We introduce Mintaka, a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models. Mintaka is composed of 20,000 question-answer pairs collected in English, annotated with Wikidata entities, and translated into Arabic, French, German, Hindi, Italian, Japanese, Portuguese, and Spanish for a total of 180,000 samples. Mintaka includes 8 types of complex questions, including superlative, intersection, and multi-hop questions, which were naturally elicited from crowd workers. We run baselines over Mintaka, the best of which achieves 38% hits@1 in English and 31% hits@1 multilingually, showing that existing models have room for improvement. We release Mintaka at https://github.com/amazon-research/mintaka.

Traffic congestion is a major urban issue due to its adverse effects on health and the environment, so much so that reducing it has become a priority for urban decision-makers. In this work, we investigate whether a high amount of data on traffic flow throughout a city and the knowledge of the road city network allows an Artificial Intelligence to predict the traffic flux far enough in advance in order to enable emission reduction measures such as those linked to the Low Emission Zone policies. To build a predictive model, we use the city of Valencia traffic sensor system, one of the densest in the world, with nearly 3500 sensors distributed throughout the city. In this work we train and characterize an LSTM (Long Short-Term Memory) Neural Network to predict temporal patterns of traffic in the city using historical data from the years 2016 and 2017. We show that the LSTM is capable of predicting future evolution of the traffic flux in real-time, by extracting patterns out of the measured data.

Unsupervised Domain Adaptation (UDA) methods aim to transfer knowledge from a labeled source domain to an unlabeled target domain. UDA has been extensively studied in the computer vision literature. Deep networks have been shown to be vulnerable to adversarial attacks. However, very little focus is devoted to improving the adversarial robustness of deep UDA models, causing serious concerns about model reliability. Adversarial Training (AT) has been considered to be the most successful adversarial defense approach. Nevertheless, conventional AT requires ground-truth labels to generate adversarial examples and train models, which limits its effectiveness in the unlabeled target domain. In this paper, we aim to explore AT to robustify UDA models: How to enhance the unlabeled data robustness via AT while learning domain-invariant features for UDA? To answer this question, we provide a systematic study into multiple AT variants that can potentially be applied to UDA. Moreover, we propose a novel Adversarially Robust Training method for UDA accordingly, referred to as ARTUDA. Extensive experiments on multiple adversarial attacks and UDA benchmarks show that ARTUDA consistently improves the adversarial robustness of UDA models. Code is available at https://github.com/shaoyuanlo/ARTUDA

The frequency of cyber-attacks continues to be prevalent – 66% of businesses experienced a cyber-attack in 2021 according to Forbes. As cyber threats and attacks grow more sophisticated, so does the technology that prevents them. Many businesses are turning to AI to build up their defenses against the crimes that their industries face. While there are numerous use cases and benefits for implementing artificial intelligence and machine learning technology for cybersecurity, the very same technologies can also be leveraged by criminals for their own gain. AI is powerful but can be used for wrongful actions. It presently assists governments in developing innovative methods of censoring online content.

Yesterday, Meta's AI Research Team announced Make-A-Video, a "state-of-the-art AI system that generates videos from text." We're pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts. Have an idea you want to see? Reply w/ your prompt using #MetaAI and we'll share more results. Like he did for the Stable Diffusion data, Simon Willison created a Datasette browser to explore WebVid-10M, one of the two datasets used to train the video generation model, and quickly learned that all 10.7 million video clips were scraped from Shutterstock, watermarks and all.

Manufacturers of products that make use of artificial intelligence are liable for any eventual damage at all times. In an effort to provide users' rights with better protection, the European Commission is tightening the AI Liability Directive. This summer, the new Meta chatbot became the target of scorn. Just days after Blenderbot 3 of Facebook's parent company launched online in the United States, the self-learning program had degenerated into a racist spreader of fake news. The same thing happened in 2016 with the Tay chatbot developed by Microsoft which was designed to engage in conversations with real people on Twitter.

Role requiring'No experience data provided' months of experience in None Pay if you succeed in getting hired and start work at a high-paying job first. Get Paid to Read Emails, Play Games, Search the Web, $5 Signup Bonus. You can choose to work remotely or in the office. Lingarians earn 500 technology certificates yearly. Refer your friends to receive bonuses.

What's happening: The EU is creating new rules to make it easier to sue AI companies for harm. A bill unveiled last week, which is likely to become law in a couple of years, is part of Europe's push to prevent AI developers from releasing dangerous systems. The details: The goal of the bill is to hold AI companies accountable for potential damage and discrimination caused by their systems by making it easier for consumers to launch EU-wide class actions. The new bill, called the AI Liability Directive, will add teeth to the EU's AI Act, which is set to become EU law around the same time, and would require extra checks for "high risk" uses of AI that have the most potential to harm people, including systems for policing, recruitment, or health care. The response: While tech companies complain it could have a chilling effect on innovation, consumer activists say it doesn't go far enough.

Role requiring'No experience data provided' months of experience in Washington

A scanned lace monitor lizard (Varanus varius) image produced by using new technology. Blue-tongue lizards and sulphur-crested cockatoos are among the native animals frequently smuggled overseas. While the number of live animals seized by the Australian Government has tripled since 2017, the full scale of the problem eludes us as authorities don't often know where and how wildlife is trafficked. Now, we can add a new technology to Australia's arsenal against this cruel and inhumane industry. Our research shows the potential for new technology to detect illegal wildlife in luggage or mail.