On October 3, renowned South Korean illustrator Kim Jung Gi passed away unexpectedly at the age of 47. He was beloved for his innovative ink-and-brushwork style of manhwa, or Korean comic-book art, and famous for captivating audiences by live-drawing huge, intricate scenes from memory. Just days afterward, a former French game developer, known online as 5you, fed Jung Gi's work into an AI model. He shared the model on Twitter as an homage to the artist, allowing any user to create Jung Gi-style art with a simple text prompt. The artworks showed dystopian battlefields and bustling food markets -- eerily accurate in style, and, apart from some telltale warping, as detailed as Jung Gi's own creations.

Proposing scoring functions to effectively understand, analyze and learn various properties of high dimensional hidden representations of large-scale transformer models like BERT can be a challenging task. In this work, we explore a new direction by studying the topological features of BERT hidden representations using persistent homology (PH). We propose a novel scoring function named "persistence scoring function (PSF)" which: (i) accurately captures the homology of the high-dimensional hidden representations and correlates well with the test set accuracy of a wide range of datasets and outperforms existing scoring metrics, (ii) captures interesting post fine-tuning "per-class" level properties from both qualitative and quantitative viewpoints, (iii) is more stable to perturbations as compared to the baseline functions, which makes it a very robust proxy, and (iv) finally, also serves as a predictor of the attack success rates for a wide category of black-box and white-box adversarial attack methods. Our extensive correlation experiments demonstrate the practical utility of PSF on various NLP tasks relevant to BERT.

In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples. In order to tackle compositional generalization across tasks, our model performs disentangled representation learning by introducing a conditional prior for the latent content space and another conditional prior for the latent label space. Both types of priors satisfy a novel property called $\epsilon$-disentangled. We show both empirically and theoretically that the novel priors can disentangle representations even without specific regularizations as in the prior work. The content prior enables directly sampling diverse content representations from the content space learned from the seen tasks, and fuse them with the representations of novel tasks for generating semantically diverse texts in the low-resource settings. Our extensive experiments demonstrate the superior performance of our model over competitive baselines in terms of i) data augmentation in continuous zero/few-shot learning, and ii) text style transfer in the few-shot setting.

Relation Extraction (RE) is a fundamental task of information extraction, which has attracted a large amount of research attention. Previous studies focus on extracting the relations within a sentence or document, while currently researchers begin to explore cross-document RE. However, current cross-document RE methods directly utilize text snippets surrounding target entities in multiple given documents, which brings considerable noisy and non-relevant sentences. Moreover, they utilize all the text paths in a document bag in a coarse-grained way, without considering the connections between these text paths.In this paper, we aim to address both of these shortages and push the state-of-the-art for cross-document RE. First, we focus on input construction for our RE model and propose an entity-based document-context filter to retain useful information in the given documents by using the bridge entities in the text paths. Second, we propose a cross-document RE model based on cross-path entity relation attention, which allow the entity relations across text paths to interact with each other. We compare our cross-document RE method with the state-of-the-art methods in the dataset CodRED. Our method outperforms them by at least 10% in F1, thus demonstrating its effectiveness.

ABSTRACT Micro-mobility is promising to contribute to sustainable cities in the future with its efficiency and low cost. To better design such a sustainable future, it is necessary to understand the trends and challenges. Thus, we examined people's opinions on micro-mobility in the US and the EU using Tweets. We used topic modeling based on advanced natural language processing techniques and categorized the data into seven topics: promotion and service, mobility, technical features, acceptance, recreation, infrastructure and regulations. Furthermore, using sentiment analysis, we investigated people's positive and negative attitudes towards specific aspects of these topics and compared the patterns of the trends and challenges in the US and the EU. We found that 1) promotion and service included the majority of Twitter discussions in the both regions, 2) the EU had more positive opinions than the US, 3) micro-mobility devices were more widely used for utilitarian mobility and recreational purposes in the EU than in the US, and 4) compared to the EU, people in the US had many more concerns related to infrastructure and regulation issues. These findings help us understand the trends and challenges and prioritize different aspects in micro-mobility to improve their safety and experience across the two areas for designing a more sustainable micro-mobility future. INTRODUCTION The growth of transportation has raised the need for compact, flexible, and more sustainable forms of transportation. Recent developments in the micro-mobility industry show that these devices might address this issue and offer people safer and cheaper trips with reduced travel time. According to the Society of Automotive Engineers (SAE) definition (Society of Automotive Engineers, 2019), micro-mobility refers to a range of small, less than 500 pounds (227 kg) lightweight, fully motorized or motor-assisted devices operating at a speed below 30 mph (48 km/h) and ideal for trips up to 10 km. Typical examples include e-bikes, e-scooters, e-unicycles and e-skateboards, and some of them are widely used as personal or shared transportation devices (Price, Blackshear, Blount Jr, & Sandt, 2021). The global micro-mobility market has been increasing over the years. According to the NACTO (National Association of City Transportation Officials, 2020), 136 million trips were generated by shared micro-mobility in 2019 in the U.S., which was 60% more than 2018. Thus, micro-mobility devices can be well integrated into the overall urban design process of smart and sustainable transportation in the near future. With the sustainable design and development goal, we should not only consider technical challenges and requirements (e.g., battery and material), but also complement and constrain the design and development process by social, infrastructural, and political schemes for a sustainable future (Jiao, Luo, Malmqvist, Johan, & Summers, 2022).

