Zhiyuan Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhiyuan Fan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ge Li
Shenzhen Graduate School, Peking University, Shenzhen, China
1 shared publication - Keyi Liang
School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China
1 shared publication - Wenpin Jiao
Peking University, Beijing, China
1 shared publication - Xue Jiang
Peking University
1 shared publication - Yihong Dong
Shanghai Jiao Tong University
1 shared publication - Zhi Jin
Peking University
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 11 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (7) , 1-24
Exploring Data-Efficient Adaptation of Large Language Models for Code Generation
Although Large Language Models (LLMs) have made significant progress in code generation, they still struggle with code generation tasks in specific scenarios. These scenarios usually necessitate the adaptation of LLMs to fulfill specific needs, but the limited training data available in practice leads to poor code generation performance. Therefore, how to effectively adapt LLMs to new scenarios with few training data is a major challenge for current code generation. In this article, we propose a novel adaptation approach named Data-Efficient adaptation with Error-Driven Learning (DEED) for code generation. D EED leverages the errors made by LLMs as learning opportunities, using error revision to overcome their own shortcomings, thus achieving efficient learning. Specifically, D EED involves identifying error code generated by LLMs, employing S elf-Revise for code revision, optimizing the model with revised code, and iteratively adapting the process for continuous improvement. Experimental results show that, compared to other mainstream fine-tuning approaches, D EED achieves superior performance with few training data, showing an average relative improvement of 46.2% in Pass@1 on multiple code generation benchmarks. We also validate the effectiveness of S elf-Revise, which generates revised code that optimizes the model more efficiently compared to the code samples from datasets. Moreover, D EED consistently demonstrates strong performance across various LLMs, underscoring its applicability.
- 11 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (7) , 1-24
Top Cited PapersOpen AccessExploring Data-Efficient Adaptation of Large Language Models for Code Generation
Although Large Language Models (LLMs) have made significant progress in code generation, they still struggle with code generation tasks in specific scenarios. These scenarios usually necessitate the adaptation of LLMs to fulfill specific needs, but the limited training data available in practice leads to poor code generation performance. Therefore, how to effectively adapt LLMs to new scenarios with few training data is a major challenge for current code generation. In this article, we propose a novel adaptation approach named Data-Efficient adaptation with Error-Driven Learning (DEED) for code generation. D EED leverages the errors made by LLMs as learning opportunities, using error revision to overcome their own shortcomings, thus achieving efficient learning. Specifically, D EED involves identifying error code generated by LLMs, employing S elf-Revise for code revision, optimizing the model with revised code, and iteratively adapting the process for continuous improvement. Experimental results show that, compared to other mainstream fine-tuning approaches, D EED achieves superior performance with few training data, showing an average relative improvement of 46.2% in Pass@1 on multiple code generation benchmarks. We also validate the effectiveness of S elf-Revise, which generates revised code that optimizes the model more efficiently compared to the code samples from datasets. Moreover, D EED consistently demonstrates strong performance across various LLMs, underscoring its applicability.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3972-3980
Video-to-Image Affordance Grounding via Visual Conceptual Learning
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3972-3980
Open AccessVideo-to-Image Affordance Grounding via Visual Conceptual Learning