arXiv Computer Science @arxiv_cs@qoto.org

This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the Clinical and Translational Science Award (CTSA) Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States. With the rapid advancement of GenAI technologies, including large language models (LLMs), healthcare institutions face unprecedented opportunities and challenges. This research explores the current status of GenAI integration, focusing on stakeholder roles, governance structures, and ethical considerations by administering a survey among leaders of health institutions (i.e., representing academic medical centers and health systems) to assess the institutional readiness and approach towards GenAI adoption. Key findings indicate a diverse range of institutional strategies, with most organizations in the experimental phase of GenAI deployment. The study highlights significant variations in governance models, with a strong preference for centralized decision-making but notable gaps in workforce training and ethical oversight. Moreover, the results underscore the need for a more coordinated approach to GenAI governance, emphasizing collaboration among senior leaders, clinicians, information technology staff, and researchers. Our analysis also reveals concerns regarding GenAI bias, data security, and stakeholder trust, which must be addressed to ensure the ethical and effective implementation of GenAI technologies. This study offers valuable insights into the challenges and opportunities of GenAI integration in healthcare, providing a roadmap for institutions aiming to leverage GenAI for improved quality of care and operational efficiency.

Efficiently serving embedding-based recommendation (EMR) models remains a significant challenge due to their increasingly large memory requirements. Today's practice splits the model across many monolithic servers, where a mix of GPUs, CPUs, and DRAM is provisioned in fixed proportions. This approach leads to suboptimal resource utilization and increased costs. Disaggregating embedding operations from neural network inference is a promising solution but raises novel networking challenges. In this paper, we discuss the design of FlexEMR for optimized EMR disaggregation. FlexEMR proposes two sets of techniques to tackle the networking challenges: Leveraging the temporal and spatial locality of embedding lookups to reduce data movement over the network, and designing an optimized multi-threaded RDMA engine for concurrent lookup subrequests. We outline the design space for each technique and present initial results from our early prototype.

Building up competencies in working with data and tools of Artificial Intelligence (AI) is becoming more relevant across disciplinary engineering fields. While the adoption of tools for teaching and learning, such as ChatGPT, is garnering significant attention, integration of AI knowledge, competencies, and skills within engineering education is lacking. Building upon existing curriculum change research, this practice paper introduces a systems perspective on integrating AI education within engineering through the lens of a change model. In particular, it identifies core aspects that shape AI adoption on a program level as well as internal and external influences using existing literature and a practical case study. Overall, the paper provides an analysis frame to enhance the understanding of change initiatives and builds the basis for generalizing insights from different initiatives in the adoption of AI in engineering education.

In this practice paper, we propose a framework for integrating AI into disciplinary engineering courses and curricula. The use of AI within engineering is an emerging but growing area and the knowledge, skills, and abilities (KSAs) associated with it are novel and dynamic. This makes it challenging for faculty who are looking to incorporate AI within their courses to create a mental map of how to tackle this challenge. In this paper, we advance a role-based conception of competencies to assist disciplinary faculty with identifying and implementing AI competencies within engineering curricula. We draw on prior work related to AI literacy and competencies and on emerging research on the use of AI in engineering. To illustrate the use of the framework, we provide two exemplary cases. We discuss the challenges in implementing the framework and emphasize the need for an embedded approach where AI concerns are integrated across multiple courses throughout the degree program, especially for teaching responsible and ethical AI development and use.

Multidisciplinary research, in conjunction with artificial intelligence (AI), the Internet of Things (IoT), Blockchain and Big Data analysis, has lowered barriers and made companies more productive, in other words, the joint work of these areas has promoted digital transformation in all areas, for example Artificial intelligence (AI) has made it possible to automate processes, and the Internet of Things (IoT) has connected devices and physical objects, enabling real-time data collection and analysis. Blockchain has provided a secure and transparent way to transact and store data. Big Data analysis has allowed companies to obtain valuable insights from large amounts of data. As these technologies continue to evolve, we can expect to see even more innovations and benefits in the future. This paper explores the feasibility of using Mobile Crowd Sensing (MCS) and visualization algorithms to detect crowding on a university campus. A survey was conducted to evaluate the university community's perception of a mobile application that provides information about crowds, and a detection scenario was simulated using randomly generated data and the DBSCAN algorithm for visualization. Preliminary results suggest that the system is viable and could be a useful tool for the prevention of accidents due to crowding and for the management of public spaces. The limitations of the study are discussed and future lines of research are proposed, such as crowd prediction, data privacy, and visualization optimization.

