Search

Your search keyword '"LIU, GUOHONG"' showing total 738 results
Start Over Author "LIU, GUOHONG"
738 results on '"LIU, GUOHONG"'

1. Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Author

Li, Yuanchun, Wen, Hao, Wang, Weijun, Li, Xiangyu, Yuan, Yizhen, Liu, Guohong, Liu, Jiacheng, Xu, Wenxing, Wang, Xiang, Sun, Yi, Kong, Rui, Wang, Yile, Geng, Hanfei, Luan, Jian, Jin, Xuefeng, Ye, Zilong, Xiong, Guanjing, Zhang, Fan, Li, Xiang, Xu, Mengwei, Li, Zhijun, Li, Peng, Liu, Yang, Zhang, Ya-Qin, and Liu, Yunxin

Subjects
Computer Science - Human-Computer Interaction, Computer Science - Artificial Intelligence, Computer Science - Software Engineering
Abstract

Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming to help users efficiently obtain information and execute tasks, and provide users with more intelligent, convenient, and rich interaction experiences. With the development of smartphones and IoT, computing and sensing devices have become ubiquitous, greatly expanding the boundaries of IPAs. However, due to the lack of capabilities such as user intent understanding, task planning, tool using, and personal data management etc., existing IPAs still have limited practicality and scalability. Recently, the emergence of foundation models, represented by large language models (LLMs), brings new opportunities for the development of IPAs. With the powerful semantic understanding and reasoning capabilities, LLM can enable intelligent agents to solve complex problems autonomously. In this paper, we focus on Personal LLM Agents, which are LLM-based agents that are deeply integrated with personal data and personal devices and used for personal assistance. We envision that Personal LLM Agents will become a major software paradigm for end-users in the upcoming era. To realize this vision, we take the first step to discuss several important questions about Personal LLM Agents, including their architecture, capability, efficiency and security. We start by summarizing the key components and design choices in the architecture of Personal LLM Agents, followed by an in-depth analysis of the opinions collected from domain experts. Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges., Comment: https://github.com/MobileLLM/Personal_LLM_Agents_Survey

Published
2024

4. AutoDroid: LLM-powered Task Automation in Android

Author

Wen, Hao, Li, Yuanchun, Liu, Guohong, Zhao, Shanhui, Yu, Tao, Li, Toby Jia-Jun, Jiang, Shiqi, Liu, Yunhao, Zhang, Yaqin, and Liu, Yunxin

Subjects
Computer Science - Artificial Intelligence, Computer Science - Software Engineering
Abstract

Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalability due to the limited language understanding ability and the non-trivial manual efforts required from developers or end-users. The recent advance of large language models (LLMs) in language understanding and reasoning inspires us to rethink the problem from a model-centric perspective, where task preparation, comprehension, and execution are handled by a unified language model. In this work, we introduce AutoDroid, a mobile task automation system capable of handling arbitrary tasks on any Android application without manual efforts. The key insight is to combine the commonsense knowledge of LLMs and domain-specific knowledge of apps through automated dynamic analysis. The main components include a functionality-aware UI representation method that bridges the UI with the LLM, exploration-based memory injection techniques that augment the app-specific domain knowledge of LLM, and a multi-granularity query optimization module that reduces the cost of model inference. We integrate AutoDroid with off-the-shelf LLMs including online GPT-4/GPT-3.5 and on-device Vicuna, and evaluate its performance on a new benchmark for memory-augmented Android task automation with 158 common tasks. The results demonstrated that AutoDroid is able to precisely generate actions with an accuracy of 90.9%, and complete tasks with a success rate of 71.3%, outperforming the GPT-4-powered baselines by 36.4% and 39.7%. The demo, benchmark suites, and source code of AutoDroid will be released at url{https://autodroid-sys.github.io/}., Comment: Published in MobiCom 2024; Original title: "Empowering LLM to use Smartphone for Intelligent Task Automation"

Published
2023

41. Application of ICP-MS in the Innovation and Practice of Instrument Analysis Course - Taking the Determination of Cesium in Soil as an Example