After plans to break physical barriers with his metaverse initiative, Meta CEO Mark Zuckerberg revealed plans for another globe-spanning artificial intelligence (AI) project earlier this year, this time a universal translation tool unlike any other. At the same time, the company that made itself famous (and notorious) for its social media networks also introduced another AI-powered tool, a virtual assistant. Both of these intelligent applications were intended to have practical use cases in Zuckerberg's metaverse, those were their intended uses but they will also have wider business applications that Meta is all too aware of. AI virtual assistants, of course, are already in wider use by organizations as chatbots to handle basic customer requests and interactions across a variety of digital services– including Meta's own popular platforms like Facebook Messenger, Instagram, and WhatsApp Business. The other, less well-known AI use case(s) is the language and translation exercises that provide alternatives to relying on human translators to provide accurate, expert-quality translations in real-time.

Ethics and Eric Schmidt are rare bedfellows. The former Google/Alphabet CEO/Chairman exudes a sense of predatory self-interest, always making the point that what he wants aligns with what is supposedly good for the United States. He has splashed money on numerous projects, including such artificial intelligence outfits as Rebellion Defense, all the time maintaining uncomfortably close ties to the government advisory circuit. For years, he has been hectoring the Department of Defense to uncritically embrace AI, in other words, machine-learning technology. "You absolutely suck at machine learning," Schmidt boldly told General Raymond Thomas in July 2016, head of US Special Operations Command.

In February 2021, seven Russian poultry-farm workers were reported to have been infected with H5N8 avian influenza. This subtype of bird flu had never been known to infect people before, and the virus's genetic sequence was quickly uploaded to the genetic data repository GISAID. For Colin Carlson, a biologist at Georgetown University in Washington DC, it presented an opportunity. "I immediately thought, 'I want to run this through FluLeap'," he says. FluLeap is a machine-learning algorithm that uses sequence data to classify influenza viruses as either avian or human.

President Joseph Biden's early October decision to impose sweeping export controls aimed at blocking China's access to advanced semiconductors was eerily timed -- a few days before the convention of Chinese Communist Party's 20th national congress. The Chinese response to American truculence, flying in the face of the Party, is defiance. The Communist Party congress, which concluded on Sunday, exuded a sense of national urgency, prioritized security over the economy and focused on looming threats: a tectonic shift in geopolitics, a technology war and an enduring pandemic. During his speech to the Party congress, Xi Jinping, who won his third term as the top leader of the country, mentioned "technology" 40 times, promised to "win the battle of key core technologies," and emphasized innovation and technological self-sufficiency. China has been working over the years to catch up with the United States in advanced technologies, and Beijing established an ambitious "Made in China 2025" program in 2015 to refocus its industries to compete in automation, microchips and self-driving cars.

Sens. Ron Wyden, D-Wash., and Jerry Moran, R-Kan., are encouraged by the Biden administration's response to the huge and growing backlog of government documents that need to be processed so that more of them can be revealed to the public. "The failures of the current classification system make our country both more vulnerable and less transparent--it's a lose-lose proposition," Wyden said in a press release Wednesday. "I'm pleased that the Biden administration is committed to reforming the classification system and investing in new declassification technology. I'll continue watching closely to ensure the White House gets it done and ultimately heeds my call to update the executive order governing classification." The executive order, issued back in 2009, looked to address how the internet has changed the items that need to be processed for classification.