Visualization for explainable and trustworthy machine learning remains one of the most important and heavily researched fields within information visualization and visual analytics with various application domains, such as medicine, finance, and bioinformatics. After our 2020 state-of-the-art report comprising 200 techniques, we have persistently collected peer-reviewed articles describing visualization techniques, categorized them based on the previously established categorization schema consisting of 119 categories, and provided the resulting collection of 542 techniques in an online survey browser. In this survey article, we present the updated findings of new analyses of this dataset as of fall 2023 and discuss trends, insights, and eight open challenges for using visualizations in machine learning. Our results corroborate the rapidly growing trend of visualization techniques for increasing trust in machine learning models in the past three years, with visualization found to help improve popular model explainability methods and check new deep learning architectures, for instance.

Database knob tuning is a critical challenge in the database community, aiming to optimize knob values to enhance database performance for specific workloads. DBMS often feature hundreds of tunable knobs, posing a significant challenge for DBAs to recommend optimal configurations. Consequently, many machine learning-based tuning methods have been developed to automate this process. Despite the introduction of various optimizers, practical applications have unveiled a new problem: they typically require numerous workload runs to achieve satisfactory performance, a process that is both time-consuming and resource-intensive. This inefficiency largely stems from the optimal configuration often being substantially different from the default setting, necessitating multiple iterations during tuning. Recognizing this, we argue that an effective starting point could significantly reduce redundant exploration in less efficient areas, thereby potentially speeding up the tuning process for the optimizers. Based on this assumption, we introduce LLMTune, a large language model-based configuration generator designed to produce an initial, high-quality configuration for new workloads. These generated configurations can then serve as starting points for various base optimizers, accelerating their tuning processes. To obtain training data for LLMTune's supervised fine-tuning, we have devised a new automatic data generation framework capable of efficiently creating a large number of pairs. We have conducted thorough experiments to evaluate LLMTune's effectiveness with different workloads, such as TPC-H and JOB. In comparison to leading methods, LLMTune demonstrates a quicker ability to identify superior configurations. For instance, with the challenging TPC-H workload, our LLMTune achieves a significant 15.6x speed-up ratio in finding the best-performing configurations.

Incorporating Generative AI (GenAI) and Large Language Models (LLMs) in education can enhance teaching efficiency and enrich student learning. Current LLM usage involves conversational user interfaces (CUIs) for tasks like generating materials or providing feedback. However, this presents challenges including the need for educator expertise in AI and CUIs, ethical concerns with high-stakes decisions, and privacy risks. CUIs also struggle with complex tasks. To address these, we propose transitioning from CUIs to user-friendly applications leveraging LLMs via API calls. We present a framework for ethically incorporating GenAI into educational tools and demonstrate its application in our tool, Feedback Copilot, which provides personalized feedback on student assignments. Our evaluation shows the effectiveness of this approach, with implications for GenAI researchers, educators, and technologists. This work charts a course for the future of GenAI in education.

We foresee robots that bootstrap knowledge representations and use them for classifying relevant situations and making decisions based on future observations. Particularly for assistive robots, the bootstrapping mechanism might be supervised by humans who should not repeat a training phase several times and should be able to refine the taught representation. We consider robots that bootstrap structured representations to classify some intelligible categories. Such a structure should be incrementally bootstrapped, i.e., without invalidating the identified category models when a new additional category is considered. To tackle this scenario, we presented the Scene Identification and Tagging (SIT) algorithm, which bootstraps structured knowledge representation in a crisp OWL-DL ontology. Over time, SIT bootstraps a graph representing scenes, sub-scenes and similar scenes. Then, SIT can classify new scenes within the bootstrapped graph through logic-based reasoning. However, SIT has issues with sensory data because its crisp implementation is not robust to perception noises. This paper presents a reformulation of SIT within the fuzzy domain, which exploits a fuzzy DL ontology to overcome the robustness issues. By comparing the performances of fuzzy and crisp implementations of SIT, we show that fuzzy SIT is robust, preserves the properties of its crisp formulation, and enhances the bootstrapped representations. On the contrary, the fuzzy implementation of SIT leads to less intelligible knowledge representations than the one bootstrapped in the crisp domain.

Note: This is not an official technical report from OpenAI. Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions and show potential in simulating the physical world. Based on public technical reports and reverse engineering, this paper presents a comprehensive review of the model's background, related technologies, applications, remaining challenges, and future directions of text-to-video AI models. We first trace Sora's development and investigate the underlying technologies used to build this "world simulator". Then, we describe in detail the applications and potential impact of Sora in multiple industries ranging from film-making and education to marketing. We discuss the main challenges and limitations that need to be addressed to widely deploy Sora, such as ensuring safe and unbiased video generation. Lastly, we discuss the future development of Sora and video generation models in general, and how advancements in the field could enable new ways of human-AI interaction, boosting productivity and creativity of video generation.

