The rapid advancement of artificial intelligence (AI) technologies has led to an increasing deployment of AI models on edge and terminal devices, driven by the proliferation of the Internet of Things (IoT) and the need for real-time data processing. This survey comprehensively explores the current state, technical challenges, and future trends of on-device AI models. We define on-device AI models as those designed to perform local data processing and inference, emphasizing their characteristics such as real-time performance, resource constraints, and enhanced data privacy. The survey is structured around key themes, including the fundamental concepts of AI models, application scenarios across various domains, and the technical challenges faced in edge environments. We also discuss optimization and implementation strategies, such as data preprocessing, model compression, and hardware acceleration, which are essential for effective deployment. Furthermore, we examine the impact of emerging technologies, including edge computing and foundation models, on the evolution of on-device AI models. By providing a structured overview of the challenges, solutions, and future directions, this survey aims to facilitate further research and application of on-device AI, ultimately contributing to the advancement of intelligent systems in everyday life.

Large language models (LLMs) have significantly facilitated human life, and prompt engineering has improved the efficiency of these models. However, recent years have witnessed a rise in prompt engineering-empowered attacks, leading to issues such as privacy leaks, increased latency, and system resource wastage. Though safety fine-tuning based methods with Reinforcement Learning from Human Feedback (RLHF) are proposed to align the LLMs, existing security mechanisms fail to cope with fickle prompt attacks, highlighting the necessity of performing security detection on prompts. In this paper, we jointly consider prompt security, service latency, and system resource optimization in Edge-Cloud LLM (EC-LLM) systems under various prompt attacks. To enhance prompt security, a vector-database-enabled lightweight attack detector is proposed. We formalize the problem of joint prompt detection, latency, and resource optimization into a multi-stage dynamic Bayesian game model. The equilibrium strategy is determined by predicting the number of malicious tasks and updating beliefs at each stage through Bayesian updates. The proposed scheme is evaluated on a real implemented EC-LLM system, and the results demonstrate that our approach offers enhanced security, reduces the service latency for benign users, and decreases system resource consumption compared to state-of-the-art algorithms.

The emergence of 5G and edge computing hardware has brought about a significant shift in artificial intelligence, with edge AI becoming a crucial technology for enabling intelligent applications. With the growing amount of data generated and stored on edge devices, deploying AI models for local processing and inference has become increasingly necessary. However, deploying state-of-the-art AI models on resource-constrained edge devices faces significant challenges that must be addressed. This paper presents an optimization triad for efficient and reliable edge AI deployment, including data, model, and system optimization. First, we discuss optimizing data through data cleaning, compression, and augmentation to make it more suitable for edge deployment. Second, we explore model design and compression methods at the model level, such as pruning, quantization, and knowledge distillation. Finally, we introduce system optimization techniques like framework support and hardware acceleration to accelerate edge AI workflows. Based on an in-depth analysis of various application scenarios and deployment challenges of edge AI, this paper proposes an optimization paradigm based on the data-model-system triad to enable a whole set of solutions to effectively transfer ML models, which are initially trained in the cloud, to various edge devices for supporting multiple scenarios.

The real estate market relies heavily on structured data, such as property details, market trends, and price fluctuations. However, the lack of specialized Tabular Question Answering datasets in this domain limits the development of automated question-answering systems. To fill this gap, we introduce RETQA, the first large-scale open-domain Chinese Tabular Question Answering dataset for Real Estate. RETQA comprises 4,932 tables and 20,762 question-answer pairs across 16 sub-fields within three major domains: property information, real estate company finance information and land auction information. Compared with existing tabular question answering datasets, RETQA poses greater challenges due to three key factors: long-table structures, open-domain retrieval, and multi-domain queries. To tackle these challenges, we propose the SLUTQA framework, which integrates large language models with spoken language understanding tasks to enhance retrieval and answering accuracy. Extensive experiments demonstrate that SLUTQA significantly improves the performance of large language models on RETQA by in-context learning. RETQA and SLUTQA provide essential resources for advancing tabular question answering research in the real estate domain, addressing critical challenges in open-domain and long-table question-answering. The dataset and code are publicly available at \url{https://github.com/jensen-w/RETQA}.

Abstract--Diversity in demonstration selection is crucial for enhancing model generalization, as it enables a broader coverage of structures and concepts. However, constructing an appropriate set of demonstrations has remained a focal point of research. This paper presents the Relevance-Diversity Enhanced Selection (RDES), an innovative approach that leverages reinforcement learning to optimize the selection of diverse reference demonstrations for text classification tasks using Large Language Models (LLMs), especially in few-shot prompting scenarios. RDES employs a Q-learning framework to dynamically identify demonstrations that maximize both diversity and relevance to the classification objective by calculating a diversity score based on label distribution among selected demonstrations. This method ensures a balanced representation of reference data, leading to improved classification accuracy. This methodology allows LLMs to leverage their inherent LLMs have demonstrated exceptional capabilities across capabilities for understanding and processing text, making a wide array of NLP tasks, including text annotation [1], them particularly suitable for tasks with limited labeled data. These However, the effectiveness of ICL is contingent upon the models leverage extensive corpora of textual data to learn rich selection of appropriate and representative demonstrations representations, which empower them to perform reasoning from the knowledge base to serve as contextual references with high accuracy [4]-[6]. This critical aspect of fewshot of these models continue to expand, enhancing their learning is often overlooked in existing literature [12], reasoning capabilities becomes increasingly crucial.

