33 citations · 48 across the 11 of their papers we have counts for
11 papers
Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
Zhensu Sun, Chengran Yang, Xiaoning Du +3
Large language models (LLMs) have shown exceptional performance in code generation and understanding tasks, yet their high computational costs hinder broader adoption. One importan…
Extending Fill-In-the-Middle with Instructions for Steerable Code Completion
Zhensu Sun, Chengran Yang, Chao Peng +4
Code completion models often fail when the developer's intent is under-specified in the code context. To mitigate this, developers frequently use natural language comments to clari…
FDI: Attack Neural Code Generation Systems through User Feedback Channel
Zhensu Sun, Xiaoning Du, Xiapu Luo +3
Neural code generation systems have recently attracted increasing attention to improve developer productivity and speed up software development. Typically, these systems maintain a…
Towards Agentic Runtime Healing
Zhensu Sun, Haotian Zhu, Bowen Xu +3
Self-healing systems have long been a focus of research, aiming to enable software to recover from unexpected runtime errors without human intervention. Traditional approaches rely…
AI Coders Are Among Us: Rethinking Programming Language Grammar Towards Efficient Code Generation
Zhensu Sun, Xiaoning Du, Zhou Yang +2
Artificial Intelligence (AI) models have emerged as another important audience for programming languages alongside humans and machines, as we enter the era of large language models…
When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
Zhensu Sun, Xiaoning Du, Fu Song +2
Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However…
Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?
Terry Yue Zhuo, Xiaoning Du, Zhenchang Xing +4
Recent breakthroughs in pre-trained code models, such as CodeBERT and Codex, have shown their superior performance in various downstream tasks. The correctness and unambiguity of A…
CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models
Zhensu Sun, Xiaoning Du, Fu Song +1
Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and pro…
Source Code Data Augmentation for Deep Learning: A Survey
Terry Yue Zhuo, Zhou Yang, Zhensu Sun +5
The increasingly popular adoption of deep learning models in many critical source code tasks motivates the development of data augmentation (DA) techniques to enhance training data…
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
Zhensu Sun, Xiaoning Du, Fu Song +4
Currently, large pre-trained language models are widely applied in neural code completion systems. Though large code models significantly outperform their smaller counterparts, aro…
CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning
Zhensu Sun, Xiaoning Du, Fu Song +2
Github Copilot, trained on billions of lines of public code, has recently become the buzzword in the computer science research and practice community. Although it is designed to he…