Search

Your search keyword '"Shi, Shiwei"' showing total 164 results
Start Over Author "Shi, Shiwei"
164 results on '"Shi, Shiwei"'

2. TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems

Author

Kong, Yilun, Ruan, Jingqing, Chen, Yihong, Zhang, Bin, Bao, Tianpeng, Shi, Shiwei, Du, Guoqing, Hu, Xiaoru, Mao, Hangyu, Li, Ziyue, Zeng, Xingyu, and Zhao, Rui

Subjects
Computer Science - Artificial Intelligence
Abstract

Large Language Models (LLMs) have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools that require a blend of task planning and the utilization of external tools, such as APIs. However, real-world complex systems present three prevalent challenges concerning task planning and tool usage: (1) The real system usually has a vast array of APIs, so it is impossible to feed the descriptions of all APIs to the prompt of LLMs as the token length is limited; (2) the real system is designed for handling complex tasks, and the base LLMs can hardly plan a correct sub-task order and API-calling order for such tasks; (3) Similar semantics and functionalities among APIs in real systems create challenges for both LLMs and even humans in distinguishing between them. In response, this paper introduces a comprehensive framework aimed at enhancing the Task Planning and Tool Usage (TPTU) abilities of LLM-based agents operating within real-world systems. Our framework comprises three key components designed to address these challenges: (1) the API Retriever selects the most pertinent APIs for the user task among the extensive array available; (2) LLM Finetuner tunes a base LLM so that the finetuned LLM can be more capable for task planning and API calling; (3) the Demo Selector adaptively retrieves different demonstrations related to hard-to-distinguish APIs, which is further used for in-context learning to boost the final performance. We validate our methods using a real-world commercial system as well as an open-sourced academic dataset, and the outcomes clearly showcase the efficacy of each individual component as well as the integrated framework.

Published
2023

3. TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage

Author

Ruan, Jingqing, Chen, Yihong, Zhang, Bin, Xu, Zhiwei, Bao, Tianpeng, Du, Guoqing, Shi, Shiwei, Mao, Hangyu, Li, Ziyue, Zeng, Xingyu, and Zhao, Rui

Subjects
Computer Science - Artificial Intelligence
Abstract

With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove insufficient for handling complex tasks which necessitate a combination of task planning and the usage of external tools. In this paper, we first propose a structured framework tailored for LLM-based AI Agents and discuss the crucial capabilities necessary for tackling intricate problems. Within this framework, we design two distinct types of agents (i.e., one-step agent and sequential agent) to execute the inference process. Subsequently, we instantiate the framework using various LLMs and evaluate their Task Planning and Tool Usage (TPTU) abilities on typical tasks. By highlighting key findings and challenges, our goal is to provide a helpful resource for researchers and practitioners to leverage the power of LLMs in their AI applications. Our study emphasizes the substantial potential of these models, while also identifying areas that need more investigation and improvement., Comment: Accepted in NeurIPS-2023 Workshop on Foundation Models for Decision Making

Published
2023

11. Efficient Fabrication of Bioinspired Flexible Pressure Sensors via Electrohydrodynamic Jet Printing Method.

Author

Shi, Shiwei, Abbas, Zeshan, Hu, Xiaoguang, Zheng, Xiaohu, Zhao, Xiangyu, Ren, Tongqun, and Wang, Dazhi

Abstract

Bioinspired microdevices have made significant strides in various applications including human motion and health detection. However, facile and highly efficient fabrication approach of flexible pressure sensors remains a great challenge. Herein, inspired by the gecko's foot structure, a flexible pressure sensor with microdomes structure is fabricated by tip‐assisted on‐demand electrohydrodynamic jet (EHD‐jet) printing method. Ascribed to the interlocking electrodes with microdome structure, 3D deformation rates are substantially enlarged. When the microdromes structure is under pressure, the resistivity of carbon nanotubes film coated on the surface of microdomes structure will change remarkably. By using the combined effect of assisted tip and ring focusing electrode, the influence and constraints on microstructure fabrication caused by substrate material and morphology are minimized. The desired uniform structures can be adjusted rapidly by changing the printing parameters and liquid properties. High length‐height ratio (0.64) of microdomes enhances sensitivity, with minimum detection limit is 2 Pa and response time is 40 ms. Finally, the bionic flexible sensor indicated excellent performance in capable of detecting pressure, sound vibrations and human motion. This work presents a new method for high‐efficiency fabrication micro‐nano patterns for flexible sensors inspired, which could be used in wearable tech and health monitoring. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

