Profiles2022-2026ORCID 0000-0003-4774-2434
Cuiyun Gao
Harbin Institute of Technology
37Papers
5Last author
58Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers37
- An Empirical Study of Knowledge Distillation for Code Understanding TasksAuthor 3 of 5ICSE 2026 · 1 citation
- SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep ReasoningAuthor 3 of 4ICSE 2026 · 1 citation
- Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM ReasoningAuthor 4 of 6ACL Findings 2026
- ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language ModelsAuthor 4 of 7ICML 2026
- Bridging User Feedback and System Diagnosis: Reproducing Mobile Performance Issues from ReviewsAuthor 3 of 3ISSTA 2026
- Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMsAuthor 5 of 7ACL 2026
- TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code DevelopmentAuthor 9 of 9ISSTA 2026
- Repo2Run: Automated Building Executable Environment for Code Repository at ScaleAuthor 5 of 5NeurIPS 2025 · 49 citations
- Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software EngineeringAuthor 4 of 6ISSTA 2025 · 27 citations
- Search-Based LLMs for Code OptimizationAuthor 2 of 4ICSE 2025 · 11 citations
- Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive SummarizationAuthor 5 of 6AAAI 2025 · 9 citations
- An Agent-based Evaluation Framework for Complex Code GenerationAuthor 5 of 5ASE 2025 · 7 citations
- Repository-Level Graph Representation Learning for Enhanced Security Patch DetectionAuthor 3 of 6ICSE 2025 · 1 citation
- Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type ErrorsAuthor 3 of 5ICSE 2024 · 39 citations
- Code Search is All You Need? Improving Code Suggestions with Code SearchAuthor 4 of 5ICSE 2024 · 31 citations
- Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided RefinementAuthor 5 of 7ACL Findings 2024 · 19 citations
- SCALE: Constructing Structured Natural Language Comment Trees for Software Vulnerability DetectionAuthor 2 of 5ISSTA 2024 · 17 citations
- Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code ModelsAuthor 3 of 6ICSE 2024 · 15 citations
- Split and Merge: Aligning Position Biases in LLM-based EvaluatorsAuthor 6 of 7EMNLP 2024 · 14 citations
- On Extracting Specialized Code Abilities from Large Language Models: A Feasibility StudyAuthor 7 of 8ICSE 2024 · 13 citations
- Less Cybersickness, Please: Demystifying and Detecting Stereoscopic Visual Inconsistencies in Virtual Reality AppsAuthor 7 of 8FSE 2024 · 10 citations
- XMoE: Sparse Models with Fine-grained and Adaptive Expert SelectionAuthor 5 of 6ACL Findings 2024 · 10 citations
- ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex CodeAuthor 3 of 7ASE 2024 · 7 citations
- Less is More? An Empirical Study on Configuration Issues in Python PyPI EcosystemAuthor 4 of 7ICSE 2024 · 5 citations
- A Systematic Evaluation of Large Code Models in API Suggestion: When, Which, and HowAuthor 3 of 7ASE 2024 · 4 citations
- Bridge and Hint: Extending Pre-trained Language Models for Long-Range CodeAuthor 2 of 5ISSTA 2024 · 4 citations
- What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs?Author 3 of 6ASE 2023 · 80 citations
- Vulnerability Detection with Graph Simplification and Enhanced Graph Representation LearningAuthor 3 of 6ICSE 2023 · 77 citations
- CCTEST: Testing and Repairing Code Completion SystemsAuthor 7 of 7ICSE 2023 · 49 citations
- Generative Type Inference for PythonAuthor 4 of 5ASE 2023 · 29 citations
Showing the 30 most recent indexed papers.
