Contemporary state-of-the-art video object segmentation (VOS) models compare incoming unannotated images to a history of image-mask relations via affinity or cross-attention to predict object masks. We refer to the internal memory state of the initial image-mask pair and past image-masks as a working memory buffer. While the current state of the art models perform very well on clean video data, their reliance on a working memory of previous frames leaves room for error. Affinity-based algorithms include the inductive bias that there is temporal continuity between consecutive frames. To account for inconsistent camera views of the desired object, working memory models need an algorithmic modification that regulates the memory updates and avoid writing irrelevant frames into working memory. A simple algorithmic change is proposed that can be applied to any existing working memory-based VOS model to improve performance on inconsistent views, such as sudden camera cuts, frame interjections, and extreme context changes. The resulting model performances show significant improvement on video data with these frame interjections over the same model without the algorithmic addition. Our contribution is a simple decision function that determines whether working memory should be updated based on the detection of sudden, extreme changes and the assumption that the object is no longer in frame. By implementing algorithmic changes, such as this, we can increase the real-world applicability of current VOS models.

Machine learning (ML) for text classification has been widely used in various domains, such as toxicity detection, chatbot consulting, and review analysis. These applications can significantly impact ethics, economics, and human behavior, raising serious concerns about trusting ML decisions. Several studies indicate that traditional metrics, such as model confidence and accuracy, are insufficient to build human trust in ML models. These models often learn spurious correlations during training and predict based on them during inference. In the real world, where such correlations are absent, their performance can deteriorate significantly. To avoid this, a common practice is to test whether predictions are reasonable. Along with this, a challenge known as the trustworthiness oracle problem has been introduced. Due to the lack of automated trustworthiness oracles, the assessment requires manual validation of the decision process disclosed by explanation methods, which is time-consuming and not scalable. We propose TOKI, the first automated trustworthiness oracle generation method for text classifiers, which automatically checks whether the prediction-contributing words are related to the predicted class using explanation methods and word embeddings. To demonstrate its practical usefulness, we introduce a novel adversarial attack method targeting trustworthiness issues identified by TOKI. We compare TOKI with a naive baseline based solely on model confidence using human-created ground truths of 6,000 predictions. We also compare TOKI-guided adversarial attack method with A2T, a SOTA adversarial attack method. Results show that relying on prediction uncertainty cannot distinguish between trustworthy and untrustworthy predictions, TOKI achieves 142% higher accuracy than the naive baseline, and TOKI-guided adversarial attack method is more effective with fewer perturbations than A2T.

Financial regulators such as central banks collect vast amounts of data, but access to the resulting fine-grained banking microdata is severely restricted by banking secrecy laws. Recent developments have resulted in mechanisms that generate faithful synthetic data, but current evaluation frameworks lack a focus on the specific challenges of banking institutions and microdata. We develop a framework that considers the utility and privacy requirements of regulators, and apply this to financial usage indices, term deposit yield curves, and credit card transition matrices. Using the Central Bank of Paraguay's data, we provide the first implementation of synthetic banking microdata using a central bank's collected information, with the resulting synthetic datasets for all three domain applications being publicly available and featuring information not yet released in statistical disclosure. We find that applications less susceptible to post-processing information loss, which are based on frequency tables, are particularly suited for this approach, and that marginal-based inference mechanisms to outperform generative adversarial network models for these applications. Our results demonstrate that synthetic data generation is a promising privacy-enhancing technology for financial regulators seeking to complement their statistical disclosure, while highlighting the crucial role of evaluating such endeavors in terms of utility and privacy requirements.

To effectively address potential harms from AI systems, it is essential to identify and mitigate system-level hazards. Current analysis approaches focus on individual components of an AI system, like training data or models, in isolation, overlooking hazards from component interactions or how they are situated within a company's development process. To this end, we draw from the established field of system safety, which considers safety as an emergent property of the entire system, not just its components. In this work, we translate System Theoretic Process Analysis (STPA) - a recognized system safety framework - for analyzing AI operation and development processes. We focus on systems that rely on machine learning algorithms and conducted STPA on three case studies involving linear regression, reinforcement learning, and transformer-based generative models. Our analysis explored how STPA's control and system-theoretic perspectives apply to AI systems and whether unique AI traits - such as model opacity, capability uncertainty, and output complexity - necessitate significant modifications to the framework. We find that the key concepts and steps of conducting an STPA readily apply, albeit with a few adaptations tailored for AI systems. We present the Process-oriented Hazard Analysis for AI Systems (PHASE) as a guideline that adapts STPA concepts for AI, making STPA-based hazard analysis more accessible. PHASE enables four key affordances for analysts responsible for managing AI system harms: 1) detection of hazards at the systems level, including those from accumulation of disparate issues; 2) explicit acknowledgment of social factors contributing to experiences of algorithmic harms; 3) creation of traceable accountability chains between harms and those who can mitigate the harm; and 4) ongoing monitoring and mitigation of new hazards.

Traditionally, Graph Neural Networks (GNNs) [1] have primarily been applied to model functions over graphs with a relatively modest number of nodes. However, recently there has been a growing interest in exploring the application of GNNs to large-scale graph benchmarks, including datasets with up to a hundred million nodes [2]. This exploration could potentially lead to better models for industrial applications such as large-scale network analysis in social media, where there are typically millions of users, or in biology, where proteins and other macromolecules are composed of a large number of atoms. This presents a significant challenge in designing GNNs that are scalable while retaining their effectiveness. To this end, we take inspiration from the literature on Large Language Models (LLMs) and propose a simple modification to how GNN architectures are typically arranged. Our framework, Scalable Message Passing Neural Networks (SMPNNs), enables the construction of deep and scalable architectures that outperform the current state-of-the-art models for large graph benchmarks in transductive classification. More specifically, we find that following the typical construction of the Pre-Layer Normalization (Pre-LN) Transformer formulation [3] and replacing attention with standard message-passing convolution is enough to outperform the best Graph Transformers in the literature. Moreover, since our formulation does not necessarily require attention, our architecture scales better than Graph Transformers.

