The wide dissemination of fake news has affected our lives in many aspects, making fake news detection important and attracting increasing attention. Existing approaches make substantial contributions in this field by modeling news from a single-modal or multi-modal perspective. However, these modal-based methods can result in sub-optimal outcomes as they ignore reader behaviors in news consumption and authenticity verification. For instance, they haven't taken into consideration the component-by-component reading process: from the headline, images, comments, to the body, which is essential for modeling news with more granularity. To this end, we propose an approach of Emulating the behaviors of readers (Ember) for fake news detection on social media, incorporating readers' reading and verificating process to model news from the component perspective thoroughly. Specifically, we first construct intra-component feature extractors to emulate the behaviors of semantic analyzing on each component. Then, we design a module that comprises inter-component feature extractors and a sequence-based aggregator. This module mimics the process of verifying the correlation between components and the overall reading and verification sequence. Thus, Ember can handle the news with various components by emulating corresponding sequences. We conduct extensive experiments on nine real-world datasets, and the results demonstrate the superiority of Ember.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

Suleman Dawood, the 19-year-old who died aboard OceanGate's Titan submersible last week, hoped to set the world record for solving a Rubik's Cube in the deep ocean, his mother said Monday. Dawood and his father, Shahzada, had finished the process of applying to the Guinness World Records and entered the submersible equipped with a camera to record the achievement. Christine Dawood and her daughter remained aboard the Polar Prince mother ship while the submersible descended toward the wreck of the Titanic earlier this month, she told the BBC in an interview. Christine spoke of the moment the crew of the Prince informed her they had lost communications with the submersible. "I didn't comprehend at that moment what it meant – and then it just went downhill from there," she said.

Log Off Movement CEO Emma Lembke and teacher Matt Miles discuss the impact of artificial intelligence on kids on'The Story.' More people are turning to dating apps to find a match, but one company is taking it a step further by using artificial intelligence (AI) to fuel a more efficient and personalized version of online dating, according to Lior Baruch, the co-founder and CEO AlgoAI Tech. "Maybe it was a website in the past, now it's an app, but it's kind of the same," Baruch told Fox News Digital of the traditional form of online dating. "You go into a website to type few details about yourself, they ask you a few questions, you answer them. You get either one, two, three options, or you see tons of options in front of you that you just choose from, like it's kind of a meat market. If you're not, people can stay there for years and I'm not exaggerating."

In 1979, when Steven Spielberg and George Lucas signed with Paramount Pictures to develop a film series based on classic Hollywood adventure serials, the deal they struck was to make five separate movies. The first, Raiders of the Lost Ark, was released in the summer of 1981 and became that year's top-grossing movie, beating even the long-anticipated Superman II and remaining on screens in some cities for more than a year. By 1984, it was Raiders' sequel, Indiana Jones and the Temple of Doom, that had become the year's most anticipated movie, banking that year's biggest opening weekend, and the third entry in the franchise, Indiana Jones and the Last Crusade, became not only the highest-grossing movie of 1989 but the top-earning Indiana Jones movie yet. Given that track record, and viewed from the perspective of our own IP-crazed times, it seems inconceivable that Spielberg and Lucas decided not to move forward immediately with a fourth Indiana Jones picture (though Lucas did go on to produce a spinoff TV series, The Young Indiana Jones Chronicles). Lucas' idea, a riff on the 1950s sci-fi films that would have been contemporaneous with a middle-aged Indy, was to introduce extraterrestrial beings into the previously earthbound Raiders universe.

Recent advances in computer vision and deep learning have influenced the field of sports performance analysis for researchers to track and reconstruct freely moving humans without any marker attachment. However, there are few works for vision-based motion capture and intelligent analysis for professional TaiChi movement. In this paper, we propose a framework for TaiChi performance capture and analysis with multi-view geometry and artificial intelligence technology. The main innovative work is as follows: 1) A multi-camera system suitable for TaiChi motion capture is built and the multi-view TaiChi data is collected and processed; 2) A combination of traditional visual method and implicit neural radiance field is proposed to achieve sparse 3D skeleton fusion and dense 3D surface reconstruction. 3) The normalization modeling of movement sequences is carried out based on motion transfer, so as to realize TaiChi performance analysis for different groups. We have carried out evaluation experiments, and the experimental results have shown the efficiency of our method.

