Like many people who saw designer Daniel Voshart's Roman emperor portraits created in Artbreeder and Photoshop, I was impressed with the results. Using the neural-net tool Artbreeder, Photoshop and historical references, I have created photoreal portraits of Roman Emperors. For this project, I have transformed, or restored (cracks, noses, ears etc.) 800 images of busts to make the 54 emperors of The Principate (27 BC to 285 AD). Artbreeder uses a machine learning method called generative adversarial network (GAN) to manipulate images. Voshart tweaked images from Photoshop to Artbreeder and back again until he got what he wanted.

Biased reporting is a major concern in today's society. Misinformation is the most commonly (mis)used buzzword. But the reality is that language itself can be used to manipulate and persuade the casual reader. By objectively analyzing language we avoid the subjective bias found in other approaches. As opposed to subjectively labeling misinformation, our approach is to illuminate how one can be manipulated with exaggerated headlines, revision history, and text of articles.

Monocular visual odometry consists of the estimation of the position of an agent through images of a single camera, and it is applied in autonomous vehicles, medical robots, and augmented reality. However, monocular systems suffer from the scale ambiguity problem due to the lack of depth information in 2D frames. This paper contributes by showing an application of the dense prediction transformer model for scale estimation in monocular visual odometry systems. Experimental results show that the scale drift problem of monocular systems can be reduced through the accurate estimation of the depth map by this model, achieving competitive state-of-the-art performance on a visual odometry benchmark.

News recommendation is one of the most challenging tasks in recommender systems, mainly due to the ephemeral relevance of news to users. As social media, and particularly microblogging applications like Twitter or Weibo, gains popularity as platforms for news dissemination, personalized news recommendation in this context becomes a significant challenge. We revisit news recommendation in the microblogging scenario, by taking into consideration social interactions and observations tracing how the information that is up for recommendation spreads in an underlying network. We propose a deep-learning based approach that is diffusion and influence-aware, called Influence-Graph News Recommender (IGNiteR). It is a content-based deep recommendation model that jointly exploits all the data facets that may impact adoption decisions, namely semantics, diffusion-related features pertaining to local and global influence among users, temporal attractiveness, and timeliness, as well as dynamic user preferences. To represent the news, a multi-level attention-based encoder is used to reveal the different interests of users. This news encoder relies on a CNN for the news content and on an attentive LSTM for the diffusion traces. For the latter, by exploiting previously observed news diffusions (cascades) in the microblogging medium, users are mapped to a latent space that captures potential influence on others or susceptibility of being influenced for news adoptions. Similarly, a time-sensitive user encoder enables us to capture the dynamic preferences of users with an attention-based bidirectional LSTM. We perform extensive experiments on two real-world datasets, showing that IGNiteR outperforms the state-of-the-art deep-learning based news recommendation methods.

Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge sources to simplify the overall task (Dinan et al., 2019), such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate the existing state of open-domain conversation knowledge selection, showing where the existing methodologies regarding data and evaluation are flawed. We then improve on them by proposing a new framework for collecting relevant knowledge, and create an augmented dataset based on the Wizard of Wikipedia (WOW) corpus, which we call WOW++. WOW++ averages 8 relevant knowledge sentences per dialogue context, embracing the inherent ambiguity of open-domain dialogue knowledge selection. We then benchmark various knowledge ranking algorithms on this augmented dataset with both intrinsic evaluation and extrinsic measures of response quality, showing that neural rerankers that use WOW++ can outperform rankers trained on standard datasets.

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.

Welcome to the first post in our multi-part series on how Netflix is developing and using machine learning (ML) to help creators make better media -- from TV shows to trailers to movies to promotional art and so much more. Media is at the heart of Netflix. Through each engagement, media is how we bring our members continued joy. This blog series will take you behind the scenes, showing you how we use the power of machine learning to create stunning media at a global scale. At Netflix, we launch thousands of new TV shows and movies every year for our members across the globe.

I explain Artificial Intelligence terms and news to non-experts. Meta AI's new model make-a-video is out and in a single sentence: it generates videos from text. It's not only able to generate videos, but it's also the new state-of-the-art method, producing higher quality and more coherent videos than ever before! You can see this model as a stable diffusion model for videos. Surely the next step after being able to generate images.

There are numerous machine learning & AI newsletters, below we feature the best. These enable you to keep up with the latest industry news, important developments, etc. AI Business by Unite.AI – This is our bi-weekly newsletter featuring the latest shake-ups, acquisitions, fund raises and more in the business world of AI. Check your inbox or spam folder to confirm your subscription. AI Disruption – Written by our very own Alex McFarland. Artificial intelligence (AI) will disrupt nearly every aspect of society.

Can you relate to this problem? I can't find anything to play on iOS right now. Now don't worry mobile developers--it's not you, it's me. I don't go for puzzle games or narrative titles because I want something more mindless before I sleep, or while I'm on the bus. I just have a different problem: I've played you already.