activity
20222024
most citedSPT-Code: Sequence-to-Sequence Pre-Training for Learning Source Code Representations

11 citations · 32 across the 7 of their papers we have counts for

collaborators
Showing cs.SEShow all

7 papers · 1 filter

cs.SE2024

On Evaluating the Efficiency of Source Code Generated by LLMs

Changan Niu, Ting Zhang, Chuanyi Li +2

Recent years have seen the remarkable capabilities of large language models (LLMs) for code generation. Different from existing work that evaluate the correctness of the code gener…

cs.SE2023

FAIR: Flow Type-Aware Pre-Training of Compiler Intermediate Representations

Changan Niu, Chuanyi Li, Vincent Ng +2

While the majority of existing pre-trained models from code learn source code features such as code tokens and abstract syntax trees, there are some other works that focus on learn…

cs.SE2023★ 1 cited

Are We Ready to Embrace Generative AI for Software Q&A?

Bowen Xu, Thanh-Dat Nguyen, Thanh Le-Cong +8

Stack Overflow, the world's largest software Q&A (SQA) website, is facing a significant traffic drop due to the emergence of generative AI techniques. ChatGPT is banned by Stack Ov…

cs.SE2023★ 3 cited

CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models

Changan Niu, Chuanyi Li, Vincent Ng +1

Despite the recent advances showing that a model pre-trained on large-scale source code data is able to gain appreciable generalization capability, it still requires a sizeable amo…

cs.SE2023★ 7 cited

An Empirical Comparison of Pre-Trained Models of Source Code

Changan Niu, Chuanyi Li, Vincent Ng +3

While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our understa…

cs.SE2022★ 10 cited

Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code

Changan Niu, Chuanyi Li, Bin Luo +1

Recent years have seen the successful application of deep learning to software engineering (SE). In particular, the development and use of pre-trained models of source code has ena…