In this paper, we propose an accurate and robust perception module for Autonomous Vehicles (AVs) for drivable space extraction. Perception is crucial in autonomous driving, where many deep learning-based methods, while accurate on benchmark datasets, fail to generalize effectively, especially in diverse and unpredictable environments. Our work introduces a robust easy-to-generalize perception module that leverages LiDAR, camera, and HD map data fusion to deliver a safe and reliable drivable space in all weather conditions. We present an adaptive ground removal and curb detection method integrated with HD map data for enhanced obstacle detection reliability. Additionally, we propose an adaptive DBSCAN clustering algorithm optimized for precipitation noise, and a cost-effective LiDAR-camera frustum association that is resilient to calibration discrepancies. Our comprehensive drivable space representation incorporates all perception data, ensuring compatibility with vehicle dimensions and road regulations. This approach not only improves generalization and efficiency, but also significantly enhances safety in autonomous vehicle operations. Our approach is tested on a real dataset and its reliability is verified during the daily (including harsh snowy weather) operation of our autonomous shuttle, WATonoBus

We introduce Image2Struct, a benchmark to evaluate vision-language models (VLMs) on extracting structure from images. Our benchmark 1) captures real-world use cases, 2) is fully automatic and does not require human judgment, and 3) is based on a renewable stream of fresh data. In Image2Struct, VLMs are prompted to generate the underlying structure (e.g., LaTeX code or HTML) from an input image (e.g., webpage screenshot). The structure is then rendered to produce an output image (e.g., rendered webpage), which is compared against the input image to produce a similarity score. This round-trip evaluation allows us to quantitatively evaluate VLMs on tasks with multiple valid structures. We create a pipeline that downloads fresh data from active online communities upon execution and evaluates the VLMs without human intervention. We introduce three domains (Webpages, LaTeX, and Musical Scores) and use five image metrics (pixel similarity, cosine similarity between the Inception vectors, learned perceptual image patch similarity, structural similarity index measure, and earth mover similarity) that allow efficient and automatic comparison between pairs of images. We evaluate Image2Struct on 14 prominent VLMs and find that scores vary widely, indicating that Image2Struct can differentiate between the performances of different VLMs. Additionally, the best score varies considerably across domains (e.g., 0.402 on sheet music vs. 0.830 on LaTeX equations), indicating that Image2Struct contains tasks of varying difficulty. For transparency, we release the full results at https://crfm.stanford.edu/helm/image2struct/v1.0.1/.

Accurate economic simulations often require many experimental runs, particularly when combined with reinforcement learning. Unfortunately, training reinforcement learning agents in multi-agent economic environments can be slow. This paper introduces EconoJax, a fast simulated economy, based on the AI economist. EconoJax, and its training pipeline, are completely written in JAX. This allows EconoJax to scale to large population sizes and perform large experiments, while keeping training times within minutes. Through experiments with populations of 100 agents, we show how real-world economic behavior emerges through training within 15 minutes, in contrast to previous work that required several days. To aid and inspire researchers to build more rich and dynamic economic simulations, we open-source EconoJax on Github at: https://github.com/ponseko/econojax.

Artificial intelligence (AI) technology has been evolving more rapidly over the past decade. With new ML models, data sources, and increased computational power, AI researchers have developed AI technologies that can understand language, recognize and create images and videos, program, and make scientific inferences. Recent advances in advanced AI technologies have evolved beyond traditional narrow domain AI to approximate or exceed artificial general intelligence (AGI) based on large language models (LLMs) or foundation models (FMs). These advanced AI systems are performing at or above human levels in complex problem solving, sophisticated natural language processing, and multi-domain tasks, and have the potential to revolutionize a wide range of fields, including science, industry, healthcare, and education. They are already surpassing human capabilities in certain task domains, such as Go, strategy games, and protein folding prediction [1] [2]. For these reasons, concerns about the safety and trustworthiness of advanced AI are growing rapidly alongside its development. The increasing complexity and autonomy of advanced AI systems is raising concerns that they could lead to new forms of safety and security risks, such as (1) uncontrollability, (2) conflicts with human values in ethical decision-making, (3) long-term socioeconomic impacts, and (4) safety assurance. In response, international standardization efforts are underway to ensure the safety and trustworthiness of advanced AI. By developing internationally agreed technical standards, efforts are being made to apply consistent safety and trustworthiness criteria to the development and use of advanced AI systems and minimize potential risks.

This paper introduces a closed-form analytical solution for the inverse kinematics (IK) of a 6 Degrees of Freedom (DOF) serial robotic manipulator arm, configured with six revolute joints and utilized within the Lunar Exploration Rover System (LERS). As a critical asset for conducting precise operations in the demanding lunar environment, this robotic arm relies on the IK solution to determine joint parameters required for precise end-effector positioning, essential for tasks such as sample collection, infrastructure assembly, and equipment deployment. By applying geometric principles, the proposed method offers a highly efficient and accurate approach to solving the IK problem, significantly reducing computational demands compared to traditional numerical methods. This advancement not only enhances real-time operational capabilities but is also optimized for space robotics, where precision and speed are critical. Additionally, the paper explores the integration of the LERS robotic system, underscoring the importance of this work in supporting autonomous lunar exploration within the ARTEMIS program and future missions