Although great progress has been made by previous table understanding methods including recent approaches based on large language models (LLMs), they rely heavily on the premise that given tables must be converted into a certain text sequence (such as Markdown or HTML) to serve as model input. However, it is difficult to access such high-quality textual table representations in some real-world scenarios, and table images are much more accessible. Therefore, how to directly understand tables using intuitive visual information is a crucial and urgent challenge for developing more practical applications. In this paper, we propose a new problem, multimodal table understanding, where the model needs to generate correct responses to various table-related requests based on the given table image. To facilitate both the model training and evaluation, we construct a large-scale dataset named MMTab, which covers a wide spectrum of table images, instructions and tasks. On this basis, we develop Table-LLaVA, a generalist tabular multimodal large language model (MLLM), which significantly outperforms recent open-source MLLM baselines on 23 benchmarks under held-in and held-out settings. The code and data is available at this https://github.com/SpursGoZmy/Table-LLaVA

In swarm robotics, confrontation including the pursuit-evasion game is a key scenario. High uncertainty caused by unknown opponents' strategies and dynamic obstacles complicates the action space into a hybrid decision process. Although the deep reinforcement learning method is significant for swarm confrontation since it can handle various sizes, as an end-to-end implementation, it cannot deal with the hybrid process. Here, we propose a novel hierarchical reinforcement learning approach consisting of a target allocation layer, a path planning layer, and the underlying dynamic interaction mechanism between the two layers, which indicates the quantified uncertainty. It decouples the hybrid process into discrete allocation and continuous planning layers, with a probabilistic ensemble model to quantify the uncertainty and regulate the interaction frequency adaptively. Furthermore, to overcome the unstable training process introduced by the two layers, we design an integration training method including pre-training and cross-training, which enhances the training efficiency and stability. Experiment results in both comparison and ablation studies validate the effectiveness and generalization performance of our proposed approach.

Social media users express their political preferences via interaction with other users, by spontaneous declarations or by participation in communities within the network. This makes a social network such as Twitter a valuable data source to study computational science approaches to political learning inference. In this work we focus on three diverse regions in Spain (Basque Country, Catalonia and Galicia) to explore various methods for multi-party categorization, required to analyze evolving and complex political landscapes, and compare it with binary left-right approaches. We use a two-step method involving unsupervised user representations obtained from the retweets and their subsequent use for political leaning detection. Comprehensive experimentation on a newly collected and curated dataset comprising labeled users and their interactions demonstrate the effectiveness of using Relational Embeddings as representation method for political ideology detection in both binary and multi-party frameworks, even with limited training data. Finally, data visualization illustrates the ability of the Relational Embeddings to capture intricate intra-group and inter-group political affinities.

Can humans and artificial intelligences share concepts and communicate? 'Making AI Intelligible' shows that philosophical work on the metaphysics of meaning can help answer these questions. Herman Cappelen and Josh Dever use the externalist tradition in philosophy to create models of how AIs and humans can understand each other. In doing so, they illustrate ways in which that philosophical tradition can be improved. The questions addressed in the book are not only theoretically interesting, but the answers have pressing practical implications. Many important decisions about human life are now influenced by AI. In giving that power to AI, we presuppose that AIs can track features of the world that we care about (for example, creditworthiness, recidivism, cancer, and combatants). If AIs can share our concepts, that will go some way towards justifying this reliance on AI. This ground-breaking study offers insight into how to take some first steps towards achieving Interpretable AI.

Cyber-physical production systems consist of highly specialized software and hardware components. Most components and communication protocols are not built according to the Secure by Design principle. Therefore, their resilience to cyberattacks is limited. This limitation can be overcome with common operational pictures generated by security monitoring solutions. These pictures provide information about communication relationships of both attacked and non-attacked devices, and serve as a decision-making basis for security officers in the event of cyberattacks. The objective of these decisions is to isolate a limited number of devices rather than shutting down the entire production system. In this work, we propose and evaluate a concept for finding the devices to isolate. Our approach is based on solving the Critical Node Cut Problem with Vulnerable Vertices (CNP-V) - an NP-hard computational problem originally motivated by isolating vulnerable people in case of a pandemic. To the best of our knowledge, this is the first work on applying CNP-V in context of cybersecurity.

