Lune

Profiles2021-2026ORCID 0000-0003-0093-3292

Xing Hu

Zhejiang University Hangzhou

38Papers
1Last author
68Unique co-authors
3First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers38

  1. Actionable Warning Is Not Enough: Recommending Valid Actionable Warnings with Weak SupervisionAuthor 5 of 7ICSE 2026
  2. Automating Just-In-Time Python Type Annotation UpdatingAuthor 3 of 6ICSE 2026
  3. CREME: Robustness Enhancement of Code LLMs via Layer-Aware Model EditingAuthor 2 of 6ICSE 2026
  4. Depradar: Agentic Coordination for Context-Aware Defect Impact Analysis in Deep Learning LibrariesAuthor 2 of 7ICSE 2026
  5. Diffploit: Facilitating Cross-Version Exploit Migration for Open Source Library VulnerabilitiesAuthor 4 of 6ICSE 2026
  6. GUIMigrator: Semantics-Preserving Transpilation from Android XML to Compose and SwiftUIAuthor 2 of 4FSE 2026
  7. IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test MigrationAuthor 3 of 5FSE 2026
  8. Automated Unit Test RefactoringAuthor 2 of 4FSE 2025 · 6 citations
  9. Reasoning Runtime Behavior of a Program with LLM: How Far are We?Author 5 of 6ICSE 2025 · 5 citations
  10. Towards Better Answers: Automated Stack Overflow Post UpdatingAuthor 5 of 7ICSE 2025 · 4 citations
  11. Understanding Practitioners' Expectations on Clear Code Review CommentsAuthor 2 of 4ISSTA 2025 · 4 citations
  12. Less Is More: On the Importance of Data Quality for Unit Test GenerationAuthor 2 of 5FSE 2025 · 2 citations
  13. Code-DiTing: Automatic Evaluation of Code Generation without References or Test CasesAuthor 5 of 8ASE 2025 · 1 citation
  14. HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based FuzzingAuthor 3 of 4ASE 2025 · 1 citation
  15. Similar but Patched Code Considered Harmful: The Impact of Similar but Patched Code on Recurring Vulnerability Detection and How to Remove ThemAuthor 3 of 6ICSE 2025 · 1 citation
  16. RealisticCodeBench: Towards More Realistic Evaluation of Large Language Models for Code GenerationAuthor 4 of 6ASE 2025
  17. When AllClose Fails: Round-Off Error Estimation for Deep Learning ProgramsAuthor 2 of 6ASE 2025
  18. Code Search is All You Need? Improving Code Suggestions with Code SearchAuthor 2 of 5ICSE 2024 · 31 citations
  19. Learning in the Wild: Towards Leveraging Unlabeled Data for Effectively Tuning Pre-trained Code ModelsAuthor 5 of 6ICSE 2024 · 15 citations
  20. What Makes a High-Quality Training Dataset for Large Language Models: A Practitioners' PerspectiveAuthor 6 of 7ASE 2024 · 15 citations
  21. Exploiting Library Vulnerability via Migration Based Automating Test GenerationAuthor 2 of 7ICSE 2024 · 10 citations
  22. SelfPiCo: Self-Guided Partial Code Execution with LLMsAuthor 4 of 6ISSTA 2024 · 8 citations
  23. Towards More Practical Automation of Vulnerability AssessmentAuthor 4 of 6ICSE 2024 · 8 citations
  24. PPT4J: Patch Presence Test for Java BinariesAuthor 2 of 6ICSE 2024 · 6 citations
  25. Automating Zero-Shot Patch Porting for Hard ForksAuthor 4 of 6ISSTA 2024 · 5 citations
  26. Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context LearningAuthor 2 of 6FSE 2024 · 4 citations
  27. MUT: Human-in-the-Loop Unit Test MigrationAuthor 2 of 6ICSE 2024 · 3 citations
  28. MiniMon: Minimizing Android Applications with Intelligent Monitoring-Based DebloatingAuthor 3 of 10ICSE 2024 · 2 citations
  29. REACT: IR-Level Patch Presence Test for BinaryAuthor 2 of 4ASE 2024 · 2 citations
  30. Streamlining Java Programming: Uncovering Well-Formed Idioms with IdioMineAuthor 2 of 5ICSE 2024 · 2 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines