Chao-Zheng Wang

Most-cited papers

No more fine-tuning? an experimental evaluation of prompt tuning in code intelligence
Chao-Zheng Wang, Yuanhang Yang, Cuiyun Gao, Yun Peng +2 more
2022ESEC/SIGSOFT FSE205 citations Open access
Semantic Scholar
CCTEST: Testing and Repairing Code Completion Systems
Zong-Jie Li, Chao-Zheng Wang, Zhibo Liu, Hao Wang +3 more
2022International Conference on Software Engineering118 citations Open access
Semantic Scholar
Split and Merge: Aligning Position Biases in LLM-based Evaluators
Zong-Jie Li, Chao-Zheng Wang, Pingchuan Ma, Dao-Yuan Wu +3 more
2023Conference on Empirical Methods in Natural Language Processing110 citations Open access
Semantic Scholar
Protecting Intellectual Property of Large Language Model-Based Code Generation APIs via Watermarks
Zong-Jie Li, Chao-Zheng Wang, Shuai Wang, Cui-Yun Gao
2023Conference on Computer and Communications Security85 citations Open access
Semantic Scholar
CRaDLe: Deep Code Retrieval Based on Semantic Dependency Learning
Wenchao Gu, Zong-Jie Li, Cuiyun Gao, Chao-Zheng Wang +3 more
2020Neural Networks58 citations Open access
Semantic Scholar
Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach
Yuxuan Wan, Chao-Zheng Wang, Yi Dong, Wenxuan Wang +3 more
2024arXiv.org57 citations Open access
Semantic Scholar
Learning to Ask: When LLM Agents Meet Unclear Instruction
Wenxuan Wang, Juluan Shi, Zi-Xuan Ling, Yuk-Kit Chan +6 more
2024Conference on Empirical Methods in Natural Language Processing57 citations Open access
Semantic Scholar
On Extracting Specialized Code Abilities from Large Language Models: A Feasibility Study
Zong-Jie Li, Chao-Zheng Wang, Pingchuan Ma, Chaowei Liu +4 more
2023International Conference on Software Engineering49 citations Open access
Semantic Scholar
Prompt Tuning in Code Intelligence: An Experimental Evaluation
Chao-Zheng Wang, Yuanhang Yang, Cuiyun Gao, Yun Peng +2 more
2023IEEE Transactions on Software Engineering45 citations
Semantic Scholar
Enriching Query Semantics for Code Search with Reinforcement Learning
Chao-Zheng Wang, Zhen-Hao Nong, Cuiyun Gao, Zong-Jie Li +3 more
2021Neural Networks41 citations Open access
Semantic Scholar
ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code
Jia Feng, Jia-Chen Liu, Cui-Yun Gao, Chun-Yong Chong +3 more
2024International Conference on Automated Software Engineering39 citations Open access
Semantic Scholar
XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection
Yuanhang Yang, Shiyi Qi, Wenchao Gu, Chao-Zheng Wang +2 more
2024Annual Meeting of the Association for Computational Linguistics38 citations Open access
Semantic Scholar
The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
Shu-Zheng Gao, Chao-Zheng Wang, Cui-Yun Gao, Xiaoqi Jiao +3 more
2025arXiv.org34 citations
Semantic Scholar
Exploring Multi-Lingual Bias of Large Code Models in Code Generation
Chao-Zheng Wang, Zong-Jie Li, Cui-Yun Gao, Wenxuan Wang +5 more
2024ACM Transactions on Software Engineering and Methodology34 citations Open access
Semantic Scholar
Two Sides of the Same Coin: Exploiting the Impact of Identifiers in Neural Code Comprehension
Shu-Zheng Gao, Cuiyun Gao, Chao-Zheng Wang, Jun Sun +2 more
2022International Conference on Software Engineering34 citations Open access
Semantic Scholar
Label-Aware Distribution Calibration for Long-Tailed Classification
Chao-Zheng Wang, Shu-Zheng Gao, Pengyun Wang, Cuiyun Gao +3 more
2021IEEE Transactions on Neural Networks and Learning Systems34 citations Open access
Semantic Scholar
How Practitioners Expect Code Completion?
Chao-Zheng Wang, Jun-Hao Hu, Cui-Yun Gao, Yu Jin +4 more
2023ESEC/SIGSOFT FSE30 citations Open access
Semantic Scholar
REEF: A Framework for Collecting Real-World Vulnerabilities and Fixes
Chao-Zheng Wang, Zong-Jie Li, Y. Peña, Shu-Zheng Gao +4 more
2023International Conference on Automated Software Engineering28 citations Open access
Semantic Scholar
Keeping Pace with Ever-Increasing Data: Towards Continual Learning of Code Intelligence Models
Shu-Zheng Gao, Hongyu Zhang, Cuiyun Gao, Chao-Zheng Wang
2023International Conference on Software Engineering27 citations Open access
Semantic Scholar
Split and Merge: Aligning Position Biases in Large Language Model based Evaluators
Zong-Jie Li, Chao-Zheng Wang, Pingchuan Ma, Dao-Yuan Wu +3 more
2023arXiv.org27 citations Open access
Semantic Scholar
Generative Type Inference for Python
Yun Peng, Chao-Zheng Wang, Wenxuan Wang, Cuiyun Gao +1 more
2023International Conference on Automated Software Engineering27 citations Open access
Semantic Scholar
Adapting Everyday Manipulation Skills to Varied Scenarios
Paweł Gajewski, P. Ferreira, Georg Bartels, Chao-Zheng Wang +4 more
2018IEEE International Conference on Robotics and Automation25 citations Open access
Semantic Scholar
RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry
Chao-Zheng Wang, Ze-Zhou Yang, Shu-Zheng Gao, Cui-Yun Gao +4 more
2025SIGSOFT FSE Companion24 citations Open access
Semantic Scholar
Practitioners' Expectations on Code Completion
Chao-Zheng Wang, Junhao Hu, Cuiyun Gao, Yu Jin +4 more
2023arXiv.org23 citations Open access
Semantic Scholar
SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents
Shu-Zheng Gao, Wenhao Zeng, Zhaojian Yu, Jianqiao Wangni +4 more
2026arXiv.org20 citations
Semantic Scholar
CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
Man Ho Lam, Chao-Zheng Wang, Jen-Tse Huang, M. Lyu
2025Neural Information Processing Systems18 citations
Semantic Scholar
CODECRASH: Stress Testing LLM Reasoning under Structural and Semantic Perturbations
Man Ho Lam, Chao-Zheng Wang, Jen-Tse Huang, M. Lyu
2025arXiv.org17 citations
Semantic Scholar
A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and How
Chao-Zheng Wang, Shu-Zheng Gao, Cui-Yun Gao, Wenxuan Wang +3 more
2024International Conference on Automated Software Engineering17 citations Open access
Semantic Scholar
A Unified Framework for Mini-game Testing: Experience on WeChat
Chao-Zheng Wang, Hao-Chuan Lu, Cui-Yun Gao, Zong-Jie Li +2 more
2023ESEC/SIGSOFT FSE14 citations Open access
Semantic Scholar
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
Man Ho Lam, Chao-Zheng Wang, Hange Liu, Jingyu Xiao +4 more
2026arXiv.org13 citations
Semantic Scholar
Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility
Jia-Lun Cao, Yuk-Kit Chan, Zi-Xuan Ling, Wen-Xuan Wang +11 more
202512 citations
Semantic Scholar
Learning to Ask: When LLMs Meet Unclear Instruction
Wenxuan Wang, Juluan Shi, Chao-Zheng Wang, Cheryl Lee +3 more
2024arXiv.org12 citations
Semantic Scholar
VRPTEST: Evaluating Visual Referring Prompting in Large Multimodal Models
Zong-Jie Li, Chao-Zheng Wang, Chaowei Liu, Pingchuan Ma +3 more
2023arXiv.org10 citations
Semantic Scholar
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
Hongbin Zhang, Chao-Zheng Wang, Ke-Hai Chen, You-Cheng Pan +3 more
