This resource page will be updated periodically prior to the event. Over the past five years, the community has made significant advances in neuro symbolic reasoning (NSR). These NSR frameworks are now capable of embedding prior knowledge in deep learning architectures, guiding the learning process with logical constraints, providing symbolic explainability, and using gradient-based approaches to learn logical statements. At this time, several approaches are seeing usage in various application areas. This tutorial is designed for researchers looking to understand the current landscape of NSR research as well as those looking to apply NSR research in areas such as natural language processing and verification.

Tehran, Iran – Iran's army has unveiled a major underground base to showcase its aerial military capabilities in response to significant joint exercises by the United States and Israel. State television on Tuesday showed footage of a variety of fighter jets and military drones at the base, dubbed the "Eagle 44", the location of which remains unknown. It said the base is dug in the mountains to protect it from ammunition dropped from US strategic bombers that are capable of penetrating defences. The unveiling, which was attended by top military officials, comes less than two weeks after the US and Israel held their largest-ever joint drill, using thousands of troops and dozens of aircraft in addition to naval vessels and artillery systems in what was widely seen as a message to Iran amid rising tensions. That joint drill had in turn come days after Iran held wide-ranging exercises to showcase its military readiness.

Back before he retired, Naval War College professor and contributor to The Atlantic Tom Nichols published a 2017 book called The Death of Expertise. Those who claim their own facts or knowledge without supporting evidence, he noted, have become more and more prominent in online conversation we've been having. And the noisiest and most prone to online pyrotechnics and bomb throwing have been getting the most attention. As a result, the quieter voices from those who know how to build a balanced consensus–using mutually agreed-upon facts–and have expertise in areas that have a direct and immediate impact on society are being drowned out. Here's a recent example of how those with expertise seem to have less clout now than they used to.

TAIPEI – Taiwan will speed up development of drones for military use, taking into account the lessons of the war in Ukraine and the threat posed by China, the island's defense ministry said Tuesday. Unmanned aircraft have played a crucial role on both sides since Russia launched a full-scale invasion of Ukraine in February last year. Ukraine's defense minister has said that he regards drones as the future of modern warfare. Taiwan, which is facing a growing threat from China to use force to bring it under Beijing's control, has repeatedly said it is closely watching the war and learning lessons it could apply to fight off a Chinese attack, including how Ukraine has resisted a numerically-superior force. This could be due to a conflict with your ad-blocking or security software.

This paper scrutinizes a database of over 4900 YouTube videos to characterize financial market coverage. Financial market coverage generates a large number of videos. Therefore, watching these videos to derive actionable insights could be challenging and complex. In this paper, we leverage Whisper, a speech-to-text model from OpenAI, to generate a text corpus of market coverage videos from Bloomberg and Yahoo Finance. We employ natural language processing to extract insights regarding language use from the market coverage. Moreover, we examine the prominent presence of trending topics and their evolution over time, and the impacts that some individuals and organizations have on the financial market. Our characterization highlights the dynamics of the financial market coverage and provides valuable insights reflecting broad discussions regarding recent financial events and the world economy.

The ongoing rise in cyberattacks and the lack of skilled professionals in the cybersecurity domain to combat these attacks show the need for automated tools capable of detecting an attack with good performance. Attackers disguise their actions and launch attacks that consist of multiple actions, which are difficult to detect. Therefore, improving defensive tools requires their calibration against a well-trained attacker. In this work, we propose a model of an attacking agent and environment and evaluate its performance using basic Q-Learning, Naive Q-learning, and DoubleQ-Learning, all of which are variants of Q-Learning. The attacking agent is trained with the goal of exfiltrating data whereby all the hosts in the network have a non-zero detection probability. Results show that the DoubleQ-Learning agent has the best overall performance rate by successfully achieving the goal in $70\%$ of the interactions.

Significant enthusiasm around AI uptake has been witnessed across societies globally. The electoral process -- the time, place and manner of elections within democratic nations -- has been among those very rare sectors in which AI has not penetrated much. Electoral management bodies in many countries have recently started exploring and deliberating over the use of AI in the electoral process. In this paper, we consider five representative avenues within the core electoral process which have potential for AI usage, and map the challenges involved in using AI within them. These five avenues are: voter list maintenance, determining polling booth locations, polling booth protection processes, voter authentication and video monitoring of elections. Within each of these avenues, we lay down the context, illustrate current or potential usage of AI, and discuss extant or potential ramifications of AI usage, and potential directions for mitigating risks while considering AI usage. We believe that the scant current usage of AI within electoral processes provides a very rare opportunity, that of being able to deliberate on the risks and mitigation possibilities, prior to real and widespread AI deployment. This paper is an attempt to map the horizons of risks and opportunities in using AI within the electoral processes and to help shape the debate around the topic.

Automatic document summarization aims to produce a concise summary covering the input document's salient information. Within a report document, the salient information can be scattered in the textual and non-textual content. However, existing document summarization datasets and methods usually focus on the text and filter out the non-textual content. Missing tabular data can limit produced summaries' informativeness, especially when summaries require covering quantitative descriptions of critical metrics in tables. Existing datasets and methods cannot meet the requirements of summarizing long text and multiple tables in each report. To deal with the scarcity of available data, we propose FINDSum, the first large-scale dataset for long text and multi-table summarization. Built on 21,125 annual reports from 3,794 companies, it has two subsets for summarizing each company's results of operations and liquidity. To summarize the long text and dozens of tables in each report, we present three types of summarization methods. Besides, we propose a set of evaluation metrics to assess the usage of numerical information in produced summaries. Dataset analyses and experimental results indicate the importance of jointly considering input textual and tabular data when summarizing report documents.

In recent years, radiation mapping has attracted widespread research attention and increased public concerns on environmental monitoring. In terms of both materials and their configurations, radiation detectors have been developed to locate the directions and positions of the radiation sources. In this process, algorithm is essential in converting detector signals to radiation source information. However, due to the complex mechanisms of radiation-matter interaction and the current limitation of data collection, high-performance, low-cost radiation mapping is still challenging. Here we present a computational framework using Tetris-inspired detector pixels and machine learning for radiation mapping. Using inter-pixel padding to increase the contrast between pixels and neural network to analyze the detector readings, a detector with as few as four pixels can achieve high-resolution directional mapping. By further imposing Maximum a Posteriori (MAP) with a moving detector, further radiation position localization is achieved. Non-square, Tetris-shaped detector can further improve performance beyond the conventional grid-shaped detector. Our framework offers a new avenue for high quality radiation mapping with least number of detector pixels possible, and is anticipated to be capable to deploy for real-world radiation detection with moderate validation.

Word-level textual adversarial attacks have achieved striking performance in fooling natural language processing models. However, the fundamental questions of why these attacks are effective, and the intrinsic properties of the adversarial examples (AEs), are still not well understood. This work attempts to interpret textual attacks through the lens of $n$-gram frequency. Specifically, it is revealed that existing word-level attacks exhibit a strong tendency toward generation of examples with $n$-gram frequency descend ($n$-FD). Intuitively, this finding suggests a natural way to improve model robustness by training the model on the $n$-FD examples. To verify this idea, we devise a model-agnostic and gradient-free AE generation approach that relies solely on the $n$-gram frequency information, and further integrate it into the recently proposed convex hull framework for adversarial training. Surprisingly, the resultant method performs quite similarly to the original gradient-based method in terms of model robustness. These findings provide a human-understandable perspective for interpreting word-level textual adversarial attacks, and a new direction to improve model robustness.