The rapid expansion of Internet of Vehicles (IoV) deployments has necessitated the creation of efficient and secure routing models to manage the massive data traffic generated by interconnected devices & vehicles. For IoV deployments, we propose a novel fan-shaped trust-based routing model with Quality of Service (QoS) and security-aware side-chaining. Our method employs temporal levels of delay, throughput, Packet Delivery Ratio (PDR), and energy consumption to determine optimal routing paths, thereby ensuring efficient data transmissions. We employ the Bacterial Foraging Optimizer (BFO) algorithm to manage side-chains within the network, which dynamically adjusts side-chain configurations to optimize system performance. The technique of fan-shaped clustering is used to group nodes into efficient clusters, allowing for more efficient communication and resource utilization sets. Extensive experimentation and performance analysis are utilized to evaluate the proposed model. Existing blockchain-based security models have been significantly improved by our findings. Our model achieves a remarkable 9.5% reduction in delay, a 10.5% improvement in throughput, a 2.9% improvement in PDR, and a 4.5% reduction in energy consumption compared to alternative approaches. In addition, we evaluate the model's resistance to Sybil, Masquerading, and Flooding attacks, which are prevalent security threats for IoV deployments. Even under these attack scenarios, our model provides consistently higher QoS levels compared to existing solutions, ensuring uninterrupted and reliable data transmissions. In IoV deployments, the proposed routing model and side-chaining management approach have numerous applications and use-cases like Smart cities, industrial automation, healthcare systems, transportation networks, and environmental monitoring.

Ads supply personalization aims to balance the revenue and user engagement, two long-term objectives in social media ads, by tailoring the ad quantity and density. In the industry-scale system, the challenge for ads supply lies in modeling the counterfactual effects of a conservative supply treatment (e.g., a small density change) over an extended duration. In this paper, we present a streamlined framework for personalized ad supply. This framework optimally utilizes information from data collection policies through the doubly robust learning. Consequently, it significantly improves the accuracy of long-term treatment effect estimates. Additionally, its low-complexity design not only results in computational cost savings compared to existing methods, but also makes it scalable for billion-scale applications. Through both offline experiments and online production tests, the framework consistently demonstrated significant improvements in top-line business metrics over months. The framework has been fully deployed to live traffic in one of the world's largest social media platforms.

Scientific data governance should prioritize maximizing the utility of data throughout the research lifecycle. Research software systems that enable analysis reproducibility inform data governance policies and assist administrators in setting clear guidelines for data reuse, data retention, and the management of scientific computing needs. Proactive analysis reproducibility and data governance are integral and interconnected components of research lifecycle management.

We consider an autonomous navigation robot that can accept human commands through natural language to provide services in an indoor environment. These natural language commands may include time, position, object, and action components. However, we observe that the positional components within such commands usually refer to objects in the environment that may contain different levels of positional ambiguity. For example, the command "Go to the chair!" may be ambiguous when there are multiple chairs of the same type in a room. In order to disambiguate these commands, we employ a large language model and a large vision-language model to conduct multiple turns of conversations with the user. We propose a two-level approach that utilizes a vision-language model to map the meanings in natural language to a unique object ID in images and then performs another mapping from the unique object ID to a 3D depth map, thereby allowing the robot to navigate from its current position to the target position. To the best of our knowledge, this is the first work linking foundation models to the positional ambiguity issue.

Explainable Artificial Intelligence (XAI) techniques are used to provide transparency to complex, opaque predictive models. However, these techniques are often designed for image and text data, and it is unclear how fit-for-purpose they are when applied to tabular data. As XAI techniques are rarely evaluated in settings with tabular data, the applicability of existing evaluation criteria and methods are also unclear and needs (re-)examination. For example, some works suggest that evaluation methods may unduly influence the evaluation results when using tabular data. This lack of clarity on evaluation procedures can lead to reduced transparency and ineffective use of XAI techniques in real world settings. In this study, we examine literature on XAI evaluation to derive guidelines on functionally-grounded assessment of local, post hoc XAI techniques. We identify 20 evaluation criteria and associated evaluation methods, and derive guidelines on when and how each criterion should be evaluated. We also identify key research gaps to be addressed by future work. Our study contributes to the body of knowledge on XAI evaluation through in-depth examination of functionally-grounded XAI evaluation protocols, and has laid the groundwork for future research on XAI evaluation.

Large language models (LLMs) have demonstrated significant potential in the development of intelligent applications and systems such as LLM-based agents and agent operating systems (AIOS). However, when these applications and systems interact with the underlying file system, the file system still remains the traditional paradigm: reliant on manual navigation through precise commands. This paradigm poses a bottleneck to the usability of these systems as users are required to navigate complex folder hierarchies and remember cryptic file names. To address this limitation, we propose an LLM-based semantic file system ( LSFS ) for prompt-driven file management. Unlike conventional approaches, LSFS incorporates LLMs to enable users or agents to interact with files through natural language prompts, facilitating semantic file management. At the macro-level, we develop a comprehensive API set to achieve semantic file management functionalities, such as semantic file retrieval, file update monitoring and summarization, and semantic file rollback). At the micro-level, we store files by constructing semantic indexes for them, design and implement syscalls of different semantic operations (e.g., CRUD, group by, join) powered by vector database. Our experiments show that LSFS offers significant improvements over traditional file systems in terms of user convenience, the diversity of supported functions, and the accuracy and efficiency of file operations. Additionally, with the integration of LLM, our system enables more intelligent file management tasks, such as content summarization and version comparison, further enhancing its capabilities.