2026arXiv.org9 citations
Semantic Scholar
A Modified QuEChERS Method Using Single-Sorbent Combined with LC-MS/MS for Simultaneous Determination of Four Phenolic Pesticide Residues in Fruits and Vegetables
Yan Chen, Weikai Cai, Zhengfeng Lin, Yuan Ma +6 more
2025Journal of Food Composition and Analysis9 citations Open access
Semantic Scholar
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Yu Pan, Chao-Zheng Wang, Zekai Wu, Qi-Fan Wang +2 more
2025International Conference on Learning Representations9 citations
Semantic Scholar
SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
Yu-Qin Dai, Ninghang Gao, Wei Zhang, Jie Wang +5 more
2026Annual Meeting of the Association for Computational Linguistics8 citations
Semantic Scholar
How Should I Build A Benchmark? Revisiting Code-Related Benchmarks For LLMs
Jia-Lun Cao, Yuk-Kit Chan, Zi-Xuan Ling, Wen-Xuan Wang +11 more
2025arXiv.org8 citations
Semantic Scholar
Beyond PEFT: Layer-Wise Optimization for More Effective and Efficient Large Code Model Tuning
Chao-Zheng Wang, Jia Feng, Shu-Zheng Gao, Cui-Yun Gao +5 more
2025Proc. ACM Softw. Eng.8 citations Open access
Semantic Scholar
SPVR: syntax-to-prompt vulnerability repair based on large language models
Ruoke Wang, Zong-Jie Li, Cui-Yun Gao, Chao-Zheng Wang +2 more
2024International Conference on Automated Software Engineering8 citations Open access
Semantic Scholar
A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
Ze-Zhou Yang, Ting Peng, Cui-Yun Gao, Chao-Zheng Wang +2 more
2025IEEE International Conference on Software Maintenance and Evolution7 citations Open access
Semantic Scholar
On the Feasibility of Specialized Ability Extracting for Large Language Code Models
Zong-Jie Li, Chao-Zheng Wang, Pingchuan Ma, Chaowei Liu +3 more
2023arXiv.org7 citations Open access
Semantic Scholar
Enhancing Efficiency in Sparse Models with Sparser Selection
Yuanhang Yang, Shiyi Qi, Wenchao Gu, Chao-Zheng Wang +2 more
2024arXiv.org6 citations
Semantic Scholar
UMoE: Unifying Attention and FFN with Shared Experts
Yuanhang Yang, Chao-Zheng Wang, Jing Li
2025Neural Information Processing Systems5 citations
Semantic Scholar
SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
Shu-Zheng Gao, Chao-Zheng Wang, Cui-Yun Gao, M. Lyu
2025Proceedings of the 2026 IEEE/ACM 48th International Conference on Software Engineering4 citations Open access
Semantic Scholar
Predicting Compilation Resources for Adaptive Build in an Industrial Setting
Jun-Hao Hu, Chao-Zheng Wang, Hai-Liang Huang, Huang Luo +3 more
2023International Conference on Automated Software Engineering4 citations
Semantic Scholar
Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)
R. Lachmy, Ziyu Yao, Greg Durrett, Milos Gligoric +496 more
20214 citations Open access
Semantic Scholar
SAGE: A Service Agent Graph-guided Evaluation Benchmark
Lingfeng Shi, Yu-Qin Dai, Ziyi Wang, Ninghang Gao +6 more
2026arXiv.org3 citations
Semantic Scholar
On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation
Jiazhan Feng, Zhan Qin, Cui-Yun Gao, Rui-Qi Wang +3 more
2026arXiv.org3 citations
Semantic Scholar
REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Yisu Wang, Ming Wang, Haoyuan Song, Wen-Jie Huang +3 more
2025arXiv.org3 citations
Semantic Scholar