Event prediction in the continuous-time domain is a crucial but rather difficult task. Temporal point process (TPP) learning models have shown great advantages in this area. Existing models mainly focus on encoding global contexts of events using techniques like recurrent neural networks (RNNs) or self-attention mechanisms. However, local event contexts also play an important role in the occurrences of events, which has been largely ignored. Popular convolutional neural networks, which are designated for local context capturing, have never been applied to TPP modelling due to their incapability of modelling in continuous time. In this work, we propose a novel TPP modelling approach that combines local and global contexts by integrating a continuous-time convolutional event encoder with an RNN. The presented framework is flexible and scalable to handle large datasets with long sequences and complex latent patterns. The experimental result shows that the proposed model improves the performance of probabilistic sequential modelling and the accuracy of event prediction. To our best knowledge, this is the first work that applies convolutional neural networks to TPP modelling.

Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for sufficiently large models (beyond 50B parameters). We show that orders-of-magnitude smaller models (125M -- 1.3B parameters) can still benefit from chain-of-thought prompting. To achieve this, we introduce Symbolic Chain-of-Thought Distillation (SCoTD), a method to train a smaller student model on rationalizations sampled from a significantly larger teacher model. Experiments across several commonsense benchmarks show that: 1) SCoTD enhances the performance of the student model in both supervised and few-shot settings, and especially for challenge sets; 2) sampling many reasoning chains per instance from the teacher is paramount; and 3) after distillation, student chain-of-thoughts are judged by humans as comparable to the teacher, despite orders of magnitude fewer parameters. We test several hypotheses regarding what properties of chain-of-thought samples are important, e.g., diversity vs. teacher likelihood vs. open-endedness. We release our corpus of chain-of-thought samples and code.

The COVID-19 Infodemic had an unprecedented impact on health behaviors and outcomes at a global scale. While many studies have focused on a qualitative and quantitative understanding of misinformation, including sentiment analysis, there is a gap in understanding the emotion-carriers of misinformation and their differences across geographies. In this study, we characterized emotion carriers and their impact on vaccination rates in India and the United States. A manually labelled dataset was created from 2.3 million tweets and collated with three publicly available datasets (CoAID, AntiVax, CMU) to train deep learning models for misinformation classification. Misinformation labelled tweets were further analyzed for behavioral aspects by leveraging Plutchik Transformers to determine the emotion for each tweet. Time series analysis was conducted to study the impact of misinformation on spatial and temporal characteristics. Further, categorical classification was performed using transformer models to assign categories for the misinformation tweets. Word2Vec+BiLSTM was the best model for misinformation classification, with an F1-score of 0.92. The US had the highest proportion of misinformation tweets (58.02%), followed by the UK (10.38%) and India (7.33%). Disgust, anticipation, and anger were associated with an increased prevalence of misinformation tweets. Disgust was the predominant emotion associated with misinformation tweets in the US, while anticipation was the predominant emotion in India. For India, the misinformation rate exhibited a lead relationship with vaccination, while in the US it lagged behind vaccination. Our study deciphered that emotions acted as differential carriers of misinformation across geography and time. These carriers can be monitored to develop strategic interventions for countering misinformation, leading to improved public health.

The exploration of sentiment analysis in low-resource languages, such as Marathi, has been limited due to the availability of suitable datasets. In this work, we present L3Cube-MahaSent-MD, a multi-domain Marathi sentiment analysis dataset, with four different domains - movie reviews, general tweets, TV show subtitles, and political tweets. The dataset consists of around 60,000 manually tagged samples covering 3 distinct sentiments - positive, negative, and neutral. We create a sub-dataset for each domain comprising 15k samples. The MahaSent-MD is the first comprehensive multi-domain sentiment analysis dataset within the Indic sentiment landscape. We fine-tune different monolingual and multilingual BERT models on these datasets and report the best accuracy with the MahaBERT model. We also present an extensive in-domain and cross-domain analysis thus highlighting the need for low-resource multi-domain datasets. The data and models are available at https://github.com/l3cube-pune/MarathiNLP .

Most feature-based stereo visual odometry (SVO) approaches estimate the motion of mobile robots by matching and tracking point features along a sequence of stereo images. However, in dynamic scenes mainly comprising moving pedestrians, vehicles, etc., there are insufficient robust static point features to enable accurate motion estimation, causing failures when reconstructing robotic motion. In this paper, we proposed DynPL-SVO, a complete dynamic SVO method that integrated united cost functions containing information between matched point features and re-projection errors perpendicular and parallel to the direction of the line features. Additionally, we introduced a \textit{dynamic} \textit{grid} algorithm to enhance its performance in dynamic scenes. The stereo camera motion was estimated through Levenberg-Marquard minimization of the re-projection errors of both point and line features. Comprehensive experimental results on KITTI and EuRoC MAV datasets showed that accuracy of the DynPL-SVO was improved by over 20\% on average compared to other state-of-the-art SVO systems, especially in dynamic scenes.

Amazon has announced that Prime Day 2023 will begin on July 11th, but you don't have to wait until then to get a good deal. The company has started to roll out a few early Prime Day deals before the two-day shopping event officially commences, including, as expected, several discounts on its own devices and services. We've rounded up the best early access Prime Day deals we can find below. Remember that you'll need to subscribe to Prime to take advantage of many (but not all) of the offers, and that there's always a chance that prices drop lower during the event itself. For those with no interest in Prime, we've also included a few of the best tech deals from this week that aren't explicitly tied to the event.

Fake news is a complex problem and can span text, images and video. For written articles in particular, there are several ways of generating fake news. A fake news article could be produced by selectively editing facts, including people's names, dates or statistics. An article could also be completely fabricated with made-up events or people. Fake news articles can also be machine-generated as advances in artificial intelligence make it particularly easy to generate misinformation.

Like many fans this week, you may have noticed something odd about the opening credits of Secret Invasion, Marvel's new show. Amidst all the Skrull green, there is something very … Midjourney about the whole thing. If you got that sense, you weren't wrong: Those credits were made with the help of artificial intelligence. The idea, Secret Invasion's executive producer Ali Selim told Polygon this week, was to make something that reflected the show's theme of aliens hiding among us. "When we reached out to the AI vendors, that was part of it--it just came right out of shape-shifting, Skrull-world identity, you know? Who is this?" Selim said.

But Apple's splashy entry has revived interest--and challenged the way that one-time undisputed king of the metaverse, Mark Zuckerberg, is pursuing mixed reality. Other players in the field will choose between these paths.

Artificial intelligence is either going to save humanity or finish it off, depending on who you speak to. Either way, every week there are new developments and breakthroughs. The Wimbledon tennis tournament revealed it will be introducing AI-generated audio and text commentary in its online highlights this year. The All England Club has teamed up with the tech group IBM to provide automatically created voiceovers and captions for its footage. The move, which is separate to the BBC's coverage of the tournament, follows use of the cloned voice of a British athletics commentator, Hannah England, for online coverage of the European Athletics Championships.