Despite its popularity in sentence-level relation extraction, distantly supervised data is rarely utilized by existing work in document-level relation extraction due to its noisy nature and low information density. Among its current applications, distantly supervised data is mostly used as a whole for pertaining, which is of low time efficiency. To fill in the gap of efficient and robust utilization of distantly supervised training data, we propose Efficient Multi-Supervision for document-level relation extraction, in which we first select a subset of informative documents from the massive dataset by combining distant supervision with expert supervision, then train the model with Multi-Supervision Ranking Loss that integrates the knowledge from multiple sources of supervision to alleviate the effects of noise. The experiments demonstrate the effectiveness of our method in improving the model performance with higher time efficiency than existing baselines.

The Large Language Model (LLM) has gained significant popularity and is extensively utilized across various domains. Most LLM deployments occur within cloud data centers, where they encounter substantial response delays and incur high costs, thereby impacting the Quality of Services (QoS) at the network edge. Leveraging vector database caching to store LLM request results at the edge can substantially mitigate response delays and cost associated with similar requests, which has been overlooked by previous research. Addressing these gaps, this paper introduces a novel Vector database-assisted cloud-Edge collaborative LLM QoS Optimization (VELO) framework. Firstly, we propose the VELO framework, which ingeniously employs vector database to cache the results of some LLM requests at the edge to reduce the response time of subsequent similar requests. Diverging from direct optimization of the LLM, our VELO framework does not necessitate altering the internal structure of LLM and is broadly applicable to diverse LLMs. Subsequently, building upon the VELO framework, we formulate the QoS optimization problem as a Markov Decision Process (MDP) and devise an algorithm grounded in Multi-Agent Reinforcement Learning (MARL) to decide whether to request the LLM in the cloud or directly return the results from the vector database at the edge. Moreover, to enhance request feature extraction and expedite training, we refine the policy network of MARL and integrate expert demonstrations. Finally, we implement the proposed algorithm within a real edge system. Experimental findings confirm that our VELO framework substantially enhances user satisfaction by concurrently diminishing delay and resource consumption for edge users utilizing LLMs.

Large Language Models (LLMs) have demonstrated amazing capabilities in language generation, text comprehension, and knowledge reasoning. While a single powerful model can already handle multiple tasks, relying on a single perspective can lead to biased and unstable results. Recent studies have further improved the model's reasoning ability on a wide range of tasks by introducing multi-model collaboration. However, models with different capabilities may produce conflicting answers on the same problem, and how to reasonably obtain the correct answer from multiple candidate models has become a challenging problem. In this paper, we propose the multi-model brainstorming based on prompt. It incorporates different models into a group for brainstorming, and after multiple rounds of reasoning elaboration and re-inference, a consensus answer is reached within the group. We conducted experiments on three different types of datasets, and demonstrate that the brainstorming can significantly improve the effectiveness in logical reasoning and fact extraction. Furthermore, we find that two small-parameter models can achieve accuracy approximating that of larger-parameter models through brainstorming, which provides a new solution for distributed deployment of LLMs.

Aiming at privacy preservation, Federated Learning (FL) is an emerging machine learning approach enabling model training on decentralized devices or data sources. The learning mechanism of FL relies on aggregating parameter updates from individual clients. However, this process may pose a potential security risk due to the presence of malicious devices. Existing solutions are either costly due to the use of compute-intensive technology, or restrictive for reasons of strong assumptions such as the prior knowledge of the number of attackers and how they attack. Few methods consider both privacy constraints and uncertain attack scenarios. In this paper, we propose a robust FL approach based on the credibility management scheme, called Fed-Credit. Unlike previous studies, our approach does not require prior knowledge of the nodes and the data distribution. It maintains and employs a credibility set, which weighs the historical clients' contributions based on the similarity between the local models and global model, to adjust the global model update. The subtlety of Fed-Credit is that the time decay and attitudinal value factor are incorporated into the dynamic adjustment of the reputation weights and it boasts a computational complexity of O(n) (n is the number of the clients). We conducted extensive experiments on the MNIST and CIFAR-10 datasets under 5 types of attacks. The results exhibit superior accuracy and resilience against adversarial attacks, all while maintaining comparatively low computational complexity. Among these, on the Non-IID CIFAR-10 dataset, our algorithm exhibited performance enhancements of 19.5% and 14.5%, respectively, in comparison to the state-of-the-art algorithm when dealing with two types of data poisoning attacks.

Feature selection is a crucial step in data mining to enhance model performance by reducing data dimensionality. However, the increasing dimensionality of collected data exacerbates the challenge known as the "curse of dimensionality", where computation grows exponentially with the number of dimensions. To tackle this issue, evolutionary computational (EC) approaches have gained popularity due to their simplicity and applicability. Unfortunately, the diverse designs of EC methods result in varying abilities to handle different data, often underutilizing and not sharing information effectively. In this paper, we propose a novel approach called PSO-based Multi-task Evolutionary Learning (MEL) that leverages multi-task learning to address these challenges. By incorporating information sharing between different feature selection tasks, MEL achieves enhanced learning ability and efficiency. We evaluate the effectiveness of MEL through extensive experiments on 22 high-dimensional datasets. Comparing against 24 EC approaches, our method exhibits strong competitiveness. Additionally, we have open-sourced our code on GitHub at https://github.com/wangxb96/MEL.