Large language models (LLMs) have revolutionized natural language processing with their exceptional capabilities. However, deploying LLMs on resource-constrained edge devices presents significant challenges due to computational limitations, memory constraints, and edge hardware heterogeneity. This survey summarizes recent developments in edge LLMs across their lifecycle, examining resource-efficient designs from pre-deployment techniques to runtime optimizations. Additionally, it explores on-device LLM applications in personal, enterprise, and industrial scenarios. By synthesizing advancements and identifying future directions, this survey aims to provide a comprehensive understanding of state-of-the-art methods for deploying LLMs on edge devices, bridging the gap between their immense potential and edge computing limitations.

In response to the growing need for dynamic software features in automobiles, Software Defined Vehicles (SDVs) have emerged as a promising solution. They integrate dynamic onboard service management to handle the large variety of user-requested services during vehicle operation. Allocating onboard resources efficiently in this setting is a challenging task, as it requires a balance between maximizing user experience and guaranteeing mixed-criticality Quality-of-Service (QoS) network requirements. Our previous research introduced a dynamic resource-based onboard service orchestration algorithm. This algorithm considers real-time invehicle and V2X network health, along with onboard resource constraints, to globally select degraded modes for onboard applications. It maximizes the overall user experience at all times while being embeddable onboard for on-the-fly decisionmaking. A key enabler of this approach is the introduction of the Automotive eXperience Integrity Level (AXIL), a metric expressing runtime priority for non-safety-critical applications. While initial simulation results demonstrated the algorithm's effectiveness, a comprehensive performance assessment would greatly contribute in validating its industrial feasibility. In this current work, we present experimental results obtained from a dedicated test bench. These results illustrate, validate, and assess the practicality of our proposed solution, providing a solid foundation for the continued advancement of dynamic onboard service orchestration in SDVs.

Image matching is a fundamental and critical task of multisource remote sensing image applications. However, remote sensing images are susceptible to various noises. Accordingly, how to effectively achieve accurate matching in noise images is a challenging problem. To solve this issue, we propose a robust multisource remote sensing image matching method utilizing attention and feature enhancement against noise interference. In the first stage, we combine deep convolution with the attention mechanism of transformer to perform dense feature extraction, constructing feature descriptors with higher discriminability and robustness. Subsequently, we employ a coarse-to-fine matching strategy to achieve dense matches. In the second stage, we introduce an outlier removal network based on a binary classification mechanism, which can establish effective and geometrically consistent correspondences between images; through weighting for each correspondence, inliers vs. outliers classification are performed, as well as removing outliers from dense matches. Ultimately, we can accomplish more efficient and accurate matches. To validate the performance of the proposed method, we conduct experiments using multisource remote sensing image datasets for comparison with other state-of-the-art methods under different scenarios, including noise-free, additive random noise, and periodic stripe noise. Comparative results indicate that the proposed method has a more well-balanced performance and robustness. The proposed method contributes a valuable reference for solving the difficult problem of noise image matching.

Analyzing individual human trajectory data helps our understanding of human mobility and finds many commercial and academic applications. There are two main approaches to accessing trajectory data for research: one involves using real-world datasets like GeoLife, while the other employs simulations to synthesize data. Real-world data provides insights from real human activities, but such data is generally sparse due to voluntary participation. Conversely, simulated data can be more comprehensive but may capture unrealistic human behavior. In this Data and Resource paper, we combine the benefit of both by leveraging the statistical features of real-world data and the comprehensiveness of simulated data. Specifically, we extract features from the real-world GeoLife dataset such as the average number of individual daily trips, average radius of gyration, and maximum and minimum trip distances. We calibrate the Pattern of Life Simulation, a realistic simulation of human mobility, to reproduce these features. Therefore, we use a genetic algorithm to calibrate the parameters of the simulation to mimic the GeoLife features. For this calibration, we simulated numerous random simulation settings, measured the similarity of generated trajectories to GeoLife, and iteratively (over many generations) combined parameter settings of trajectory datasets most similar to GeoLife. Using the calibrated simulation, we simulate large trajectory datasets that we call GeoLife+, where + denotes the Kleene Plus, indicating unlimited replication with at least one occurrence. We provide simulated GeoLife+ data with 182, 1k, and 5k over 5 years, 10k, and 50k over a year and 100k users over 6 months of simulation lifetime.