12. Mesoporous carbon hollow spheres loaded with Fe/Fe3C as efficient solar vapour generation materials.

Author

Gao, Jianfeng, Zhang, Hui, Zhang, Zhaoshun, Lin, Changcheng, Yang, Qun, Shi, Shiwei, Zuo, Xueqin, Jin, Shaowei, and Li, Guang

Subjects
SPHERES, ELECTRONIC excitation, PHOTOTHERMAL conversion, METAL nanoparticles, PHOTOTHERMAL effect, MAGNETIC particles, COMPOSITE materials
Abstract

Solar-driven interfacial evaporation technology has great potential in solving the global challenge of freshwater shortage. However, the selection of excellent photothermal conversion materials is a challenging task. To achieve efficient solar interface evaporation materials, we developed a new material loaded with Fe/Fe3C nanoparticles on mesoporous carbon hollow spheres (MCHSs). As an interfacial evaporation material, Fe/Fe3C@MCHS-x has an evaporation rate of 1.633 kg m−2 h−1 and an energy conversion efficiency of 94.17% (Fe/Fe3C@MCHS-2). The innovative introduction of magnetic particles into the evaporation unit allows the metal nanoparticles to absorb light at their resonance wavelength. This absorption leads to the excitation of electrons from the occupied state to the unoccupied state, and the diffusion of thermoelectrons leads to an increase of carriers, which makes the interface temperature rise rapidly. The composite material has a certain degree of organic pollution treatment capability along with high-efficiency water evaporation, which provides new ideas for interfacial evaporation material technology. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

18. A Novel Discriminative Weighted Pooling Feature for Multi-view Face Detection

Author

Shi, Shiwei, Shen, Jifeng, Zuo, Xin, Yang, Wankou, Diniz Junqueira Barbosa, Simone, Series editor, Chen, Phoebe, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Kotenko, Igor, Series editor, Liu, Ting, Series editor, Sivalingam, Krishna M., Series editor, Washio, Takashi, Series editor, Tan, Tieniu, editor, Li, Xuelong, editor, Chen, Xilin, editor, Zhou, Jie, editor, Yang, Jian, editor, and Cheng, Hong, editor

Published
2016
Full Text
View/download PDF

47. Effects of Electrodeposition Electrolyte Concentration on Microstructure, Optical Properties and Wettability of ZnO Nanorods

Author

Yao, Guang, primary, Zhang, Miao, additional, Lv, Jianguo, additional, Xu, Kai, additional, Shi, Shiwei, additional, Gong, Zezhou, additional, Tao, Jiajia, additional, Jiang, Xishun, additional, Yang, Lei, additional, Cheng, Yunlang, additional, He, Gang, additional, Chen, Xiaoshuang, additional, and Sun, Zhaoqi, additional

Published
2015
Full Text
View/download PDF

48. Auswirkungen des Beitritts Chinas zur WTO auf die Wettbewerbspolitik in China: Eine institutionenöknomische Betrachtung

Author

Shi, Shiwei

Subjects
O53, China, B52, L41, K21, ddc:320, P3, Wettbewerbspolitik, WTO, Antitrustgesetz, Transformation
Abstract

Dieses Paper beschäftigt sich mit dem Zusammenhang zwischen der Wettbewerbspolitik in China und dem WTO-Beitritt. Es wurde festgestellt, dass der WTO-Beitritt zur rechtlichen Verankerung der Wettbewerbspolitik in China wesentlich beigetragen hat. Die chinesische Transformation von der Planwirtschaft hin zur Marktwirtschaft verfolgt einen spezifischen Pfad: Gradualismus und selektive Öffnung. Die Öffnung als Motor der ordnungspolitischen Reform ist eine der wichtigsten Erfahrungen der Wirtschaftstransformation Chinas. Jedes Mal hat die weitere Öffnung der Wirtschaft die Transformation in China ein Stück vorangebracht. So wies die chinesische Transformation einen pfadabhängigen Charakter auf. Die Akzeptanz der WTOPrinzipien als weltweite marktwirtschaftliche Ordnungsregeln führte nicht nur zur Allokationseffizienz im Sinne besserer Nutzung von komparativen Vorteilen, sondern auch zur Anpassungseffizienz im Sinne des institutionellen Wandels.

Published
2009

Catalog

Books, media, physical & digital resources
See catalog results