Author

Li Daxue, Liu Guohong, Li Jian, Xiao Yanhua, Li Danping, and Xu Yuru

Subjects
Social Sciences
Abstract

Instrumental analysis is an important part of analytical chemistry, which plays a crucial role in cultivating the experimental operation ability of students in disciplines such as environment, geology, and medicine. Inductively coupled plasma mass spectrometry (ICP-MS) is currently an irreplaceable basic equipment in inorganic element analysis, and incorporating it into experimental teaching content is a requirement of the times. However, there is still a lack of application in this area. This article focuses on the graduate course “Modern Detection Technology”. The experimental course adopts a mixed teaching mode of pre class theoretical guidance and in class emphasis on practical operation. It combines theoretical and practical teaching organically, and takes the current hot topic of radioactive pollution as the problem orientation. The teaching mainly focuses on analyzing experimental design, instrument operation and use, sample measurement and result analysis, etc. The teaching mode and content of ICP-MS continuously explored to improve the quality of experimental teaching and enable students to comprehensively enhance their basic skill knowledge, scientific research literacy, and innovation awareness.

Published
2024
Full Text
View/download PDF

45. Advanced Mass-Spectra-Based Machine Learning for Predicting the Toxicity of Traditional Chinese Medicines

Author

Jia, Chen, Li, Xiaofang, Hu, Song, Liu, Guohong, Fang, Jiansong, Zhou, Xiaoxia, Yan, Xiliang, and Yan, Bing

Abstract

Traditional Chinese medicine (TCM) has been a cornerstone of health care for centuries, valued for its preventive and therapeutic properties. However, recent decades have revealed significant toxicological concerns associated with TCMs due to their complex chemical compositions. Traditional QSAR (quantitative structure–activity relationships) models, which predict toxicity based on chemical structures, face challenges with the intricate nature of TCM compounds. In this study, we effectively resolved this issue by correlating the toxicity of TCMs with advanced analytical descriptors from electron ionization mass spectra (EI-MS) data. The optimal classification model achieved a balanced accuracy of over 0.74. Through interpretable machine learning models, we identified specific toxic components, such as 13-hexyloxacyclotridec-10-en-2-one and loliolide. We applied molecular dynamics (MD) simulations to explore the interactions of identified toxic components with crucial protein targets, using hepatic cytochrome P450 3A4 as an example. This novel approach not only enhances our understanding of the toxicological profiles of TCMs but also maximizes their therapeutic benefits while minimizing adverse effects. More importantly, our findings support the application of analytical descriptor-based machine learning in predicting the toxicity of unknown mixtures in the real environment.

Published
2025
Full Text
View/download PDF

46. Federated Double Deep Q-Networks for Unbalanced Material Classification in Tactile Internet

Author

Liu, Guohong, Wang, Haoming, Wang, Cong, Yang, Lijing, Lv, Liheng, and Li, Yanjun

Abstract

Unbalanced material classification with visual–haptic data has become one of the primary concerns of tactile internet, existent classifiers suffer from performance degradation, since: the imbalance across both material classes and visual–haptic samples causes overestimation, some clients experience dropouts in global classifier training, and determining the theoretical convergence of a global classifier is challenging. This article develops the FedDDQN method to cope with the above issues. Specifically, for the server, the optimized federated learning scheme efficiently deals with unbalanced material classes and clients dropouts, and for clients, the adjusted double deep Q-networks (DDQN) effectively avoids the overestimation caused by unbalanced visual–haptic samples and improves representation ability. The convergence of FedDDQN are theoretically examined, using autonomous ordinary differential equation systems and Lyapunov stability. Numerical evaluations show that FedDDQN outperforms existing methods in both classification accuracy and computational complexity.

Published
2024
Full Text
View/download PDF

47. Attention-Enhanced Actor–Critic Learning for Household Nonintrusive Load Monitoring

Author

Liu, Guohong, Lv, Liheng, Wang, Cong, Wang, Haoming, Wan, Hui, and Yang, Lijing

Abstract

Nonintrusive load monitoring (NILM) estimates the power of all loads in a smart home, using only the aggregated power on the bus. By leveraging NILM, smart grids implement demand-side management and anomaly diagnosis, optimizing energy allocation, and reducing casualties. To date, some NILM methods have been well developed. However, their estimation accuracy can be further improved when dealing with loads with more than two states. For this reason, a method is proposed using an actor–critic architecture with an attention mechanism to improve accuracy. Both actor and critic are neural networks: the former transforms the aggregated power into estimated load power, while the latter provides feedback on the estimated load power. To capture the dependencies of diverse states, an attention mechanism is equipped to the actor to enhance its representational ability. The proposed method is evaluated on the U.K.-DALE and REDD datasets and demonstrates improved accuracy compared to state-of-the-art.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results