Enabling robot autonomy in complex environments for mission critical application requires robust state estimation. Particularly under conditions where the exteroceptive sensors, which the navigation depends on, can be degraded by environmental challenges thus, leading to mission failure. It is precisely in such challenges where the potential for FMCW radar sensors is highlighted: as a complementary exteroceptive sensing modality with direct velocity measuring capabilities. In this work we integrate radial speed measurements from a FMCW radar sensor, using a radial speed factor, to provide linear velocity updates into a sliding-window state estimator for fusion with LiDAR pose and IMU measurements. We demonstrate that this augmentation increases the robustness of the state estimator to challenging conditions present in the environment and the negative effects they can pose to vulnerable exteroceptive modalities. The proposed method is extensively evaluated using robotic field experiments conducted using an autonomous, full-scale, off-road vehicle operating at high-speeds (~12 m/s) in complex desert environments. Furthermore, the robustness of the approach is demonstrated for cases of both simulated and real-world degradation of the LiDAR odometry performance along with comparison against state-of-the-art methods for radar-inertial odometry on public datasets.

If two agents disagree in their decisions, we may suspect they are not both correct. This intuition is formalized for evaluating agents that have carried out a binary classification task. Their agreements and disagreements on a joint test allow us to establish the only group evaluations logically consistent with their responses. This is done by establishing a set of axioms (algebraic relations) that must be universally obeyed by all evaluations of binary responders. A complete set of such axioms are possible for each ensemble of size N. The axioms for $N = 1, 2$ are used to construct a fully logical alarm - one that can prove that at least one ensemble member is malfunctioning using only unlabeled data. The similarities of this approach to formal software verification and its utility for recent agendas of safe guaranteed AI are discussed.

Enriching datasets with demographic information, such as gender, race, and age from names, is a critical task in fields like healthcare, public policy, and social sciences. Such demographic insights allow for more precise and effective engagement with target populations. Despite previous efforts employing hidden Markov models and recurrent neural networks to predict demographics from names, significant limitations persist: the lack of large-scale, well-curated, unbiased, publicly available datasets, and the lack of an approach robust across datasets. This scarcity has hindered the development of traditional supervised learning approaches. In this paper, we demonstrate that the zero-shot capabilities of Large Language Models (LLMs) can perform as well as, if not better than, bespoke models trained on specialized data. We apply these LLMs to a variety of datasets, including a real-life, unlabelled dataset of licensed financial professionals in Hong Kong, and critically assess the inherent demographic biases in these models. Our work not only advances the state-of-the-art in demographic enrichment but also opens avenues for future research in mitigating biases in LLMs.

Underwater object-level mapping requires incorporating visual foundation models to handle the uncommon and often previously unseen object classes encountered in marine scenarios. In this work, a metric of semantic uncertainty for open-set object detections produced by visual foundation models is calculated and then incorporated into an object-level uncertainty tracking framework. Object-level uncertainties and geometric relationships between objects are used to enable robust object-level loop closure detection for unknown object classes. The above loop closure detection problem is formulated as a graph-matching problem. While graph matching, in general, is NP-Complete, a solver for an equivalent formulation of the proposed graph matching problem as a graph editing problem is tested on multiple challenging underwater scenes. Results for this solver as well as three other solvers demonstrate that the proposed methods are feasible for real-time use in marine environments for the robust, open-set, multi-object, semantic-uncertainty-aware loop closure detection. Further experimental results on the KITTI dataset demonstrate that the method generalizes to large-scale terrestrial scenes.

The Statistical Classification of Economic Activities in the European Community (NACE) is the standard classification system for the categorization of economic and industrial activities within the European Union. This paper proposes a novel approach to transform the NACE classification into low-dimensional embeddings, using state-of-the-art models and dimensionality reduction techniques. The primary challenge is the preservation of the hierarchical structure inherent within the original NACE classification while reducing the number of dimensions. To address this issue, we introduce custom metrics designed to quantify the retention of hierarchical relationships throughout the embedding and reduction processes. The evaluation of these metrics demonstrates the effectiveness of the proposed methodology in retaining the structural information essential for insightful analysis. This approach not only facilitates the visual exploration of economic activity relationships, but also increases the efficacy of downstream tasks, including clustering, classification, integration with other classifications, and others. Through experimental validation, the utility of our proposed framework in preserving hierarchical structures within the NACE classification is showcased, thereby providing a valuable tool for researchers and policymakers to understand and leverage any hierarchical data.