Current methods for generating attractive headlines often learn directly from data, which bases attractiveness on the number of user clicks and views. Although clicks or views do reflect user interest, they can fail to reveal how much interest is raised by the writing style and how much is due to the event or topic itself. Also, such approaches can lead to harmful inventions by over-exaggerating the content, aggravating the spread of false information. In this work, we propose HonestBait, a novel framework for solving these issues from another aspect: generating headlines using forward references (FRs), a writing technique often used for clickbait. A self-verification process is included during training to avoid spurious inventions. We begin with a preliminary user study to understand how FRs affect user interest, after which we present PANCO1, an innovative dataset containing pairs of fake news with verified news for attractive but faithful news headline generation. Automatic metrics and human evaluations show that our framework yields more attractive results (+11.25% compared to human-written verified news headlines) while maintaining high veracity, which helps promote real information to fight against fake news.

The field of neuromorphic computing is rapidly evolving. As both biological accuracy and practical implementations are explored, existing architectures are modified and improved for both purposes. The Temporal Neural Network(TNN) style of architecture is a good basis for approximating biological neurons due to its use of timed pulses to encode data and a voltage-threshold-like system. Using the Temporal Neural Network cortical column C3S architecture design as a basis, this project seeks to augment the network's design. This project takes note of two ideas and presents their designs with the goal of improving existing cortical column architecture. One need in this field is for an encoder that could convert between common digital formats and timed neuronal spikes, as biologically accurate networks are temporal in nature. To this end, this project presents an encoder to translate between binary encoded values and timed spikes to be processed by the neural network. Another need is for the reduction of wasted processing time to idleness, caused by lengthy Gamma cycle processing bursts. To this end, this project presents a relaxation of Gamma cycles to allow for them to end arbitrarily early once the network has determined an output response. With the goal of contributing to the betterment of the field of neuromorphic computer architecture, designs for both a binary-to-spike encoder, as well as a Gamma cycle controller, are presented and evaluated for optimal design parameters, with overall system gain and performance.

Fake news detection has been a critical task for maintaining the health of the online news ecosystem. However, very few existing works consider the temporal shift issue caused by the rapidly-evolving nature of news data in practice, resulting in significant performance degradation when training on past data and testing on future data. In this paper, we observe that the appearances of news events on the same topic may display discernible patterns over time, and posit that such patterns can assist in selecting training instances that could make the model adapt better to future data. Specifically, we design an effective framework FTT (Forecasting Temporal Trends), which could forecast the temporal distribution patterns of news data and then guide the detector to fast adapt to future distribution. Experiments on the real-world temporally split dataset demonstrate the superiority of our proposed framework. The code is available at https://github.com/ICTMCG/FTT-ACL23.

Maximum Inner Product Search (MIPS) is a ubiquitous task in machine learning applications such as recommendation systems. Given a query vector and $n$ atom vectors in $d$-dimensional space, the goal of MIPS is to find the atom that has the highest inner product with the query vector. Existing MIPS algorithms scale at least as $O(\sqrt{d})$, which becomes computationally prohibitive in high-dimensional settings. In this work, we present BanditMIPS, a novel randomized MIPS algorithm whose complexity is independent of $d$. BanditMIPS estimates the inner product for each atom by subsampling coordinates and adaptively evaluates more coordinates for more promising atoms. The specific adaptive sampling strategy is motivated by multi-armed bandits. We provide theoretical guarantees that BanditMIPS returns the correct answer with high probability, while improving the complexity in $d$ from $O(\sqrt{d})$ to $O(1)$. We also perform experiments on four synthetic and real-world datasets and demonstrate that BanditMIPS outperforms prior state-of-the-art algorithms. For example, in the Movie Lens dataset ($n$=4,000, $d$=6,000), BanditMIPS is 20$\times$ faster than the next best algorithm while returning the same answer. BanditMIPS requires no preprocessing of the data and includes a hyperparameter that practitioners may use to trade off accuracy and runtime. We also propose a variant of our algorithm, named BanditMIPS-$\alpha$, which achieves further speedups by employing non-uniform sampling across coordinates. Finally, we demonstrate how known preprocessing techniques can be used to further accelerate BanditMIPS, and discuss applications to Matching Pursuit and Fourier analysis.