Ziwei Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ziwei Tang has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Bokai Xu
Computer Science, Tsinghua University, Beijing, China
1 shared publication - Bowen Li
Computer Science, Tsinghua University, Beijing, China
1 shared publication - Chaojun Xiao
Department of Computer Science and Technology, Institute for AI, Tsinghua University, Beijing, China
1 shared publication - Cheng Qian
Computer Science, Tsinghua University, Beijing, China
1 shared publication - Cheng Yang
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Chi Han
University of Illinois at Urbana-Champaign, Urbana, UNITED STATES
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 24 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (4) , 1-40
Tool Learning with Foundation Models
Humans possess an extraordinary ability to create and utilize tools. With the advent of foundation models, artificial intelligence systems have the potential to be equally adept in tool use as humans. This paradigm, which is dubbed as tool learning with foundation models , combines the strengths of tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. This article presents a systematic investigation and comprehensive review of tool learning. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research and formulate a general framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate generalization in tool learning. Finally, we discuss several open problems that require further investigation, such as ensuring trustworthy tool use, enabling tool creation with foundation models, and addressing personalization challenges. Overall, we hope this article could inspire future research in integrating tools with foundation models.
- 24 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (4) , 1-40
Top Cited PapersOpen AccessTool Learning with Foundation Models
Humans possess an extraordinary ability to create and utilize tools. With the advent of foundation models, artificial intelligence systems have the potential to be equally adept in tool use as humans. This paradigm, which is dubbed as tool learning with foundation models , combines the strengths of tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. This article presents a systematic investigation and comprehensive review of tool learning. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research and formulate a general framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate generalization in tool learning. Finally, we discuss several open problems that require further investigation, such as ensuring trustworthy tool use, enabling tool creation with foundation models, and addressing personalization challenges. Overall, we hope this article could inspire future research in integrating tools with foundation models.
- 14 March 2012
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 134 (12) , 5464-5467
Graphene Oxide Based Recyclable Dehydrogenation of Ammonia Borane within a Hybrid Nanostructure
The recyclable dehydrogenation of ammonia borane (AB) is achievable within a graphene oxide (GO)-based hybrid nanostructure, in which a combined modification strategy of acid activation and nanoconfinement by GO allows AB to release more than 2 equiv of pure H2 at temperatures below 100 °C. This process yields polyborazylene (PB) as a single product and, thus, promotes the chemical regeneration of AB via reaction of PB with hydrazine in liquid ammonia.
- 14 March 2012
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 134 (12) , 5464-5467
Graphene Oxide Based Recyclable Dehydrogenation of Ammonia Borane within a Hybrid Nanostructure
The recyclable dehydrogenation of ammonia borane (AB) is achievable within a graphene oxide (GO)-based hybrid nanostructure, in which a combined modification strategy of acid activation and nanoconfinement by GO allows AB to release more than 2 equiv of pure H2 at temperatures below 100 °C. This process yields polyborazylene (PB) as a single product and, thus, promotes the chemical regeneration of AB via reaction of PB with hydrazine in liquid ammonia.