Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns...
详细信息
Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns and conjure coherent and contextually fitting responses. LLMs are a type of artificial intelligence (AI) that have emerged as powerful tools for a wide range of tasks, including natural language processing (NLP), machine translation, vision applications, and question-answering. This survey provides a comprehensive overview of LLMs, including their history, architecture, datasets, training methods, applications, challenges, and future prospects. We begin by discussing the fundamental concepts of generative AI and the architecture of generative pre-trained transformers (GPT). We then provide an overview of the history of LLMs, their evolution over time, and the different training methods. We also present benchmark dataset for training and fine-tuning and evaluating LLMs. We then discuss the wide range of tasks where they are used and also discuss applications of LLMs in different domains, including medicine, education, finance, engineering, agriculture, media, entertainment, politics, and law. We also discuss how LLMs are shaping the future of AI and their increasing role in scientific discovery, and how they can be used to solve real-world problems. Next, we explore the challenges associated with deploying LLMs in real-world scenarios, including ethical considerations, model biases, interpretability, privacy concerns, and computational resource requirements. This survey also highlights techniques for enhancing the robustness and controllability of LLMs and addressing bias, fairness, and quality issues in Generative AI. Finally, we conclude by highlighting the future of LLM research and the challenges that need to be addressed in order to make this technology more reliable and useful. This survey is intended to provide researchers, practitioners, and ent
In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visua...
详细信息
— Robotic grasping in the open world is a critical component of manufacturing and automation processes. While numerous existing approaches depend on 2D segmentation output to facilitate the grasping procedure, accura...
详细信息
Cross-Site Scripting (XSS) attacks continue to pose a significant threat to web applications, compromising the security and integrity of user data. XSS is a web application vulnerability where malicious scripts are in...
详细信息
Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications. Pretraining on vast web-scale data has laid the foundation for these models, yet the re...
详细信息
In this work, we present a comprehensive survey on applications of the most recent transformer architecture based on attention in information security. Our review reveals three primary areas of application: Intrusion ...
详细信息
In this work, we present a comprehensive survey on applications of the most recent transformer architecture based on attention in information security. Our review reveals three primary areas of application: Intrusion detection, Anomaly Detection and Malware Detection. We have presented an overview of attention-based mechanisms and their application in each cybersecurity use case, and discussed open grounds for future trends in Artificial Intelligence enabled information security.
Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server. However, due to system heterogeneity and limited budget, it is general...
Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server. However, due to system heterogeneity and limited budget, it is generally impractical for the server to incentivize all clients to participate in all training rounds (known as full participation). The existing FL incentive mechanisms are typically designed by stimulating a fixed subset of clients based on their data quantity or system resources. Hence, FL is performed only using this subset of clients throughout the entire training process, leading to a biased model because of data heterogeneity. This paper proposes a game-theoretic incentive mechanism for FL with randomized client participation, where the server adopts a customized pricing strategy that motivates different clients to join with different participation levels (probabilities) for obtaining an unbiased and high-performance model. Each client responds to the server's monetary incentive by choosing its best participation level, to maximize its profit based on not only the incurred local cost but also its intrinsic value for the global model. To effectively evaluate clients' contribution to the model performance, we derive a new convergence bound which analytically predicts how clients' arbitrary participation levels and their heterogeneous data affect the model performance. By solving a non-convex optimization problem, our analysis reveals that the intrinsic value leads to the interesting possibility of bi-directional payment between the server and clients. Experimental results using real datasets on a hardware prototype demonstrate the superiority of our mechanism in achieving higher model performance for the server as well as higher profits for the clients.
—Deep Learning (DL) is the most widely used tool in the contemporary field of computervision. Its ability to accurately solve complex problems is employed in visionresearch to learn deep neural models for a variety...
详细信息
Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalis...
详细信息
Deep Reinforcement Learning (DRL) is emerging as a promising approach to generate adaptive behaviors for robotic platforms. However, a major drawback of using DRL is the data-hungry training regime that requires milli...
详细信息
暂无评论