Amid growing concerns over AI's societal risks--ranging from civilizational collapse to misinformation and systemic bias--this study explores the perceptions of AI experts and the general US registered voters on the likelihood and impact of 18 specific AI risks, alongside their policy preferences for managing these risks. While both groups favor international oversight over national or corporate governance, our survey reveals a discrepancy: voters perceive AI risks as both more likely and more impactful than experts, and also advocate for slower AI development. Specifically, our findings indicate that policy interventions may best assuage collective concerns if they attempt to more carefully balance mitigation efforts across all classes of societal-scale risks, effectively nullifying the near-vs-long-term debate over AI risks. More broadly, our results will serve not only to enable more substantive policy discussions for preventing and mitigating AI risks, but also to underscore the challenge of consensus building for effective policy implementation.

Texture, a significant visual attribute in images, has been extensively investigated across various image recognition applications. Convolutional Neural Networks (CNNs), which have been successful in many computer vision tasks, are currently among the best texture analysis approaches. On the other hand, Vision Transformers (ViTs) have been surpassing the performance of CNNs on tasks such as object recognition, causing a paradigm shift in the field. However, ViTs have so far not been scrutinized for texture recognition, hindering a proper appreciation of their potential in this specific setting. For this reason, this work explores various pre-trained ViT architectures when transferred to tasks that rely on textures. We review 21 different ViT variants and perform an extensive evaluation and comparison with CNNs and hand-engineered models on several tasks, such as assessing robustness to changes in texture rotation, scale, and illumination, and distinguishing color textures, material textures, and texture attributes. The goal is to understand the potential and differences among these models when directly applied to texture recognition, using pre-trained ViTs primarily for feature extraction and employing linear classifiers for evaluation. We also evaluate their efficiency, which is one of the main drawbacks in contrast to other methods. Our results show that ViTs generally outperform both CNNs and hand-engineered models, especially when using stronger pre-training and tasks involving in-the-wild textures (images from the internet). We highlight the following promising models: ViT-B with DINO pre-training, BeiTv2, and the Swin architecture, as well as the EfficientFormer as a low-cost alternative. In terms of efficiency, although having a higher number of GFLOPs and parameters, ViT-B and BeiT(v2) can achieve a lower feature extraction time on GPUs compared to ResNet50.

In the contemporary world of AI and data-driven applications, supervised machines often derive their understanding, which they mimic and reproduce, through annotations--typically conveyed in the form of words or labels. However, such annotations are often divorced from or lack contextual information, and as such hold the potential to inadvertently introduce biases when subsequently used for training. This paper introduces SituAnnotate, a novel ontology explicitly crafted for 'situated grounding,' aiming to anchor the ground truth data employed in training AI systems within the contextual and culturally-bound situations from which those ground truths emerge. SituAnnotate offers an ontology-based approach to structured and context-aware data annotation, addressing potential bias issues associated with isolated annotations. Its representational power encompasses situational context, including annotator details, timing, location, remuneration schemes, annotation roles, and more, ensuring semantic richness. Aligned with the foundational Dolce Ultralight ontology, it provides a robust and consistent framework for knowledge representation. As a method to create, query, and compare label-based datasets, SituAnnotate empowers downstream AI systems to undergo training with explicit consideration of context and cultural bias, laying the groundwork for enhanced system interpretability and adaptability, and enabling AI models to align with a multitude of cultural contexts and viewpoints.

During the use of Advanced Driver Assistance Systems (ADAS), drivers can intervene in the active function and take back control due to various reasons. However, the specific reasons for driver-initiated takeovers in naturalistic driving are still not well understood. In order to get more information on the reasons behind these takeovers, a test group study was conducted. There, 17 participants used a predictive longitudinal driving function for their daily commutes and annotated the reasons for their takeovers during active function use. In this paper, the recorded takeovers are analyzed and the different reasons for them are highlighted. The results show that the reasons can be divided into three main categories. The most common category consists of takeovers which aim to adjust the behavior of the ADAS within its Operational Design Domain (ODD) in order to better match the drivers' personal preferences. Other reasons include takeovers due to leaving the ADAS's ODD and corrections of incorrect sensing state information. Using the questionnaire results of the test group study, it was found that the number and frequency of takeovers especially within the ADAS's ODD have a significant negative impact on driver satisfaction. Therefore, the driver satisfaction with the ADAS could be increased by adapting its behavior to the drivers' wishes and thereby lowering the number of takeovers within the ODD. The information contained in the takeover behavior of the drivers could be used as feedback for the ADAS. Finally, it is shown that there are considerable differences in the takeover behavior of different drivers, which shows a need for ADAS individualization.

Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch? Recent works show that Transformers can be Turing-complete in terms of expressivity, but this does not address the learnability objective. This paper puts forward the notion of 'distribution locality' to capture when weak learning is efficiently achievable by regular Transformers, where the locality measures the least number of tokens required in addition to the tokens histogram to correlate nontrivially with the target. As shown experimentally and theoretically under additional assumptions, distributions with high locality cannot be learned efficiently. In particular, syllogisms cannot be composed on long chains. Furthermore, we show that (i) an agnostic scratchpad cannot help to break the locality barrier, (ii) an educated scratchpad can help if it breaks the locality at each step, (iii) a notion of 'inductive scratchpad' can both break the locality and improve the out-of-distribution generalization, e.g., generalizing to almost double input size for some arithmetic tasks.

Woman critically injured in ride'malfunction' 10 hours agoShareBBCOn Sunday tarpaulin was seen around one of the rides, although it is not clear which ride suffered the malfunction A woman in her 40s is in hospital with life-threatening injuries after a funfair ride malfunctioned at a country show in south London, the Met Police has said. The incident happened during Lambeth Country Show in Brockwell Park at about 18:20 BST on Saturday. A man in his 40s is also being treated for "potentially life-threatening injuries", the force said. Lambeth Council said the investigation would "determine the cause of the malfunction". Two other people, a man in his 50s and an 11-year-old girl, were injured in the incident and have since been discharged from hospital, the Met said.

The original version of this story appeared in Quanta Magazine. Imagine you had a friend who gave different answers to the same question, depending on how you asked it. "What's the capital of Peru?" would get one answer, and "Is Lima the capital of Peru?" would get another. You'd probably be a little worried about your friend's mental faculties, and you'd almost certainly find it hard to trust any answer they gave. A generative question, which is open-ended, yields one answer, and a discriminative question, which involves having to choose between options, often yields a different one.

Magnetic resonance imaging (MRI) has significantly benefited from the resurgence of artificial intelligence (AI). By leveraging AI's capabilities in large-scale optimization and pattern recognition, innovative methods are transforming the MRI acquisition workflow, including planning, sequence design, and correction of acquisition artifacts. These emerging algorithms demonstrate substantial potential in enhancing the efficiency and throughput of acquisition steps.

Transparent Displays (TDs) are cutting-edge visual technologies that allow users to see digital content superimposed over physical environments with a variety of applications in dynamic Head-Up Displays (HUDs) in vehicles [1, 2, 3], augmented reality glasses [4, 5, 6], and smart windows in commercial buildings [7]. Their ability to blend digital information with the real world offers significant advancements in fields such as navigation, interactive advertising, robotics [8, 9, 10, 11], and immersive user interfaces and feedback [12, 13, 14, 15, 16]. Imagine a transparent display, such as a dynamic HUD in a vehicle, that not only shows essential metrics like speed, fuel levels, and engine status but also overlays navigational cues directly onto the road ahead, highlighting paths, directions, pedestrians, and other vehicles [2, 1, 17]. Beyond practical utilities, such dynamic HUDs could enhance the journey by identifying points of interest, e.g., service stations, or even serve as platforms for entertainment and work-related activities. However, realizing this vision introduces significant challenges, particularly in tracking the user's gaze across an ever-changing array of widgets and information layers projected onto the transparent display. Moreover, the accurate estimation of gaze depth levels is crucial, especially because of the display's transparency and the potential for the human gaze to interact with or pass through specific widgets, necessitating a system that can precisely discern the focus of a user's attention between virtual overlays and real-world objects to enhance both interactivity and safety [18]. The dynamic nature of this problem, coupled with the need for real-time processing, sets a complex problem space for effectively identifying and monitoring what the user is focusing on at any given moment.

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 28 countries on four continents, covering 26 languages with 11 scripts, providing a total of 9k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.