Zobrazeno 1 - 10
of 206
pro vyhledávání: '"Xiong, Yingfei"'
Unlike the flow structure of natural languages, programming languages have an inherent rigidity in structure and grammar.However, existing detection methods based on pre-trained models typically treat code as a natural language sequence, ignoring its
Externí odkaz:
http://arxiv.org/abs/2407.18877
Large Language Models (LLMs) have strong capabilities in code comprehension, but fine-tuning costs and semantic alignment issues limit their project-specific optimization; conversely, code models such CodeBERT are easy to fine-tune, but it is often d
Externí odkaz:
http://arxiv.org/abs/2406.05940
Proving equivalence between functional programs is a fundamental problem in program verification, which often amounts to reasoning about algebraic data types (ADTs) and compositions of structural recursions. Modern theorem provers address this proble
Externí odkaz:
http://arxiv.org/abs/2405.11535
Reducing test inputs that trigger bugs is crucial for efficient debugging. Delta debugging is the most popular approach for this purpose. When test inputs need to conform to certain specifications, existing delta debugging practice encounters a valid
Externí odkaz:
http://arxiv.org/abs/2402.04623
Autor:
Guo, Daya, Zhu, Qihao, Yang, Dejian, Xie, Zhenda, Dong, Kai, Zhang, Wentao, Chen, Guanting, Bi, Xiao, Wu, Y., Li, Y. K., Luo, Fuli, Xiong, Yingfei, Liang, Wenfeng
The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce the DeepSe
Externí odkaz:
http://arxiv.org/abs/2401.14196
The development of correct and efficient software can be hindered by compilation errors, which must be fixed to ensure the code's syntactic correctness and program language constraints. Neural network-based approaches have been used to tackle this pr
Externí odkaz:
http://arxiv.org/abs/2309.06771
Publikováno v:
IEEE Transactions on Software Engineering, vol. 50, no. 3, pp. 618-635, March 2024
Long patch validation time is a limiting factor for automated program repair (APR). Though the duality between patch validation and mutation testing is recognized, so far there exists no study of systematically adapting mutation testing techniques to
Externí odkaz:
http://arxiv.org/abs/2305.03955
With the widespread deployment of deep neural networks (DNNs), ensuring the reliability of DNN-based systems is of great importance. Serious reliability issues such as system failures can be caused by numerical defects, one of the most frequent defec
Externí odkaz:
http://arxiv.org/abs/2302.06086
Deep learning compilers help address difficulties of deploying deep learning models on diverse types of hardware. Testing deep learning compilers is highly crucial, because they are impacting countless AI applications that use them for model optimiza
Externí odkaz:
http://arxiv.org/abs/2302.00842
Dynamic programming is an important optimization technique, but designing efficient dynamic programming algorithms can be difficult for even professional programmers. Thinning, a technique developed for systematically deriving efficient dynamic progr
Externí odkaz:
http://arxiv.org/abs/2202.12208