Generative AI offers a simple, prompt-based alternative to fine-tuning smaller BERT-style LLMs for text classification tasks. This promises to eliminate the need for manually labeled training data and task-specific model training. However, it remains an open question whether tools like ChatGPT can deliver on this promise. In this paper, we show that smaller, fine-tuned LLMs (still) consistently and significantly outperform larger, zero-shot prompted models in text classification. We compare three major generative AI models (ChatGPT with GPT-3.5/GPT-4 and Claude Opus) with several fine-tuned LLMs across a diverse set of classification tasks (sentiment, approval/disapproval, emotions, party positions) and text categories (news, tweets, speeches). We find that fine-tuning with application-specific training data achieves superior performance in all cases. To make this approach more accessible to a broader audience, we provide an easy-to-use toolkit alongside this paper. Our toolkit, accompanied by non-technical step-by-step guidance, enables users to select and fine-tune BERT-like LLMs for any classification task with minimal technical and computational effort.

We introduce transformation-dependent adversarial attacks, a new class of threats where a single additive perturbation can trigger diverse, controllable mis-predictions by systematically transforming the input (e.g., scaling, blurring, compression). Unlike traditional attacks with static effects, our perturbations embed metamorphic properties to enable different adversarial attacks as a function of the transformation parameters. We demonstrate the transformation-dependent vulnerability across models (e.g., convolutional networks and vision transformers) and vision tasks (e.g., image classification and object detection). Our proposed geometric and photometric transformations enable a range of targeted errors from one crafted input (e.g., higher than 90% attack success rate for classifiers). We analyze effects of model architecture and type/variety of transformations on attack effectiveness. This work forces a paradigm shift by redefining adversarial inputs as dynamic, controllable threats. We highlight the need for robust defenses against such multifaceted, chameleon-like perturbations that current techniques are ill-prepared for.

Network data is ubiquitous in many disciplines and application domains, including computer science, statistics, biology, and physics. These data, encoding relationships between units represented as nodes, are often accompanied by additional information about the nodes, usually referred to as node covariates, attributes, or metadata (Newman and Clauset, 2016; Liu, 2019; Chunaev, 2020). In these situations, a common goal is to understand the associations between the network connectivity and the node covariates. In our example, we consider international food commodity trade data represented as a network, where the nodes correspond to different countries and edge weights encode food commodity trade volumes between corresponding countries. The covariates at each node consist of economic and geographic information for each country, such as gross domestic product (GDP) per capita, birth rate and region. We wish to exploit that both datasets contain information about the nodes in order to better understand the structure of the network, node covariates and their relationship. Specifically, we seek to understand how economic and geographic factors explain the observed trade between countries, and identify additional information in the network that cannot be explained solely by these variables. There has been substantial work that incorporates network and node covariate information. Some examples include methods that use node covariates to improve community detection (Binkiewicz et al., 2017; Huang et al., 2023), dimensionality reduction (Zhao et al., 2022), regression with network information (Li et al., 2019) and mixed effect models for network edges (Hoff, 2005).

Elon Musk dropped a lawsuit against OpenAI one day before a judge in California state court was set to hear OpenAI's request for dismissal. Musk's suit, which was filed in February, had accused OpenAI co-founders Sam Altman and Greg Brockman of violating the company's non-profit status and instead prioritizing profits over using AI to help humanity. In the 35-page suit, Musk had alleged that OpenAI had become a "closed-source de facto subsidiary" of Microsoft, which invested 13 billion in the company and owns a 49 percent stake. Microsoft uses OpenAI's technology to power Copilot, the company's generative AI tools that are deeply integrated in products like Windows and Office. OpenAI had reportedly requested for the lawsuit to be dismissed, arguing that Musk would use any information that emerged as a result to get access to the company's "proprietary records and technology."

As the United Kingdom heads toward its elections next month, the country is seeing its first instance of a new kind of politician: an AI candidate. AI Steve, an avatar of real-life Steven Endacott, a Brighton-based businessman, is running for Parliament as an Independent. Voters will be able to cast their ballots for AI Steve, as well as ask policy positions or raise issues of their own. AI Steve will then incorporate suggestions and requests into its platform. Endacott will be the in-person representative attending meetings and parliamentary sessions on behalf of AI Steve.