Zobrazeno 1 - 10
of 2 136
pro vyhledávání: '"WANG, YANLIN"'
Recently, an increasing number of AI-driven programming assistants powered by code LLMs have been integrated into various real-world software development environments, significantly boosting developer productivity. However, existing code generation b
Externí odkaz:
http://arxiv.org/abs/2412.18573
Autor:
Wang, Yanli, Wang, Yanlin, Wang, Suiquan, Guo, Daya, Chen, Jiachi, Grundy, John, Liu, Xilin, Ma, Yuchi, Mao, Mingzhi, Zhang, Hongyu, Zheng, Zibin
Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of
Externí odkaz:
http://arxiv.org/abs/2412.17744
Autor:
Gu, Wenchao, Shi, Ensheng, Wang, Yanlin, Du, Lun, Han, Shi, Zhang, Hongyu, Zhang, Dongmei, Lyu, Michael R.
Code retrieval, which retrieves code snippets based on users' natural language descriptions, is widely used by developers and plays a pivotal role in real-world software development. The advent of deep learning has shifted the retrieval paradigm from
Externí odkaz:
http://arxiv.org/abs/2412.11728
Code search is crucial for code reuse, enabling developers to efficiently locate relevant snippets. Current methods rely on encoder-based models, which suffer from limitations such as poor generalization and restricted input lengths. Decoder-only lar
Externí odkaz:
http://arxiv.org/abs/2410.22240
Code generation aims to automatically generate code from input requirements, significantly enhancing development efficiency. Recent large language models (LLMs) based approaches have shown promising results and revolutionized code generation task. De
Externí odkaz:
http://arxiv.org/abs/2409.20550
Autor:
Chen, Jiachi, Zhong, Qingyuan, Wang, Yanlin, Ning, Kaiwen, Liu, Yongkun, Xu, Zenan, Zhao, Zhe, Chen, Ting, Zheng, Zibin
The emergence of Large Language Models (LLMs) has significantly influenced various aspects of software development activities. Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and being abused
Externí odkaz:
http://arxiv.org/abs/2409.15154
Autor:
Wang, Yanlin, Zhong, Wanjun, Huang, Yanxian, Shi, Ensheng, Yang, Min, Chen, Jiachi, Li, Hui, Ma, Yuchi, Wang, Qianxiang, Zheng, Zibin
In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field. We find that many studies combining LLMs with SE hav
Externí odkaz:
http://arxiv.org/abs/2409.09030
Autor:
Yang, Shuo, Lin, Xingwei, Chen, Jiachi, Zhong, Qingyuan, Xiao, Lei, Huang, Renke, Wang, Yanlin, Zheng, Zibin
The rapid advancement of blockchain platforms has significantly accelerated the growth of decentralized applications (DApps). Similar to traditional applications, DApps integrate front-end descriptions that showcase their features to attract users, a
Externí odkaz:
http://arxiv.org/abs/2408.06037
Autor:
Wang, Yanlin, Guo, Lianghong, Shi, Ensheng, Chen, Wenqing, Chen, Jiachi, Zhong, Wanjun, Wang, Menghan, Li, Hui, Zhang, Hongyu, Lyu, Ziyu, Zheng, Zibin
Code search plays a crucial role in software development, enabling developers to retrieve and reuse code using natural language queries. While the performance of code search models improves with an increase in high-quality data, obtaining such data c
Externí odkaz:
http://arxiv.org/abs/2408.05542
Autor:
Zhang, Jiashuo, Shen, Yiming, Chen, Jiachi, Su, Jianzhong, Wang, Yanlin, Chen, Ting, Gao, Jianbo, Chen, Zhong
Ethereum has officially provided a set of system-level cryptographic APIs to enhance smart contracts with cryptographic capabilities. These APIs have been utilized in over 10% of Ethereum transactions, motivating developers to implement various on-ch
Externí odkaz:
http://arxiv.org/abs/2408.04939