One application area of long-term memory (LTM) capabilities with increasing traction is personal AI companions and assistants. With the ability to retain and contextualize past interactions and adapt to user preferences, personal AI companions and assistants promise a profound shift in how we interact with AI and are on track to become indispensable in personal and professional settings. However, this advancement introduces new challenges and vulnerabilities that require careful consideration regarding the deployment and widespread use of these systems. The goal of this paper is to explore the broader implications of building and deploying personal AI applications with LTM capabilities using a holistic evaluation approach. This will be done in three ways: 1) reviewing the technological underpinnings of LTM in Large Language Models, 2) surveying current personal AI companions and assistants, and 3) analyzing critical considerations and implications of deploying and using these applications.

Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a standardized pipeline. This paper introduces THaMES (Tool for Hallucination Mitigations and EvaluationS), an integrated framework and library addressing this gap. THaMES offers an end-to-end solution for evaluating and mitigating hallucinations in LLMs, featuring automated test set generation, multifaceted benchmarking, and adaptable mitigation strategies. It automates test set creation from any corpus, ensuring high data quality, diversity, and cost-efficiency through techniques like batch processing, weighted sampling, and counterfactual validation. THaMES assesses a model's ability to detect and reduce hallucinations across various tasks, including text generation and binary classification, applying optimal mitigation strategies like In-Context Learning (ICL), Retrieval Augmented Generation (RAG), and Parameter-Efficient Fine-tuning (PEFT). Evaluations of state-of-the-art LLMs using a knowledge base of academic papers, political news, and Wikipedia reveal that commercial models like GPT-4o benefit more from RAG than ICL, while open-weight models like Llama-3.1-8B-Instruct and Mistral-Nemo gain more from ICL. Additionally, PEFT significantly enhances the performance of Llama-3.1-8B-Instruct in both evaluation tasks.

AI data-driven models (Graphcast, Pangu Weather, Fourcastnet, and SFNO) are explored for storyline-based climate attribution due to their short inference times, which can accelerate the number of events studied, and provide real time attributions when public attention is heightened. The analysis is framed on the extreme atmospheric river episode of February 2017 that contributed to the Oroville dam spillway incident in Northern California. Past and future simulations are generated by perturbing the initial conditions with the pre-industrial and the late-21st century temperature climate change signals, respectively. The simulations are compared to results from a dynamical model which represents plausible pseudo-realities under both climate environments. Overall, the AI models show promising results, projecting a 5-6 % increase in the integrated water vapor over the Oroville dam in the present day compared to the pre-industrial, in agreement with the dynamical model. Different geopotential-moisture-temperature dependencies are unveiled for each of the AI-models tested, providing valuable information for understanding the physicality of the attribution response. However, the AI models tend to simulate weaker attribution values than the pseudo-reality imagined by the dynamical model, suggesting some reduced extrapolation skill, especially for the late-21st century regime. Large ensembles generated with an AI model (>500 members) produced statistically significant present-day to pre-industrial attribution results, unlike the >20-member ensemble from the dynamical model. This analysis highlights the potential of AI models to conduct attribution analysis, while emphasizing future lines of work on explainable artificial intelligence to gain confidence in these tools, which can enable reliable attribution studies in real-time.

The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and lack of a fairness baseline. SAGED(-Bias) is the first holistic benchmarking pipeline to address these problems. The pipeline encompasses five core stages: scraping materials, assembling benchmarks, generating responses, extracting numeric features, and diagnosing with disparity metrics. SAGED includes metrics for max disparity, such as impact ratio, and bias concentration, such as Max Z-scores. Noticing that assessment tool bias and contextual bias in prompts can distort evaluation, SAGED implements counterfactual branching and baseline calibration for mitigation. For demonstration, we use SAGED on G20 Countries with popular 8b-level models including Gemma2, Llama3.1, Mistral, and Qwen2. With sentiment analysis, we find that while Mistral and Qwen2 show lower max disparity and higher bias concentration than Gemma2 and Llama3.1, all models are notably biased against countries like Russia and (except for Qwen2) China. With further experiments to have models role-playing U.S. (vice-/former-) presidents, we see bias amplifies and shifts in heterogeneous directions. Moreover, we see Qwen2 and Mistral not engage in role-playing, while Llama3.1 and Gemma2 role-play Trump notably more intensively than Biden and Harris, indicating role-playing performance bias in these models.

Synthetic opioids are the most common drugs involved in drug-involved overdose mortalities in the U.S. The Center for Disease Control and Prevention reported that in 2018, about 70% of all drug overdose deaths involved opioids and 67% of all opioid-involved deaths were accounted for by synthetic opioids. In this study, we investigated the spread of synthetic opioids between 2013 and 2020 in the U.S. We analyzed the relationship between the spatiotemporal pattern of synthetic opioid-involved deaths and another key opioid, heroin, and compared patterns of deaths involving these two types of drugs during this period. Spatial connections and human mobility between counties were incorporated into a graph convolutional neural network model to represent and analyze the spread of synthetic opioid-involved deaths in the context of previous heroin-involved death patterns.