Ai-assisted programming tasks using code embeddings and transformers

S Kotsiantis, V Verykios, M Tzagarakis - Electronics, 2024‏ - mdpi.com
This review article provides an in-depth analysis of the growing field of AI-assisted
programming tasks, specifically focusing on the use of code embeddings and transformers …

Peculiar: Smart contract vulnerability detection based on crucial data flow graph and pre-training techniques

H Wu, Z Zhang, S Wang, Y Lei, B Lin… - 2021 IEEE 32nd …, 2021‏ - ieeexplore.ieee.org
Smart contracts with natural economic attributes have been widely and rapidly developed in
various fields. However, the bugs and vulnerabilities in smart contracts have brought huge …

Context-aware code change embedding for better patch correctness assessment

B Lin, S Wang, M Wen, X Mao - ACM Transactions on Software …, 2022‏ - dl.acm.org
Despite the capability in successfully fixing more and more real-world bugs, existing
Automated Program Repair (APR) techniques are still challenged by the long-standing …

Learning to represent programs with heterogeneous graphs

K Zhang, W Wang, H Zhang, G Li, Z ** - Proceedings of the 30th IEEE …, 2022‏ - dl.acm.org
Code representation, which transforms programs into vectors with semantics, is essential for
source code processing. We have witnessed the effectiveness of incorporating structural …

How important are good method names in neural code generation? a model robustness perspective

G Yang, Y Zhou, W Yang, T Yue, X Chen… - ACM Transactions on …, 2024‏ - dl.acm.org
Pre-trained code generation models (PCGMs) have been widely applied in neural code
generation, which can generate executable code from functional descriptions in natural …

Learning to recommend method names with global context

F Liu, G Li, Z Fu, S Lu, Y Hao, Z ** - Proceedings of the 44th …, 2022‏ - dl.acm.org
In programming, the names for the program entities, especially for the methods, are the
intuitive characteristic for understanding the functionality of the code. To ensure the …

Predictive comment updating with heuristics and ast-path-based neural learning: A two-phase approach

B Lin, S Wang, Z Liu, X **a… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Just-in-time comment update is a promising way to reduce the burden of developers during
software maintenance and evolution. Existing approaches can be divided into two …

Better context makes better code language models: A case study on function call argument completion

H Pei, J Zhao, L Lausen, S Zha, G Karypis - Proceedings of the AAAI …, 2023‏ - ojs.aaai.org
Pretrained code language models have enabled great progress towards program synthesis.
However, common approaches only consider in-file local context and thus miss information …

Implant global and local hierarchy information to sequence based code representation models

K Zhang, Z Li, Z **, G Li - 2023 IEEE/ACM 31st International …, 2023‏ - ieeexplore.ieee.org
Source code representation with deep learning techniques is an important research field.
There have been many studies that learn sequential or structural information for code …

Peeler: Learning to effectively predict flakiness without running tests

Y Qin, S Wang, K Liu, B Lin, H Wu, L Li… - 2022 IEEE …, 2022‏ - ieeexplore.ieee.org
Regression testing is a widely adopted approach to expose change-induced bugs as well as
to verify the correctness/robustness of code in modern software development settings …