Accurately predicting the relevance of items to users is crucial to the success of many social platforms. Conventional approaches train models on logged historical data; but recommendation systems, media services, and online marketplaces all exhibit a constant influx of new content -- making relevancy a moving target, to which standard predictive models are not robust. In this paper, we propose a learning framework for relevance prediction that is robust to changes in the data distribution. Our key observation is that robustness can be obtained by accounting for how users causally perceive the environment. We model users as boundedly-rational decision makers whose causal beliefs are encoded by a causal graph, and show how minimal information regarding the graph can be used to contend with distributional changes. Experiments in multiple settings demonstrate the effectiveness of our approach.

In this paper, we focus on video-to-text summarization and investigate how to best utilize multimodal information for summarizing long inputs (e.g., an hour-long TV show) into long outputs (e.g., a multi-sentence summary). We extend SummScreen (Chen et al., 2021), a dialogue summarization dataset consisting of transcripts of TV episodes with reference summaries, and create a multimodal variant by collecting corresponding full-length videos. We incorporate multimodal information into a pre-trained textual summarizer efficiently using adapter modules augmented with a hierarchical structure while tuning only 3.8\% of model parameters. Our experiments demonstrate that multimodal information offers superior performance over more memory-heavy and fully fine-tuned textual summarization methods.

While there has been substantial progress in developing systems to automate fact-checking, they still lack credibility in the eyes of the users. Thus, an interesting approach has emerged: to perform automatic fact-checking by verifying whether an input claim has been previously fact-checked by professional fact-checkers and to return back an article that explains their decision. This is a sensible approach as people trust manual fact-checking, and as many claims are repeated multiple times. Yet, a major issue when building such systems is the small number of known tweet--verifying article pairs available for training. Here, we aim to bridge this gap by making use of crowd fact-checking, i.e., mining claims in social media for which users have responded with a link to a fact-checking article. In particular, we mine a large-scale collection of 330,000 tweets paired with a corresponding fact-checking article. We further propose an end-to-end framework to learn from this noisy data based on modified self-adaptive training, in a distant supervision scenario. Our experiments on the CLEF'21 CheckThat! test set show improvements over the state of the art by two points absolute. Our code and datasets are available at https://github.com/mhardalov/crowdchecked-claims

A large body of recent work targets semantically conditioned image generation. Most such methods focus on the narrower task of pose transfer and ignore the more challenging task of subject transfer that consists in not only transferring the pose but also the appearance and background. In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details. This is enabled by the Semantic Attention Transformer Encoder that extracts multiple latent vectors for each semantic region, and the corresponding generator that exploits these multiple latents by using semantic cross attention modulation. It is trained only using a reconstruction setup, while subject transfer is performed at test time. Our analysis shows that our proposed architecture is successful at encoding the diversity of appearance in each semantic region. Extensive experiments on the iDesigner and CelebAMask-HD datasets show that SCAM outperforms SEAN and SPADE; moreover, it sets the new state of the art on subject transfer.

A "robot" is a machine that's designed by humans to do a specific job. And the scientists who design and build robots are called "roboticists". Robots do job that people can't do or don't want to do. Like if the job is boring, if it involves doing the same thing over and over or if a job is very dangerous and it means going places where people could get hurt, then robots are used, to do that job. Basically, robot is any automatically operated machine that replaces human effort, though it may resemble humans in appearance or perform functions like humans.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Weeks of teases and vignettes featuring a white rabbit and cryptic messages paid off Saturday night at WWE's Extreme Rules pay-per-view at the Wells Fargo Center in Philadelphia. After Riddle defeated Seth Rollings in the fight pit, WWE announcers Michael Cole and Corey Graves were about to sign off the broadcast when the screen went black and shady characters began to appear in the crowd. "He's got the whole world in his hands," blared over the speakers and characters from Bray Wyatt's Firefly Fun House showed up in the crowd.

US-based multinational Google is collaborating with Saudi Authority for Data and Artificial Intelligence (SADAI) to unveil a global initiative named'Elevate' which will focus on technology, precisely in Artificial Intelligence (AI), to overcome gender inequality. Elevate strives to make women knowledgeable in tech and science by providing free accessibility and training in the sectors and also reduce the gender gap and empowering more than 25,000 women worldwide in the coming 5 years. On the technical track, 30 percent of the program trainees will be data engineers, cloud architects, Ml engineers, and data scientists. Meanwhile, the rest of the 70 percent of the program trainees will be from the non-technical track Cloud Business Enthusiast. According to Princess Haifa Bint Abdul Aziz Al-Muqrin, Saudi Arabia's permanent representative to the UN Educational, Scientific, and Cultural Organization, "Women are underrepresented in the fields of artificial intelligence and technology". "At the moment, when digital technologies are reshaping everyday life, we cannot deny that women are underrepresented in AI and STEM fields in general.

Although James Earl Jones has stepped away from his most iconic role, the legendary "Star Wars" actor's incredible baritone lives on, thanks to a Ukrainian artificial intelligence startup. First reported by Vanity Fair, the 91-year-old actor worked with the Ukrainian firm Respeecher to recreate Vader's instantly recognizable voice for the franchise's recent "Obi-Wan Kenobi" series -- and it was actually the second time Lucasfilm had worked with the company. Using archival soundbites, Respeecher "cloned" both Jones' voice for "Obi-Wan Kenobi" and the younger version of Mark Hamill's early Luke Skywalker for "The Mandalorian" and "The Book of Boba Fett," the report notes. Per those who worked on the Disney series, Earl Jones still provides guidance on the depiction of his infamous character. He has retired as the voice of Darth Vader so here is a young James Earl Jones reciting the alphabet and it's pretty much Oscar worthy.

Machine learning-based computational models have been successfully applied to a broad range of complex information processing tasks, including those that involve retrieving specific data items from large archives. Researchers at the Sony Computer Science Laboratories (CSL) in France have been trying to develop machine learning techniques that could help music producers to easily identify and retrieve specific audio samples from a database. To this end, Stefan Lattner, a researcher at Sony CSL, recently introduced SampleMatch, a machine learning-based model that can automatically retrieve drum samples that match a specific music track from large archives. His model is set to be presented in December at the ISMIR 2022 conference, a leading event that focuses on music information retrieval. "Our music team at Sony CSL is working on AI that could make the life of music producers easier," Stefan Lattner, one of the researchers who carried out the study, told TechXplore.

Graphs emerge in almost every real-world application domain, ranging from online social networks all the way to health data and movie viewership patterns. Typically, such real-world graphs are big and dynamic, in the sense that they evolve over time. Furthermore, graphs usually contain multi-aspect information i.e. in a social network, we can have the "means of communication" between nodes, such as who messages whom, who calls whom, and who comments on whose timeline and so on. How can we model and mine useful patterns, such as communities of nodes in that graph, from such multi-aspect graphs? How can we identify dynamic patterns in those graphs, and how can we deal with streaming data, when the volume of data to be processed is very large? In order to answer those questions, in this thesis, we propose novel tensor-based methods for mining static and dynamic multi-aspect graphs. In general, a tensor is a higher-order generalization of a matrix that can represent high-dimensional multi-aspect data such as time-evolving networks, collaboration networks, and spatio-temporal data like Electroencephalography (EEG) brain measurements. The thesis is organized in two synergistic thrusts: First, we focus on static multi-aspect graphs, where the goal is to identify coherent communities and patterns between nodes by leveraging the tensor structure in the data. Second, as our graphs evolve dynamically, we focus on handling such streaming updates in the data without having to re-compute the decomposition, but incrementally update the existing results.