Energy consumption has become a critical design metric and a limiting factor in the development of future computing architectures, from small wearable devices to large-scale leadership computing facilities. The predominant methods in energy management optimization are focused on CPUs. However, GPUs are increasingly significant and account for the majority of energy consumption in heterogeneous high performance computing (HPC) systems. Moreover, they typically rely on either purely offline training or a hybrid of offline and online training, which are impractical and lead to energy loss during data collection. Therefore, this paper studies a novel and practical online energy optimization problem for GPUs in HPC scenarios. The problem is challenging due to the inherent performance-energy trade-offs of GPUs, the exploration & exploitation dilemma across frequencies, and the lack of explicit performance counters in GPUs. To address these challenges, we formulate the online energy consumption optimization problem as a multi-armed bandit framework and develop a novel bandit based framework EnergyUCB. EnergyUCB is designed to dynamically adjust GPU core frequencies in real-time, reducing energy consumption with minimal impact on performance. Specifically, the proposed framework EnergyUCB (1) balances the performance-energy trade-off in the reward function, (2) effectively navigates the exploration & exploitation dilemma when adjusting GPU core frequencies online, and (3) leverages the ratio of GPU core utilization to uncore utilization as a real-time GPU performance metric. Experiments on a wide range of real-world HPC benchmarks demonstrate that EnergyUCB can achieve substantial energy savings. The code of EnergyUCB is available at https://github.com/XiongxiaoXu/EnergyUCB-Bandit.

The widespread use of AI technologies to generate digital content has led to increased misinformation and online harm. Deep fake technologies, a type of AI, make it easier to create convincing but fake content on social media, leading to various cyber threats. Malicious actors exploit AI capabilities, posing digital, physical, and psychological harm to individuals. While social media platforms have safety measures such as content rating and feedback systems, these are often used by people with higher digital literacy. There is a lack of preventive measures and a need for user-friendly tools that can be used by people with lower digital literacy. Our goal is to create a user-friendly multilingual AI-based personal assistant, Malak, to reduce online harm and promote safe online interactions, benefiting users with lower literacy levels.

In this paper, we make a case for a proxy for large language models which has explicit support for cost-saving optimizations. We design LLMProxy, which supports three key optimizations: model selection, context management, and caching. These optimizations present tradeoffs in terms of cost, inference time, and response quality, which applications can navigate through our high level, bidirectional interface. As a case study, we implement a WhatsApp-based Q&A service that uses LLMProxy to provide a rich set of features to the users. This service is deployed on a small scale (100+ users) leveraging the cloud; it has been operational for 15+ weeks and users have asked 1400+ questions so far. We report on the experiences of running this service as well as microbenchmark the specific benefits of the various cost-optimizations we present in this paper.

Mental health issues significantly impact individuals' daily lives, yet many do not receive the help they need even with available online resources. This study aims to provide accessible, stigma-free, personalized, and real-time mental health support through cutting-edge AI technologies. It makes the following contributions: (1) Conducting an extensive survey of recent mental health support methods to identify prevalent functionalities and unmet needs. (2) Introducing SouLLMate, an adaptive LLM-driven system that integrates LLM technologies, Chain, Retrieval-Augmented Generation (RAG), prompt engineering, and domain knowledge. This system offers advanced features such as Suicide Risk Detection and Proactive Guidance Dialogue, and utilizes RAG for personalized profile uploads and Conversational Information Extraction. (3) Developing novel evaluation approaches to assess preliminary assessments and suicide risk detection, utilizing annotated real-life interview data and professionally labeled datasets indicating suicide tendencies. (4) Proposing Key Indicator Summarization (KIS) and Proactive Questioning Strategy (PQS) methods to enhance model performance and usability through context-sensitive response adjustments and semantic coherence evaluations. This study contributes to advancing mental health support technologies, potentially improving the accessibility and effectiveness of mental health care globally.

When designing an AI-assisted decision-making system, there is often a tradeoff between precision and recall in the AI's recommendations. We argue that careful exploitation of this tradeoff can harness the complementary strengths in the human-AI collaboration to significantly improve team performance. We investigate a real-world video anonymization task for which recall is paramount and more costly to improve. We analyze the performance of 78 professional annotators working with a) no AI assistance, b) a high-precision "restrained" AI, and c) a high-recall "zealous" AI in over 3,466 person-hours of annotation work. In comparison, the zealous AI helps human teammates achieve significantly shorter task completion time and higher recall. In a follow-up study, we remove AI assistance for everyone and find negative training effects on annotators trained with the restrained AI. These findings and our analysis point to important implications for the design of AI assistance in recall-demanding scenarios.