasible ones. For our experimentation we used three commonly used datasets and we managed to generate feasible and at the same time sparse, CF examples that satisfy all possible predefined causal constraints, by confirming their importance with the attributes in a dataset.

Information Extraction (IE) is a transformative process that converts unstructured text data into a structured format by employing entity and relation extraction (RE) methodologies. The identification of the relation between a pair of entities plays a crucial role within this framework. Despite the existence of various techniques for relation extraction, their efficacy heavily relies on access to labeled data and substantial computational resources. In addressing these challenges, Large Language Models (LLMs) emerge as promising solutions; however, they might return hallucinating responses due to their own training data. To overcome these limitations, Retrieved-Augmented Generation-based Relation Extraction (RAG4RE) in this work is proposed, offering a pathway to enhance the performance of relation extraction tasks. This work evaluated the effectiveness of our RAG4RE approach utilizing different LLMs. Through the utilization of established benchmarks, such as TACRED, TACREV, Re-TACRED, and SemEval RE datasets, our aim is to comprehensively evaluate the efficacy of our RAG4RE approach. In particularly, we leverage prominent LLMs including Flan T5, Llama2, and Mistral in our investigation. The results of our study demonstrate that our RAG4RE approach surpasses performance of traditional RE approaches based solely on LLMs, particularly evident in the TACRED dataset and its variations. Furthermore, our approach exhibits remarkable performance compared to previous RE methodologies across both TACRED and TACREV datasets, underscoring its efficacy and potential for advancing RE tasks in natural language processing.

The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquiring new knowledge but also overwriting outdated information into updated ones. To study the ability of language models for these time-dependent dynamics in human language, we introduce a novel task, EvolvingQA, a temporally evolving question-answering benchmark designed for training and evaluating LMs on an evolving Wikipedia database. The construction of EvolvingQA is automated with our pipeline using large language models. We uncover that existing continual learning baselines suffer from updating and removing outdated knowledge. Our analysis suggests that models fail to rectify knowledge due to small weight gradients. In addition, we elucidate that language models particularly struggle to reflect the change of numerical or temporal information. Our work aims to model the dynamic nature of real-world information, suggesting faithful evaluations of the evolution-adaptability of language models.

For decades, Israel and Iran have fought a shadow war across the Middle East, trading attacks by land, sea, air and in cyberspace. A recent round of strikes -- mainly an aerial barrage by Iran against Israel last weekend -- has brought the conflict more clearly into the open and raised fears of a broader war. A retaliatory Israeli strike on an Iranian air base on Friday, however, appeared limited in scope, and analysts said it suggested an effort to pull back from the dangerous cycle and potentially move the war back into the shadows. August 2019: An Israeli airstrike killed two Iranian-trained militants in Syria, a drone set off a blast near a Hezbollah office in Lebanon and an airstrike in Qaim, Iraq, killed a commander of an Iran-backed Iraqi militia. Israel accused Iran at the time of trying to establish an overland arms-supply line through Iraq and northern Syria to Lebanon, and analysts said the strikes were aimed at stopping Iran and signaling to its proxies that Israel would not tolerate a fleet of smart missiles on its borders. January 2020: Israel greeted with satisfaction the assassination of Maj.

Iranian officials said that the Israeli strike on Friday morning was carried out by small exploding drones, a tactic that would follow a well-established pattern in Israeli attacks on Iranian military targets. As Israel has targeted Iranian defense and military officials and infrastructure, small drones -- specifically ones known as quadcopters -- have been a signature of those operations. Quadcopter drones, so named because they have four rotors, have a short flight range and can explode on impact. The drones might have been launched from inside Iran, whose radar systems had not detected unidentified aircraft entering Iranian airspace, Iranian officials said. If the drones were launched within the country, it demonstrates once again Israel's ability to mount clandestine operations in Iranian territory.

Israeli warplanes fired missiles on Iran during a retaliatory strike early Friday morning, one Western official and two Iranian officials said, suggesting that the attack included more advanced firepower than initial reports indicated. It was not immediately clear the types of missiles used, from where they were fired, whether any were intercepted by Iran's defenses or where they landed. The Western official and the Iranian officials requested anonymity to discuss classified information. Previously, Iranian officials said Friday's attack on a military base in central Iran was conducted by small aerial drones, most likely launched from inside Iranian territory. A separate group of small drones, they said soon after the attack, was shot down in the region of Tabriz, roughly 500 miles north of Isfahan.

Two of the biggest deepfake pornography websites have now started blocking people trying to access them from the United Kingdom. The move comes days after the UK government announced plans for a new law that will make creating nonconsensual deepfakes a criminal offense. Nonconsensual deepfake pornography websites and apps that "strip" clothes off of photos have been growing at an alarming rate--causing untold harm to the thousands of women they are used to target. Clare McGlynn, a professor of law at Durham University, says the move is a "hugely significant moment" in the fight against deepfake abuse. "This ends the easy access and the normalization of deepfake sexual abuse material," McGlynn tells WIRED.

Academia's greatest strength lies in its ability to pursue long-term research projects and fundamental studies that push the boundaries of knowledge. The freedom to explore and experiment with bold, cutting-edge theories will lead to discoveries and innovations that serve as the foundation for future innovation. While tools enabled by LFMs are in everybody's pocket, there are many questions that need to be answered about them, since they remain a "black box" in many ways. For example, we know AI models have a propensity to hallucinate, but we still don't fully understand why. Because they are insulated from market forces, universities can chart a future where AI truly benefits the many.