Buildings account for a substantial portion of global energy consumption. Reducing buildings' energy usage primarily involves obtaining data from building systems and environment, which are instrumental in assessing and optimizing the building's performance. However, as devices from various manufacturers represent their data in unique ways, this disparity introduces challenges for semantic interoperability and creates obstacles in developing scalable building applications. This survey explores the leading semantic modeling techniques deployed for energy management in buildings. Furthermore, it aims to offer tangible use cases for applying semantic models, shedding light on the pivotal concepts and limitations intrinsic to each model. Our findings will assist researchers in discerning the appropriate circumstances and methodologies for employing these models in various use cases.

Meeting summarization has become a critical task considering the increase in online interactions. While new techniques are introduced regularly, their evaluation uses metrics not designed to capture meeting-specific errors, undermining effective evaluation. This paper investigates what the frequently used automatic metrics capture and which errors they mask by correlating automatic metric scores with human evaluations across a broad error taxonomy. We commence with a comprehensive literature review on English meeting summarization to define key challenges like speaker dynamics and contextual turn-taking and error types such as missing information and linguistic inaccuracy, concepts previously loosely defined in the field. We examine the relationship between characteristic challenges and errors by using annotated transcripts and summaries from Transformer-based sequence-to-sequence and autoregressive models from the general summary QMSum dataset. Through experimental validation, we find that different model architectures respond variably to challenges in meeting transcripts, resulting in different pronounced links between challenges and errors. Current default-used metrics struggle to capture observable errors, showing weak to mid-correlations, while a third of the correlations show trends of error masking. Only a subset reacts accurately to specific errors, while most correlations show either unresponsiveness or failure to reflect the error's impact on summary quality.

With the rapid advancement of large language models (LLMs), information retrieval (IR) systems, such as search engines and recommender systems, have undergone a significant paradigm shift. This evolution, while heralding new opportunities, introduces emerging challenges, particularly in terms of biases and unfairness, which may threaten the information ecosystem. In this paper, we present a comprehensive survey of existing works on emerging and pressing bias and unfairness issues in IR systems when the integration of LLMs. We first unify bias and unfairness issues as distribution mismatch problems, providing a groundwork for categorizing various mitigation strategies through distribution alignment. Subsequently, we systematically delve into the specific bias and unfairness issues arising from three critical stages of LLMs integration into IR systems: data collection, model development, and result evaluation. In doing so, we meticulously review and analyze recent literature, focusing on the definitions, characteristics, and corresponding mitigation strategies associated with these issues. Finally, we identify and highlight some open problems and challenges for future work, aiming to inspire researchers and stakeholders in the IR field and beyond to better understand and mitigate bias and unfairness issues of IR in this LLM era. We also consistently maintain a GitHub repository for the relevant papers and resources in this rising direction at https://github.com/KID-22/LLM-IR-Bias-Fairness-Survey.

Federated Learning (FL) has emerged as a promising approach for privacy-preserving machine learning, particularly in sensitive domains such as healthcare. In this context, the TRUSTroke project aims to leverage FL to assist clinicians in ischemic stroke prediction. This paper provides an overview of the TRUSTroke FL network infrastructure. The proposed architecture adopts a client-server model with a central Parameter Server (PS). We introduce a Docker-based design for the client nodes, offering a flexible solution for implementing FL processes in clinical settings. The impact of different communication protocols (HTTP or MQTT) on FL network operation is analyzed, with MQTT selected for its suitability in FL scenarios. A control plane to support the main operations required by FL processes is also proposed. The paper concludes with an analysis of security aspects of the FL architecture, addressing potential threats and proposing mitigation strategies to increase the trustworthiness level.

The application of artificial intelligence (AI) models in fields such as engineering is limited by the known difficulty of quantifying the reliability of an AI's decision. A well-calibrated AI model must correctly report its accuracy on in-distribution (ID) inputs, while also enabling the detection of out-of-distribution (OOD) inputs. A conventional approach to improve calibration is the application of Bayesian ensembling. However, owing to computational limitations and model misspecification, practical ensembling strategies do not necessarily enhance calibration. This paper proposes an extension of variational inference (VI)-based Bayesian learning that integrates calibration regularization for improved ID performance, confidence minimization for OOD detection, and selective calibration to ensure a synergistic use of calibration regularization and confidence minimization. The scheme is constructed successively by first introducing calibration-regularized Bayesian learning (CBNN), then incorporating out-of-distribution confidence minimization (OCM) to yield CBNN-OCM, and finally integrating also selective calibration to produce selective CBNN-OCM (SCBNN-OCM). Selective calibration rejects inputs for which the calibration performance is expected to be insufficient. Numerical results illustrate the trade-offs between ID accuracy, ID calibration, and OOD calibration attained by both frequentist and Bayesian learning methods. Among the main conclusions, SCBNN-OCM is seen to achieve best ID and OOD performance as compared to existing state-of-the-art approaches at the cost of rejecting a sufficiently large number of inputs.